%0 Journal Article %@ 1438-8871 %I JMIR Publications %V 27 %N %P e76215 %T Comparing the Performance of Machine Learning Models and Conventional Risk Scores for Predicting Major Adverse Cardiovascular Cerebrovascular Events After Percutaneous Coronary Intervention in Patients With Acute Myocardial Infarction: Systematic Review and Meta-Analysis %A Yu,Min-Young %A Yoo,Hae Young %A Han,Ga In %A Kim,Eun-Jung %A Son,Youn-Jung %K machine learning %K mortality %K myocardial infarction %K patient readmission %K percutaneous coronary intervention %K prediction algorithm %K statistical model %D 2025 %7 18.7.2025 %9 %J J Med Internet Res %G English %X Background: Machine learning (ML) models may offer greater clinical utility than conventional risk scores, such as the Thrombolysis in Myocardial Infarction (TIMI) and Global Registry of Acute Coronary Events (GRACE) risk scores. However, there is a lack of knowledge on whether ML or traditional models are better at predicting the risk of major adverse cardiovascular and cerebrovascular events (MACCEs) in patients with acute myocardial infarction (AMI) who have undergone percutaneous coronary interventions (PCI). Objective: The aim of this study is to systematically review and critically appraise studies comparing the performance of ML models and conventional risk scores for predicting MACCEs in patients with AMI who have undergone PCI. Methods: Nine academic and electronic databases including PubMed, CINAHL, Embase, Web of Science, Scopus, ACM, IEEE, Cochrane, and Google Scholar were systematically searched from January 1, 2010, to December 31, 2024. We included studies of patients with AMI who underwent PCI, and predicted MACCE risk using ML algorithms or conventional risk scores. We excluded conference abstracts, gray literature, reviews, case reports, editorials, qualitative studies, secondary data analyses, and non-English publications. Our systematic search yielded 10 retrospective studies, with a total sample size of 89,702 individuals. Three validation tools were used to assess the validity of the published prediction models. Most included studies were assessed as having a low overall risk of bias. Results: The most frequently used ML algorithms were random forest (n=8) and logistic regression (n=6), while the most used conventional risk scores were GRACE (n=8) and TIMI (n=4). The most common MACCEs component was 1-year mortality (n=3), followed by 30-day mortality (n=2) and in-hospital mortality (n=2). Our meta-analysis demonstrated that ML-based models (area under the receiver operating characteristic curve: 0.88, 95% CI 0.86‐0.90; I²=97.8%; P<.001) outperformed conventional risk scores (area under the receiver operating characteristic curve: 0.79, 95% CI 0.75‐0.84; I²=99.6%; P<.001) in predicting mortality risk among patients with AMI who underwent PCI. Heterogeneity across studies was high. Publication bias was assessed using a funnel plot. The top-ranked predictors of mortality in both ML and conventional risk scores were age, systolic blood pressure, and Killip class. Conclusions: This review demonstrated that ML-based models had superior discriminatory performance compared to conventional risk scores for predicting MACCEs in patients with AMI who had undergone PCI. The most commonly used predictors were confined to nonmodifiable clinical characteristics. Therefore, health care professionals should understand the advantages and limitations of ML algorithms and conventional risk scores before applying them in clinical practice. We highlight the importance of incorporating modifiable factors—including psychosocial and behavioral variables—into prediction models for MACCEs following PCI in patients with AMI. In addition, further multicenter prospective studies with external validation are required to address validation limitations. Trial Registration: PROSPERO CRD42024557418; https://www.crd.york.ac.uk/PROSPERO/view/CRD42024557418 %R 10.2196/76215 %U https://www.jmir.org/2025/1/e76215 %U https://doi.org/10.2196/76215 %0 Journal Article %@ 2819-2044 %I JMIR Publications %V 3 %N %P e71675 %T Discovery of Novel Inhibitors of HMG-CoA Reductase Using Bioactive Compounds Isolated From Cochlospermum Species Through Computational Methods: Virtual Screening and Algorithm Validation Study %A Olatoye,Toba Isaac %K HMGR %K statins %K hypercholesterolemia %K cochlospermum %K phytochemicals %K molecular docking %K 3-hydroxy-3-methylglutaryl coenzyme-A reductase %D 2025 %7 10.7.2025 %9 %J JMIRx Bio %G English %X Background: Cholesterol biosynthesis is a critical pathway in cellular metabolism, with 3-hydroxy-3-methylglutaryl coenzyme-A reductase (HMGR) catalyzing its committed step. HMGR inhibition has been widely explored as a therapeutic target for managing hypercholesterolemia, and statins are the most commonly used competitive inhibitors. However, the search for novel, natural HMGR inhibitors remains a vital area of research, due to the adverse effects associated with long-term statin use. Cochlospermum planchonii and Cochlospermum tinctorium are West African medicinal plants traditionally used to treat metabolic disorders, including dyslipidemia. Despite their usefulness, the specific bioactive compounds responsible for these effects are currently poorly characterized, justifying further investigations. Objective: This study investigates the potential of phytochemicals from Cochlospermum planchonii and Cochlospermum tinctorium as natural inhibitors of human HMGR using molecular docking techniques. Methods: A total of 84 phytochemicals from 2 species of Cochlospermum as reported in literature, were evaluated as potential inhibitors of HMGR. Using DataWarrior software, their drug-likeness and ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) properties were screened in accordance with Lipinski’s Rule of Five. The 32 compounds that met the criteria were docked on PyRx against the HMG-binding site of HMGR, alongside atorvastatin (native ligand) and 6 known statins, which served as control ligands. Results: Docking analysis of their two best binding modes showed that 10 (31.3%) out of the 32 screened phytochemicals demonstrated strong binding affinities and interactions with the HMG-binding pocket (residues 682‐694) of HMGR, with binding energy (ΔG) scores ranging from −4.6 to −6.0 kcal/mol, comparable to or exceeding those of statins (−4.6 to −5.7 kcal/mol). Their docking scores (−13.272 to −32.103) also compared favorably with those of statins (−25.939 to −36.584). Interestingly, 3-O-methylellagic acid (ID_13915428) demonstrated the strongest interaction, forming 26 binding interactions with the HMG-binding pocket residues, more than any compound, including statins. One-way ANOVA of the mean and SEM of the binding affinity scores for the phytochemicals and statins (9 replicates each) indicated a statistically significant difference at P<.05 (total sample size n=153; actual P=.0001). Conclusions: This study is the first to virtually screen and identify specific bioactive compounds isolated from Cochlospermum planchonii and Cochlospermum tinctorium with potential cholesterol-lowering effects in humans. The findings not only support the traditional use of these plants in West Africa to manage dyslipidemia and other ailments, but also present the phytochemicals as promising drug candidates for further optimization as natural inhibitors of HMGR. However, while this study provides valuable computational insights into the molecular interactions of the compounds with HMGR, further advanced computational, in vitro, and in vivo studies are still necessary to validate their inhibitory potential and therapeutic applications. %R 10.2196/71675 %U https://bio.jmirx.org/2025/1/e71675 %U https://doi.org/10.2196/71675 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 14 %N %P e73389 %T A Higher-Than-Standard-Intensity International Normalized Ratio Goal for Patients Undergoing Mechanical Aortic Valve Replacement With Additional Thrombotic Risk Factors: Protocol for a Systematic Review and Meta-Analysis %A Kim,Myung-Rho %A Shaikh,Taha %A Wang,Shawn %A Taylor,Spencer %A Goel,Vidhani %A Khetarpal,Banveet Kaur %A Ahsan,Chowdhury %A Batra,Kavita %+ Department of Internal Medicine, Kirk Kerkorian School of Medicine, University of Nevada, Las Vegas, 1701 W Charleston Blvd, Las Vegas, 89102, United States, 1 702 382 0092, rlaaudfh87@gmail.com %K mechanical aortic valve replacement %K MAVR %K thromboembolic risk factors %K thromboembolism %K anticoagulation %K international normalized ratio %K warfarin %K Coumadin %K vitamin K antagonist %D 2025 %7 10.7.2025 %9 Protocol %J JMIR Res Protoc %G English %X Background: Lifelong anticoagulation therapy with vitamin K antagonists is recommended following mechanical aortic valve replacement (MAVR) to prevent valve thrombosis. Current guidelines recommend a standard international normalized ratio (INR) of 2.5 for patients with MAVR without additional thromboembolic risk factors, and a higher INR goal of 3.0 for those with conditions such as atrial fibrillation, prior thromboembolism, or left ventricular dysfunction. However, limited clinical evidence exists to guide anticoagulation intensity in this high-risk subgroup, necessitating a systematic review. Objective: We aimed to assess the safety and efficacy of higher-intensity INR goals (>3.0) compared to standard-intensity goals (approximately 2.5) in patients with MAVR with additional thromboembolic risk factors. Methods: This protocol describes a systematic review and meta-analysis following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines. A comprehensive literature search will be conducted across PubMed, Embase, and the Cochrane Library for studies published before December 18, 2024. Eligible studies include randomized controlled trials (RCTs), cohort studies, and follow-up studies involving adult patients with MAVR on warfarin therapy, stratified by the presence of additional thromboembolic risk factors. Non–English-language studies, case reports, editorials, and animal studies will be excluded. Results: The review will synthesize existing data to compare the risks and benefits of intensified anticoagulation in patients with MAVR with additional thromboembolic risk factors. Data analysis and manuscript preparation are scheduled for July-August 2025. Conclusions: This study will provide critical evidence on INR management in high-risk patients with MAVR, potentially informing future updates to clinical guidelines and optimizing the balance between thromboembolic prevention and bleeding risk. International Registered Report Identifier (IRRID): PRR1-10.2196/73389 %M 40638916 %R 10.2196/73389 %U https://www.researchprotocols.org/2025/1/e73389 %U https://doi.org/10.2196/73389 %U http://www.ncbi.nlm.nih.gov/pubmed/40638916 %0 Journal Article %@ 2369-1999 %I JMIR Publications %V 11 %N %P e71062 %T Perception and Counseling for Cardiac Health in Breast Cancer Survivors Using the Health Belief Model: Qualitative Analysis %A Marrison,Sarah Tucker %A Shungu,Nicholas %A Diaz,Vanessa %K cardiovascular health %K cancer survivorship %K lifestyle counseling %K breast cancer %K cancer survivors %D 2025 %7 3.7.2025 %9 %J JMIR Cancer %G English %X Background: Breast cancer survivors have increased cardiovascular risk compared to those without cancer history. Cardiovascular disease is the most common cause of death in breast cancer survivors. Cardiovascular risk in breast cancer survivors is impacted by both cancer treatment–associated effects and in risk factors for breast cancer and cardiovascular disease overlap. Strategies to improve screening for and management of cardiovascular disease in breast cancer survivors are needed to improve the delivery of survivorship care. Objective: This study aims to assess current cardiovascular risk counseling practices and perceived cardiovascular risk in breast cancer survivors. Methods: Semistructured interviews were conducted from May to December 2021 with breast cancer survivors identified as having a primary care clinician within an academic family medicine center in Charleston, South Carolina. The interview guide and content were developed using the Health Belief Model with a focus on cardiovascular risk behaviors, risk perception, and barriers to risk reduction. Analysis of categorical data was conducted by frequency and quantitative variables by mean and SD. Template analysis was performed for qualitative analysis. Outcome measures included self-reported history of cardiovascular disease, risk perception, and risk behaviors. Results: The average age of participants (n=19) was 54 (SD 7) years; 68% (13/19) were White and 32% (6/19) were Black or African American. Of the interviewed women, 90% (17/19) reported a personal history and 90% (17/19) reported a family history of cardiovascular disease. Only 53% (10/19) had previously reported receipt of cardiovascular counseling. Primary care most commonly provided counseling, followed by oncology. Among breast cancer survivors, 32% (6/19) reported being at increased cardiovascular risk, and 47% (9/19) were unsure of their relative cardiovascular risk. Factors affecting perceived cardiovascular risk included family history, cancer treatments, cardiovascular diagnoses, and lifestyle factors. Video (15/19, 79%) and SMS text messaging (13/19, 68%) were the most highly reported mechanisms through which breast cancer survivors requested to receive additional information and counseling on cardiovascular risk and risk reduction. Commonly reported barriers to risk reduction such as physical activity included time for meal planning and exercise, resources to support dietary and exercise changes, physical limitations, and competing responsibilities. Barriers specific to survivorship status included concerns for immune status during the COVID-19 pandemic, physical limitations associated with cancer treatment, and psychosocial aspects of cancer survivorship. Conclusions: Breast cancer survivors identified that factors associated with their cancer diagnosis and treatment both impacted their cardiovascular risk and introduced additional barriers to risk reduction. Potential strategies to improve counseling and awareness around cardiovascular risk include video and messaging platforms. Further risk reduction strategies should consider the unique challenges of cancer survivorship in delivery and implementation. %R 10.2196/71062 %U https://cancer.jmir.org/2025/1/e71062 %U https://doi.org/10.2196/71062 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 14 %N %P e71948 %T Intradialytic Changes and Prognostic Value of Ventriculo-Arterial Coupling in Patients With End-Stage Renal Disease: Protocol for an Observational Prospective Trial %A Salustri,Alessandro %A Tonti,Giovanni %A Pedrizzetti,Gianni %A Zhankorazova,Aizhan %A Khamitova,Zaukiya %A Toktarbay,Bauyrzhan %A Jumadilova,Dinara %A Khvan,Marina %A Galiyeva,Dinara %A Bekbossynova,Makhabbat %A Mukarov,Murat %A Kokoshko,Alexey %A Gaipov,Abduzhappar %+ Nazarbayev University School of Medicine, 5/1, Kerey, Zhanibek Khandar str, Astana, 010000, Kazakhstan, 7 (7172) 696523, alessandro.salustri@nu.edu.kz %K ventriculo-arterial coupling %K pressure-volume loop %K end-stage renal disease %K hemodialysis %K echocardiography %D 2025 %7 23.6.2025 %9 Protocol %J JMIR Res Protoc %G English %X Background: The acute effect of hemodialysis (HD) on left ventricular mechanics has been evaluated in several studies; however, their results are not consistent. Eventually, the heart and the arterial system behave as an interconnected system and not as isolated structures; thus, the evaluation of the interaction of cardiac contractility with the arterial system would provide a more comprehensive understanding of cardiovascular function and cardiac energetics. However, there have not been any studies demonstrating changes in terms of volumes, contractility, intraventricular pressure gradient distribution, and vascular properties in response to changes in loading conditions and their impact on the outcome in patients undergoing HD. Recently, a noninvasive method for assessing left ventricular pressure-volume loop and ventriculo-arterial coupling (VAC) from feature-tracking cardiac magnetic resonance or echocardiography has been proposed. We believe that this method allows a comprehensive evaluation of the hemodynamic status of the patients undergoing HD, including the relationships between cardiac function and arterial elastance, and might provide prognostic information. Objective: The primary objective of this study is to evaluate changes in VAC before and after a HD session. The secondary objective is to assess the prognostic value of VAC parameters in predicting adverse outcomes. Methods: A 2D transthoracic echocardiogram will be performed before and after a HD session in patients with end-stage renal disease. We target to enroll 323 patients. Images will be analyzed with advanced software based on speckle-tracking, able to reconstruct the pressure-volume loop. From the pressure-volume loop, arterial (Ea) and ventricular (Ees) elastance will be derived. VAC will be calculated as the Ea/Ees ratio. Patients will be followed up for 18 months. Primary endpoints will be a composite of all causes of death, nonfatal myocardial infarction, and hospitalization due to worsening heart failure. Results: The study received funding in August 2024, with patients’ enrollment scheduled to take place from January 1 to June 30, 2025. Data analysis will start in April 2025 and is expected to continue until June 2026. The findings of the study are tentatively planned for publication in the winter of 2027. Conclusions: This study will provide data on the changes in VAC induced by HD and their potential prognostic value. This assessment could be useful for tailoring volume depletion during HD and to improve patients’ outcomes. Trial Registration: ClinicalTrials.gov NCT06622928; https://clinicaltrials.gov/study/NCT06622928 International Registered Report Identifier (IRRID): PRR1-10.2196/71948 %M 40550123 %R 10.2196/71948 %U https://www.researchprotocols.org/2025/1/e71948 %U https://doi.org/10.2196/71948 %U http://www.ncbi.nlm.nih.gov/pubmed/40550123 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 13 %N %P e68898 %T The Use of Machine Learning for Analyzing Real-World Data in Disease Prediction and Management: Systematic Review %A Alhumaidi,Norah Hamad %A Dermawan,Doni %A Kamaruzaman,Hanin Farhana %A Alotaiq,Nasser %+ Health Sciences Research Center, Imam Mohammad ibn Saud Islamic University, Othman Bin Affan Rd. Al-Nada 13317, Riyadh, Saudi Arabia, 966 50 411 9153, naalotaiq@imamu.edu.sa %K machine learning %K big data %K real-world data %K disease prediction %K health care management %K real-world evidence %K artificial intelligence %K AI %D 2025 %7 19.6.2025 %9 Review %J JMIR Med Inform %G English %X Background: Machine learning (ML) and big data analytics are rapidly transforming health care, particularly disease prediction, management, and personalized care. With the increasing availability of real-world data (RWD) from diverse sources, such as electronic health records (EHRs), patient registries, and wearable devices, ML techniques present substantial potential to enhance clinical outcomes. Despite this promise, challenges such as data quality, model transparency, generalizability, and integration into clinical practice persist. Objective: This systematic review aims to examine the use of ML for analyzing RWD in disease prediction and management, identifying the most commonly used ML methods, prevalent disease types, study designs, and the sources of real-world evidence (RWE). It also explores the strengths and limitations of current practices, offering insights for future improvements. Methods: A comprehensive search was conducted following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to identify studies using ML techniques for analyzing RWD in disease prediction and management. The search focused on extracting data regarding the ML algorithms applied; disease categories studied; types of study designs (eg, clinical trials and cohort studies); and the sources of RWE, including EHRs, patient registries, and wearable devices. Studies published between 2014 and 2024 were included to ensure the analysis of the most recent advances in the field. Results: This review identified 57 studies that met the inclusion criteria, with a total sample size of >150,000 patients. The most frequently applied ML methods were random forest (n=24, 42%), logistic regression (n=21, 37%), and support vector machines (n=18, 32%). These methods were predominantly used for predictive modeling across disease areas, including cardiovascular diseases (n=19, 33%), cancer (n=9, 16%), and neurological disorders (n=6, 11%). RWE was primarily sourced from EHRs, patient registries, and wearable devices. A substantial portion of studies (n=38, 67%) focused on improving clinical decision-making, patient stratification, and treatment optimization. Among these studies, 14 (25%) focused on decision-making; 12 (21%) on health care outcomes, such as quality of life, recovery rates, and adverse events; and 11 (19%) on survival prediction, particularly in oncology and chronic diseases. For example, random forest models for cardiovascular disease prediction demonstrated an area under the curve of 0.85 (95% CI 0.81-0.89), while support vector machine models for cancer prognosis achieved an accuracy of 83% (P=.04). Despite the promising outcomes, many (n=34, 60%) studies faced challenges related to data quality, model interpretability, and ensuring generalizability across diverse patient populations. Conclusions: This systematic review highlights the significant potential of ML and big data analytics in health care, especially for improving disease prediction and management. However, to fully realize the benefits of these technologies, future research must focus on addressing the challenges of data quality, enhancing model transparency, and ensuring the broader applicability of ML models across diverse populations and clinical settings. %M 40537090 %R 10.2196/68898 %U https://medinform.jmir.org/2025/1/e68898 %U https://doi.org/10.2196/68898 %U http://www.ncbi.nlm.nih.gov/pubmed/40537090 %0 Journal Article %@ 2292-9495 %I JMIR Publications %V 12 %N %P e71103 %T Collecting at-Home Biometric Measures for Longitudinal Research From the i3C: Feasibility and Acceptability Study %A Russell,Marta %A Cain,Erin %A Bazzano,Lydia %A De Anda,Ileana %A Woo,Jessica G %A Urbina,Elaine M %K mHealth %K cardiovascular risk factors %K epidemiology %K wearable devices %K feasibility %K acceptability %K biometric %D 2025 %7 18.6.2025 %9 %J JMIR Hum Factors %G English %X Background: The use of individual wearable devices or internet-based applications to collect biometric data from research participants is popular, but several devices may be needed to replace a full set of research measurements. Objective: In this study, we assessed the feasibility of a “Virtual Home Clinic” within the context of long-term epidemiologic studies. Methods: Participants from 3 study cohorts were recruited. Devices were sent to the home to measure anthropometrics, resting metabolic rate, blood pressure (BP), heart rate (HR), heart rhythm, oxygen saturation, glucose, total cholesterol, physical activity, diet, sleep duration or quality, and arterial stiffness over the course of 1 week. Stool and saliva were also self-collected for microbiome, DNA, and cotinine. Feasibility and acceptability of collecting measurements using home devices were assessed. Results: A total of 134 participants were enrolled (87% female, 31% Black; mean age 54.2, SD 8.4 years). Furthermore, 91% (N=122) performed at least one of the home tests. At least two-thirds of participants were able to complete all of the requested readings for glucose, electrocardiogram, BP, diet record, and resting metabolic rate. The scale that measured weight, body composition, and pulse wave velocity (PWV) was more difficult to use (113/134, 84% participants recorded at least one weight and 84/134, 63% recorded a PWV). The device to measure total cholesterol was least successful (32/134, 24% participants completed all readings, 72/134, 54% provided at least one result). Return of biospecimens was highly successful (115/134, 86% returned saliva and 113/134, 84% returned stool). Of 95 who responded to the user acceptability survey, 38 (40%) participants preferred home assessment, 36 (38%) preferred clinic, and 21 (22%) did not have a preference. The mean user acceptability score across devices for ease of use was 4.3 (SD 1.0), for instructions was 4.5 (SD 0.7), and for time to use was 3.9 (SD 1.1; scale of 1‐5, with higher scores indicating greater acceptability). The study team documented several regulatory or IT, connectivity or account, data retrieval, and logistical issues encountered during the study. Conclusions: Despite several complications involved with managing multiple devices and applications, most of the components of the virtual home clinic were reasonably feasible and acceptable to participants. %R 10.2196/71103 %U https://humanfactors.jmir.org/2025/1/e71103 %U https://doi.org/10.2196/71103 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 14 %N %P e71314 %T Real-World Characteristics and Treatment Patterns of Patients With Transthyretin Amyloid Cardiomyopathy: Protocol for a Multicountry Disease Registry Study %A Lin,Yen-Hung %A Chou,Hsu-Wen %A Tsai,Sarah %A Gomez,Roy %+ , Emerging Markets Asia Specialty Care, Global Medical Affairs, Pfizer Private Limited, 80 Pasir Panjang Rd, #16-81/82 Mapletree Business City II, Singapore, 117372, Singapore, 65 6403 8888, Roy.Gomez@pfizer.com %K ATTR-CM %K transthyretin amyloid cardiomyopathy %K registry %K real world data %D 2025 %7 6.6.2025 %9 Protocol %J JMIR Res Protoc %G English %X Background: Transthyretin amyloid cardiomyopathy (ATTR-CM) is a systemic amyloidosis disorder with early clinical manifestations similar to other heart conditions, which complicates its diagnosis and management. The disease’s insidious nature and its progression to heart failure emphasize the critical need for enhanced recognition and understanding of its clinical landscape. Objective: This study aimed to understand the natural history and current treatment patterns for managing ATTR-CM in a diverse Asian cohort from Taiwan, Hong Kong, and Malaysia. Methods: This study is a multicenter, noninterventional disease registry that plans to enroll patients diagnosed with ATTR-CM across approximately 17 sites in Taiwan, Hong Kong, and Malaysia. Almost 350 patients with a documented diagnosis of ATTR‑CM after June 1, 2019, will be enrolled in the study. Deceased patients will be enrolled without the need for consent in accordance with applicable regulations. Their data will be gathered retrospectively through a 1-time review of their medical records, where permissible. Data related to clinical characteristics, treatment, and outcomes will be collected for each patient during the routine clinical practice while adhering to local standards of care. The end of data collection is planned for at least 12 months after the end of the enrollment period. Results: As of March 16, 2025, ethical approvals for this study have been obtained or are under review at multiple sites across Taiwan, Hong Kong, and Malaysia. The study commenced on October 1, 2024, with the first participant’s first visit and so far, 59 patients have been recruited: 35 from National Taiwan University Hospital (Taiwan), 13 from Taipei Veterans General Hospital (Taiwan), 2 from China Medical University Hospital (Taiwan), 2 from Sarawak Heart Center (Malaysia), and 7 from Queen Mary Hospital (Hong Kong). An interim report is scheduled for completion by December 31, 2025. The end of data collection, marked by the last participant’s visit, is planned for October 1, 2027, and the final study report is expected to be finalized by June 1, 2028. Once established, the database will serve as a comprehensive resource for analyzing baseline characteristics, treatment patterns, and outcomes in patients with ATTR-CM from diverse health care systems. Conclusions: This research will aid in understanding the demographic, clinical, and therapeutic patterns of ATTR-CM in Taiwan, Hong Kong, and Malaysia. This registry may influence advancements in early detection, diagnosis, and tailored treatment strategies in ATTR-CM. Trial Registration: ClinicalTrials.gov NCT06651073; https://clinicaltrials.gov/study/NCT06651073 International Registered Report Identifier (IRRID): DERR1-10.2196/71314 %M 40479720 %R 10.2196/71314 %U https://www.researchprotocols.org/2025/1/e71314 %U https://doi.org/10.2196/71314 %U http://www.ncbi.nlm.nih.gov/pubmed/40479720 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 13 %N %P e68138 %T Trajectory-Ordered Objectives for Self-Supervised Representation Learning of Temporal Healthcare Data Using Transformers: Model Development and Evaluation Study %A Amirahmadi,Ali %A Etminani,Farzaneh %A Björk,Jonas %A Melander,Olle %A Ohlsson,Mattias %+ Center for Applied Intelligent Systems Research in Health, Halmstad University, Kristian IV:s väg 3, Halmstad, 30118, Sweden, 46 03516 7100, ali.amirahmadi@hh.se %K patient trajectories %K disease prediction %K representation learning %K masked language mode %K deep learning %K BERT %K electronic health record %K language mode %K transformer %K heart failure %K alzheimer disease %K prolonged health of stay %K effectiveness %K temporal %D 2025 %7 4.6.2025 %9 Original Paper %J JMIR Med Inform %G English %X Background: The growing availability of electronic health records (EHRs) presents an opportunity to enhance patient care by uncovering hidden health risks and improving informed decisions through advanced deep learning methods. However, modeling EHR sequential data, that is, patient trajectories, is challenging due to the evolving relationships between diagnoses and treatments over time. Significant progress has been achieved using transformers and self-supervised learning. While BERT-inspired models using masked language modeling (MLM) capture EHR context, they often struggle with the complex temporal dynamics of disease progression and interventions. Objective: This study aims to improve the modeling of EHR sequences by addressing the limitations of traditional transformer-based approaches in capturing complex temporal dependencies. Methods: We introduce Trajectory Order Objective BERT (Bidirectional Encoder Representations from Transformers; TOO-BERT), a transformer-based model that advances the MLM pretraining approach by integrating a novel TOO to better learn the complex sequential dependencies between medical events. TOO-Bert enhanced the learned context by MLM by pretraining the model to distinguish ordered sequences of medical codes from permuted ones in a patient trajectory. The TOO is enhanced by a conditional selection process that focus on medical codes or visits that frequently occur together, to further improve contextual understanding and strengthen temporal awareness. We evaluate TOO-BERT on 2 extensive EHR datasets, MIMIC-IV hospitalization records and the Malmo Diet and Cancer Cohort (MDC)—comprising approximately 10 and 8 million medical codes, respectively. TOO-BERT is compared against conventional machine learning methods, a transformer trained from scratch, and a transformer pretrained on MLM in predicting heart failure (HF), Alzheimer disease (AD), and prolonged length of stay (PLS). Results: TOO-BERT outperformed conventional machine learning methods and transformer-based approaches in HF, AD, and PLS prediction across both datasets. In the MDC dataset, TOO-BERT improved HF and AD prediction, increasing area under the receiver operating characteristic curve (AUC) scores from 67.7 and 69.5 with the MLM-pretrained Transformer to 73.9 and 71.9, respectively. In the MIMIC-IV dataset, TOO-BERT enhanced HF and PLS prediction, raising AUC scores from 86.2 and 60.2 with the MLM-pretrained Transformer to 89.8 and 60.4, respectively. Notably, TOO-BERT demonstrated strong performance in HF prediction even with limited fine-tuning data, achieving AUC scores of 0.877 and 0.823, compared to 0.839 and 0.799 for the MLM-pretrained Transformer, when fine-tuned on only 50% (442/884) and 20% (176/884) of the training data, respectively. Conclusions: These findings demonstrate the effectiveness of integrating temporal ordering objectives into MLM-pretrained models, enabling deeper insights into the complex temporal relationships inherent in EHR data. Attention analysis further highlights TOO-BERT’s capability to capture and represent sophisticated structural patterns within patient trajectories, offering a more nuanced understanding of disease progression. %M 40465350 %R 10.2196/68138 %U https://medinform.jmir.org/2025/1/e68138 %U https://doi.org/10.2196/68138 %U http://www.ncbi.nlm.nih.gov/pubmed/40465350 %0 Journal Article %@ 2561-326X %I JMIR Publications %V 9 %N %P e71408 %T Engagement With a Smartphone-Delivered Dietary Education Intervention and Its Relation to Dietary Intake and Cardiometabolic Risk Markers in People With Type 2 Diabetes: Secondary Analysis of a Randomized Controlled Trial %A Sjoblom,Linnea %A Stenbeck,Freja %A Trolle Lagerros,Ylva %A Hantikainen,Essi %A Bonn,Stephanie E %K adherence %K dietary change %K diabetes mellitus %K type 2 diabetes mellitus %K healthy diet %K mHealth %K smartphone app %K user engagement %K mobile phone %D 2025 %7 30.5.2025 %9 %J JMIR Form Res %G English %X Background: Mobile health (mHealth) interventions offer a promising way to support healthy lifestyle habits, but effectiveness depends on user engagement. Maintaining high user engagement in app-based interventions is important, yet challenging. Objective: We aimed to examine the association between user engagement with an app-based dietary education for people with type 2 diabetes and changes in diet quality, dietary intake, and clinical measures. Methods: In this randomized clinical trial, people with type 2 diabetes were recruited within primary care and randomized 1:1 to a 12-week smartphone-delivered app-based dietary education or control group. Participants were followed up after 3, 6, and 12 months. Dietary intake was assessed using a food frequency questionnaire. The control group received the app at the 3-month follow-up. User engagement was analyzed among all participants. Categories of high (100%), moderate (50%‐99.9%), and low (<50%) user engagement were created based on the percentage of activities completed in the app. We used paired t tests to compare mean changes in diet quality, dietary intake, and clinical markers within user engagement groups, and fitted linear regression models to analyze differences in change between groups. Results: Data from 119 participants (60.5%, 72/119 men) were analyzed. The mean age at baseline was 63.2 (SD 10.3) years and mean BMI was 30.1 (SD 5.1) kg/m2. User engagement was high with an average of 77.1% of app activities completed. More than half (53.8%, 64/119) of the users showed high user engagement, 21.8% (26/119) moderate, and 24.4% (29/119) low. Directly following the app-based education, a significant difference in change was seen for whole grains (β=20.4, 95%CI 0.57‐40.3) in participants with high user engagement compared to the low user engagement group who decreased their intake (P=.03). At follow-up after 6 to 9 months after completed education, significant differences in change were seen for fiber, wholegrains, carbohydrates, saturated fat, sodium, and total energy in the moderate compared with the low engagement group, and a significant difference in change was seen for carbohydrates in the high, compared with the low, user engagement group. Conclusions: User engagement was generally high for the smartphone-based dietary education, suggesting that an app targeting dietary habits is feasible to use. Those with higher user engagement seem to maintain healthier dietary behaviours over time, compared to those with low user engagement. Future mHealth interventions should focus on ways to engage those with low interest. Trial Registration: ClinicalTrials.gov NCT03784612; https://www.clinicaltrials.gov/study/NCT03784612 International Registered Report Identifier (IRRID): RR2-10.2196/24422 %R 10.2196/71408 %U https://formative.jmir.org/2025/1/e71408 %U https://doi.org/10.2196/71408 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 13 %N %P e72349 %T Machine Learning for the Prediction of Acute Kidney Injury in Critically Ill Patients With Coronary Heart Disease: Algorithm Development and Validation %A Li,Yike %A Xiao,Mingyang %A Li,Yaqian %A Lv,Lulu %A Zhang,Shanshan %A Liu,Yuhui %A Zhang,Juan %+ , The Second Clinical Medical School, Zhengzhou University, No 2 Jingba Road, Jinshui District, Zhengzhou, China, 86 15038180882, zj78420@163.com %K coronary heart disease %K coronary artery disease %K acute kidney injury %K machine learning %K MIMIC-IV database %D 2025 %7 28.5.2025 %9 Original Paper %J JMIR Med Inform %G English %X Background: Acute kidney injury (AKI) frequently occurs in critically ill patients with coronary heart disease (CHD), and its development markedly elevates mortality rates and prolongs hospitalization duration. Early AKI prediction is crucial for timely intervention and amelioration of patient outcomes. Objective: This study aimed to develop and verify a clinical prediction model for the occurrence of AKI upon admission in the critically ill population with CHD through machine learning (ML). Methods: Data from the MIMIC-IV (Medical Information Mart for Intensive Care IV) version 2.2 database were gathered and included information about critically ill individuals with CHD in the intensive care unit (ICU). The dataset was randomized into a training set (70%) and a testing set (30%). Least absolute shrinkage and selection operator (LASSO) regression was used for feature variable selection. ML models, including logistic regression (LR), decision tree (DT), naive Bayes (NB), random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM), were constructed using 13 variables in the training set. The 6 models were compared in the testing set to identify the best-performing model. Subsequently, the model was assessed using calibration curve analysis and decision curve analysis (DCA). External validation was conducted using data from the Second Affiliated Hospital of Zhengzhou University. Ultimately, the predictive model was interpreted via Shapley Additive Explanation (SHAP) values. Results: In total, 2711 patients with CHD admitted to the ICU were selected, with 1809 (66.7%) having AKI. XGBoost exhibited the best performance regarding discrimination (area under the receiver operating characteristic curve [AUROC]=0.765, 95% CI 0.731-0.800), accuracy (0.725), and sensitivity (0.759). External validation using a cohort of 226 patients confirmed the strong generalizability of the XGBoost model (AUROC=0.835, 95% CI 0.782-0.887). Feature importance analyses derived from SHAP values, DT, RF, and XGBoost consistently identified 5 key predictors associated with the development of AKI: mechanical ventilation, use of antiplatelet agents, age, N-terminal pro–B-type natriuretic peptide (NT-proBNP) levels, and acute physiology score III (APSIII). Conclusions: ML models can serve as reliable tools for forecasting AKI in the critically ill population with CHD. The XGBoost model is highly accurate and may aid doctors in identifying high-risk individuals for early intervention to lower mortality. %M 40383933 %R 10.2196/72349 %U https://medinform.jmir.org/2025/1/e72349 %U https://doi.org/10.2196/72349 %U http://www.ncbi.nlm.nih.gov/pubmed/40383933 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 14 %N %P e71726 %T Coronary Computed Tomographic Angiography to Optimize the Diagnostic Yield of Invasive Angiography for Low-Risk Patients Screened With Artificial Intelligence: Protocol for the CarDIA-AI Randomized Controlled Trial %A Petch,Jeremy %A Tabja Bortesi,Juan Pablo %A Sheth,Tej %A Natarajan,Madhu %A Pinilla-Echeverri,Natalia %A Di,Shuang %A Bangdiwala,Shrikant I %A Mosleh,Karen %A Ibrahim,Omar %A Bainey,Kevin R %A Dobranowski,Julian %A Becerra,Maria P %A Sonier,Katie %A Schwalm,Jon-David %+ , Centre for Data Science and Digital Health, Hamilton Health Sciences, 175 Longwood Road South, Suite 207, Hamilton, ON, L8P 0A1, Canada, 1 4164769039, jeremy.petch@utoronto.ca %K artificial intelligence %K coronary artery disease %K coronary computed tomographic angiography %K clinical decision support %K invasive coronary angiography %D 2025 %7 21.5.2025 %9 Protocol %J JMIR Res Protoc %G English %X Background: Invasive coronary angiography (ICA) is the gold standard in the diagnosis of coronary artery disease (CAD). Being invasive, it carries rare but serious risks including myocardial infarction, stroke, major bleeding, and death. A large proportion of elective outpatients undergoing ICA have nonobstructive CAD, highlighting the suboptimal use of this test. Coronary computed tomographic angiography (CCTA) is a noninvasive option that provides similar information with less risk and is recommended as a first-line test for patients with low-to-intermediate risk of CAD. Leveraging artificial intelligence (AI) to appropriately direct patients to ICA or CCTA based on the predicted probability of disease may improve the efficiency and safety of diagnostic pathways. Objective: he CarDIA-AI (Coronary computed tomographic angiography to optimize the Diagnostic yield of Invasive Angiography for low-risk patients screened with Artificial Intelligence) study aims to evaluate whether AI-based risk assessment for obstructive CAD implemented within a centralized triage process can optimize the use of ICA in outpatients referred for nonurgent ICA. Methods: CarDIA-AI is a pragmatic, open-label, superior randomized controlled trial involving 2 Canadian cardiac centers. A total of 252 adults referred for elective outpatient ICA will be randomized 1:1 to usual care (directly proceeding to ICA) or to triage using an AI-based decision support tool. The AI-based decision support tool was developed using referral information from over 37,000 patients and uses a light gradient boosting machine model to predict the probability of obstructive CAD based on 42 clinically relevant predictors, including patient referral information, demographic characteristics, risk factors, and medical history. Participants in the intervention arm will have their ICA referral forms and medical charts reviewed, and select details entered into the decision support tool, which recommends CCTA or ICA based on the patient’s predicted probability of obstructive CAD. All patients will receive the selected imaging modality within 6 weeks of referral and will be subsequently followed for 90 days. The primary outcome is the proportion of normal or nonobstructive CAD diagnosed via ICA and will be assessed using a 2-sided z test to compare the patients referred for cardiac investigation with normal or nonobstructive CAD diagnosed through ICA between the intervention and control groups. Secondary outcomes include the number of angiograms avoided and the diagnostic yield of ICA. Results: Recruitment began on January 9, 2025, and is expected to conclude in mid to late 2025. As of April 14, 2025, we have enrolled 81 participants. Data analysis will begin once data collection is completed. We expect to submit the results for publication in 2026. Conclusions: CarDIA-AI will be the first randomized controlled trial using AI to optimize patient selection for CCTA versus ICA, potentially improving diagnostic efficiency, avoiding unnecessary complications of ICA, and improving health care resource usage. Trial Registration: ClinicalTrials.gov NCT06648239; https://clinicaltrials.gov/study/NCT06648239/ International Registered Report Identifier (IRRID): DERR1-10.2196/71726 %M 40397500 %R 10.2196/71726 %U https://www.researchprotocols.org/2025/1/e71726 %U https://doi.org/10.2196/71726 %U http://www.ncbi.nlm.nih.gov/pubmed/40397500 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 9 %N %P e68066 %T Machine Learning Model for Predicting Coronary Heart Disease Risk: Development and Validation Using Insights From a Japanese Population–Based Study %A Vu,Thien %A Kokubo,Yoshihiro %A Inoue,Mai %A Yamamoto,Masaki %A Mohsen,Attayeb %A Martin-Morales,Agustin %A Dawadi,Research %A Inoue,Takao %A Tay,Jie Ting %A Yoshizaki,Mari %A Watanabe,Naoki %A Kuriya,Yuki %A Matsumoto,Chisa %A Arafa,Ahmed %A Nakao,Yoko M %A Kato,Yuka %A Teramoto,Masayuki %A Araki,Michihiro %K coronary heart disease %K machine learning %K logistic regression %K random forest %K support vector machine %K Extreme Gradient Boosting %K Light Gradient-Boosting Machine %K Shapley Additive Explanations %K CHD %K SVM %K XGBoost %K LightGBM %K SHAP %D 2025 %7 12.5.2025 %9 %J JMIR Cardio %G English %X Background: Coronary heart disease (CHD) is a major cause of morbidity and mortality worldwide. Identifying key risk factors is essential for effective risk assessment and prevention. A data-driven approach using machine learning (ML) offers advanced techniques to analyze complex, nonlinear, and high-dimensional datasets, uncovering novel predictors of CHD that go beyond the limitations of traditional models, which rely on predefined variables. Objective: This study aims to evaluate the contribution of various risk factors to CHD, focusing on both established and novel markers using ML techniques. Methods: The study recruited 7672 participants aged 30-84 years from Suita City, Japan, between 1989 and 1999. Over an average of 15 years, participants were monitored for cardiovascular events. A total of 7260 participants and 28 variables were included in the analysis after excluding individuals with missing outcome data and eliminating unnecessary variables. Five ML models—logistic regression, random forest (RF), support vector machine, Extreme Gradient Boosting, and Light Gradient-Boosting Machine—were applied for predicting CHD incidence. Model performance was evaluated using accuracy, sensitivity, specificity, precision, area under the curve, F1-score, calibration curves, observed-to-expected ratios, and decision curve analysis. Additionally, Shapley Additive Explanations (SHAPs) were used to interpret the prediction models and understand the contribution of various risk factors to CHD. Results: Among 7260 participants, 305 (4.2%) were diagnosed with CHD. The RF model demonstrated the highest performance, with an accuracy of 0.73 (95% CI 0.64‐0.80), sensitivity of 0.74 (95% CI 0.62‐0.84), specificity of 0.72 (95% CI 0.61‐0.83), and an area under the curve of 0.73 (95% CI 0.65‐0.80). RF also showed excellent calibration, with predicted probabilities closely aligning with observed outcomes, and provided substantial net benefit across a range of risk thresholds, as demonstrated by decision curve analysis. SHAP analysis elucidated key predictors of CHD, including the intima-media thickness (IMT_cMax) of the common carotid artery, blood pressure, lipid profiles (non–high-density lipoprotein cholesterol, high-density lipoprotein cholesterol, and triglycerides), and estimated glomerular filtration rate. Novel risk factors identified as significant contributors to CHD risk included lower calcium levels, elevated white blood cell counts, and body fat percentage. Furthermore, a protective effect was observed in women, suggesting the potential necessity for gender-specific risk assessment strategies in future cardiovascular health evaluations. Conclusions: We developed a model to predict CHD using ML and applied SHAP methods for interpretation. This approach highlights the multifactor nature of CHD risk evaluation, aiming to support health care professionals in identifying risk factors and formulating effective prevention strategies. %R 10.2196/68066 %U https://cardio.jmir.org/2025/1/e68066 %U https://doi.org/10.2196/68066 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 13 %N %P e69102 %T Effects of the National Institutes of Health Stroke Scale and Modified Rankin Scale on Predictive Models of 30-Day Nonelective Readmission and Mortality After Ischemic Stroke: Cohort Study %A Nguyen-Huynh,Mai N %A Alexander,Janet %A Zhu,Zheng %A Meighan,Melissa %A Escobar,Gabriel %K ischemic stroke %K readmission %K predictive modeling %K mortality %K National Institutes of Health Stroke Scale %K NIHSS %K modified Rankin scale %K mRS %D 2025 %7 9.5.2025 %9 %J JMIR Med Inform %G English %X Background: Patients with stroke have high rates of all-cause readmission and case fatality. Limited information is available on how to predict these outcomes. Objective: We aimed to assess whether adding the initial National Institutes of Health Stroke Scale (NIHSS) score or modified Rankin scale (mRS) score at discharge improved predictive models of 30-day nonelective readmission or 30-day mortality poststroke. Methods: Using a cohort of patients with ischemic stroke in a large multiethnic integrated health care system from June 15, 2018, to April 29, 2020, we tested 2 predictive models for a composite outcome (30-day nonelective readmission or death). The models were based on administrative data (Length of Stay, Acuity, Charlson Comorbidities, Emergency Department Use score; LACE) as well as a comprehensive model (Transition Support Level; TSL). The models, initial NIHSS score, and mRS scores at discharge, were tested independently and in combination with age and sex. We assessed model performance using the area under the receiver operator characteristic (c-statistic), Nagelkerke pseudo-R2, and Brier score. Results: The study cohort included 4843 patients with 5014 stroke hospitalizations. Average age was 71.9 (SD 14) years, 50.6% (2537/5014) were female, and 52.1% (2614/5014) were White. Median initial NIHSS score was 4 (IQR 2-8). There were 538 (10.7%) nonelective readmissions and 150 (3.9%) deaths within 30 days. The logistic models revealed that the best performing models were TSL (c-statistic=0.69) and TSL plus mRS score at discharge (c-statistic=0.69). Conclusions: We found that neither the initial NIHSS score nor the mRS score at discharge significantly enhanced the predictive ability of the LACE or TSL models. Future efforts at prediction of short-term stroke outcomes will need to incorporate new data elements. %R 10.2196/69102 %U https://medinform.jmir.org/2025/1/e69102 %U https://doi.org/10.2196/69102 %0 Journal Article %@ 2291-5222 %I JMIR Publications %V 13 %N %P e56466 %T Review and Comparative Evaluation of Mobile Apps for Cardiovascular Risk Estimation: Usability Evaluation Using mHealth App Usability Questionnaire %A Svenšek,Adrijana %A Gosak,Lucija %A Lorber,Mateja %A Štiglic,Gregor %A Fijačko,Nino %K cardiovascular diseases %K MAUQ %K prognostic models %K mobile applications %K visualization %K PRISMA %D 2025 %7 8.5.2025 %9 %J JMIR Mhealth Uhealth %G English %X Background: Cardiovascular diseases (CVD) are the leading cause of death and disability worldwide, and their prevention is a major public health priority. Detecting health issues early and assessing risk levels can significantly improve the chances of reducing mortality. Mobile apps can help estimate and manage CVD risks by providing users with personalized feedback, education, and motivation. Incorporating visual analysis into apps is an effective method for educating society. However, the usability evaluation and inclusion of visualization of these apps are often unclear and variable. Objective: The primary objective of this study is to review and compare the usability of existing apps designed to estimate CVD risk using the mHealth App Usability Questionnaire (MAUQ). This is not a traditional usability study involving user interaction design, but rather an assessment of how effectively these applications meet usability standards as defined by the MAUQ. Methods: First, we used predefined criteria to review 16 out of 2238 apps to estimate CVD risk in the Google Play Store and the Apple App Store. Based on the apps’ characteristics (ie, developed for health care professionals or patient use) and their functions (single or multiple CVD risk calculators), we conducted a descriptive analysis. Then we also compared the usability of existing apps using the MAUQ and calculated the agreement among 3 expert raters. Results: Most apps used the Framingham Risk Score (8/16, 50%) and Atherosclerotic Cardiovascular Disease Risk (7/16, 44%) prognostic models to estimate CVD risk. The app with the highest overall MAUQ score was the MDCalc Medical Calculator (mean 6.76, SD 0.25), and the lowest overall MAUQ score was obtained for the CardioRisk Calculator (mean 3.96, SD 0.21). The app with the highest overall MAUQ score in the “ease-of-use” domain was the MDCalc Medical Calculator (mean 7, SD 0); in the domain “interface and satisfaction,” it was the MDCalc Medical Calculator (mean 6.67, SD 0.33); and in the domain “usefulness,” it was the ASCVD Risk Estimator Plus (mean 6.80, SD 0.32). Conclusions: We found that the Framingham Risk Score is the most widely used prognostic model in apps for estimating CVD risk. The “ease-of-use” domain received the highest ratings. While more than half of the apps were suitable for both health care professionals and patients, only a few offered sophisticated visualizations for assessing CVD risk. Less than a quarter of the apps included visualizations, and those that did were single calculators. Our analysis of apps showed that they are an appropriate tool for estimating CVD risk. %R 10.2196/56466 %U https://mhealth.jmir.org/2025/1/e56466 %U https://doi.org/10.2196/56466 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 27 %N %P e67525 %T Development of a Predictive Model for Metabolic Syndrome Using Noninvasive Data and its Cardiovascular Disease Risk Assessments: Multicohort Validation Study %A Park,Jin-Hyun %A Jeong,Inyong %A Ko,Gang-Jee %A Jeong,Seogsong %A Lee,Hwamin %+ Korea University College of Medicine, 73 Goryeodae-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea, 82 1063205109, hwamin@korea.ac.kr %K metabolic syndrome prediction %K noninvasive data %K clinical interpretable model %K body composition data %K early intervention %D 2025 %7 2.5.2025 %9 Original Paper %J J Med Internet Res %G English %X Background: Metabolic syndrome is a cluster of metabolic abnormalities, including obesity, hypertension, dyslipidemia, and insulin resistance, that significantly increase the risk of cardiovascular disease (CVD) and other chronic conditions. Its global prevalence is rising, particularly in aging and urban populations. Traditional screening methods rely on laboratory tests and specialized assessments, which may not be readily accessible in routine primary care and community settings. Limited resources, time constraints, and inconsistent screening practices hinder early identification and intervention. Developing a noninvasive and scalable predictive model could enhance accessibility and improve early detection. Objective: This study aimed to develop and validate a predictive model for metabolic syndrome using noninvasive body composition data. Additionally, we evaluated the model’s ability to predict long-term CVD risk, supporting its application in clinical and public health settings for early intervention and preventive strategies. Methods: We developed a machine learning–based predictive model using noninvasive data from two nationally representative cohorts: the Korea National Health and Nutrition Examination Survey (KNHANES) and the Korean Genome and Epidemiology Study. The model was trained using dual-energy x-ray absorptiometry data from KNHANES (2008-2011) and validated internally with bioelectrical impedance analysis data from KNHANES 2022. External validation was conducted using Korean Genome and Epidemiology Study follow-up datasets. Five machine learning algorithms were compared, and the best-performing model was selected based on the area under the receiver operating characteristic curve. Cox proportional hazards regression was used to assess the model’s ability to predict long-term CVD risk. Results: The model demonstrated strong predictive performance across validation cohorts. Area under the receiver operating characteristic curve values for metabolic syndrome prediction ranged from 0.8338 to 0.8447 in internal validation, 0.8066 to 0.8138 in external validation 1, and 0.8039 to 0.8123 in external validation 2. The model’s predictions were significantly associated with future cardiovascular risk, with Cox regression analysis indicating that individuals classified as having metabolic syndrome had a 1.51-fold higher risk of developing CVD (hazard ratio 1.51, 95% CI 1.32-1.73; P<.001). The ability to predict long-term CVD risk highlights the potential utility of this model for guiding early interventions. Conclusions: This study developed a noninvasive predictive model for metabolic syndrome with strong performance across diverse validation cohorts. By enabling early risk identification without laboratory tests, the model enhances accessibility in primary care and large-scale screenings. Its ability to predict long-term CVD risk supports proactive intervention strategies, potentially reducing the burden of cardiometabolic diseases. Further research should refine the model with additional clinical factors and broader population validation to maximize its clinical impact. %M 40315452 %R 10.2196/67525 %U https://www.jmir.org/2025/1/e67525 %U https://doi.org/10.2196/67525 %U http://www.ncbi.nlm.nih.gov/pubmed/40315452 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 27 %N %P e70587 %T Multimodal Visualization and Explainable Machine Learning–Driven Markers Enable Early Identification and Prognosis Prediction for Symptomatic Aortic Stenosis and Heart Failure With Preserved Ejection Fraction After Transcatheter Aortic Valve Replacement: Multicenter Cohort Study %A Wang,Jun %A Zhu,Jiajun %A Li,Hui %A Wu,Shili %A Li,Siyang %A Yao,Zhuoya %A Zhu,Tongjian %A Tang,Bi %A Tang,Shengxing %A Liu,Jinjun %+ , Department of Cardiology, The First Affiliated Hospital of Bengbu Medical University, No. 287, Changhuai Road, Longzihu District, Bengbu, 233030, China, 86 05523086107, byyfyliujinjun@163.com %K machine learning %K interpretable models %K heart failure with preserved ejection fraction %K symptomatic aortic stenosis %K transcatheter aortic valve replacement %K major adverse cardiovascular and cerebrovascular events. %D 2025 %7 1.5.2025 %9 Original Paper %J J Med Internet Res %G English %X Background: Currently, there is a paucity of literature addressing personalized risk stratification using multimodal data in patients with symptomatic aortic stenosis and heart failure with preserved ejection fraction (HFpEF) following transcatheter aortic valve replacement (TAVR). Objective: This study aimed to enhance the performance of risk assessment models in this patient population by developing a predictive model for adverse outcomes using various machine learning (ML) techniques. Methods: This multicenter cohort study included 326 patients diagnosed with severe AS and HFpEF who underwent TAVR between January 2017 and December 2023. Patients were allocated to training (n=195) and independent validation (n=131) sets based on hospital affiliation. A dual-phase feature selection process, combining least absolute shrinkage and selection operator logistic regression and the Boruta algorithm, was used to identify relevant variables from the multimodal dataset. A total of 5 ML model-decision trees, K-nearest neighbors, random forest, support vector machine, and extreme gradient boosting were used to construct a visualization and explainable predictive framework to elucidate model decision-making processes. Results: The primary features identified included age, N-terminal pro-brain natriuretic peptide, fasting blood glucose, triglyceride/high-density lipoprotein cholesterol ratio, triglyceride glucose index, triglyceride glucose-BMI index, atherogenic index of plasma index, and Apolipoprotein B. Among the 5 models, the support vector machine demonstrated the best predictive performance for major adverse cardiovascular and cerebrovascular events in patients with severe AS and HFpEF following TAVR, achieving an area under the curve of 0.756 (95% CI 0.631-0.881) in the independent validation set. The model exhibited good calibration and robust predictive power in both training and validation sets and demonstrated the highest net benefit in decision curve analysis compared to other models. To extract significant variables influencing the algorithm and ensure model appropriateness, we interpreted cohort and personalized model predictions using Shapley Additive Explanations values. Conclusions: Our ML-based multimodal model, incorporating 8 readily accessible predictors, demonstrated robust predictive capability for 12 months of major adverse cardiovascular and cerebrovascular events risk. This model can be used to identify high-risk individuals with AS and HFpEF following TAVR, potentially aiding in risk stratification and personalized treatment strategies. %M 40310672 %R 10.2196/70587 %U https://www.jmir.org/2025/1/e70587 %U https://doi.org/10.2196/70587 %U http://www.ncbi.nlm.nih.gov/pubmed/40310672 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 27 %N %P e68929 %T Effects of a Cloud-Based Synchronous Telehealth Program on Valvular Regurgitation Regression: Retrospective Study %A Yang,Li-Tan %A Wu,Chi-Han %A Lee,Jen-Kuang %A Wang,Wei-Jyun %A Chen,Ying-Hsien %A Huang,Ching-Chang %A Hung,Chi-Sheng %A Chiang,Kuang-Chien %A Ho,Yi-Lwun %A Wu,Hui-Wen %+ Division of Cardiology, Department of Internal Medicine, National Taiwan University Hospital, No 7, Jhongshan S Rd, Jhongjheng Dist, Taipei, 10002, Taiwan, 886 972651295, ylho@ntu.edu.tw %K mitral regurgitation %K tricuspid regurgitation %K telehealth %K telemedicine %K cardiac remodeling %D 2025 %7 23.4.2025 %9 Original Paper %J J Med Internet Res %G English %X Background: Telemedicine has been associated with better cardiovascular outcomes, but its effects on the regression of mitral regurgitation (MR) and tricuspid regurgitation (TR) remain unknown. Objective: This study aimed to evaluate whether telemedicine could facilitate the regression of MR and TR compared to usual care and whether it was associated with better survival. Methods: This retrospective cohort study enrolled consecutive patients with moderate or greater MR or TR from 2010 through 2020, excluding those with concomitant aortic stenosis, aortic regurgitation, or mitral stenosis greater than mild severity. All patients underwent follow-up transthoracic echocardiography (TTE) at least 3 months apart. Patients receiving telehealth services for at least two weeks within 90 days of baseline TTE were categorized as the telehealth group; the remainder constituted the nontelehealth group. Telemedicine participants transmitted daily biometric data—blood pressure, pulse rate, blood glucose, electrocardiogram, and oxygen saturation—to a cloud-based platform for timely monitoring. Experienced case managers regularly contacted patients and initiated immediate action for concerning measurements. The primary endpoint was MR or TR regression from ≥moderate to 80 years), and the highest proportions of cases were assigned an urgency level (3=urgent or 2=very urgent). The internal validation showed accuracy and specificity levels above 96% for all syndrome definitions. The sensitivity was 85.3% for ACS, 56.6% for MI, and 80.5% for STR. The external validation showed high levels of correspondence between the ED data and the German hospital statistics, with most ratios ranging around 1, indicating congruence, particularly in older age groups. The highest differences were noted in younger age groups, with the highest ratios in women aged between 20 and 39 years (4.57 for MI and 4.17 for ACS). Conclusions: We developed NCD indicators for ACS, MI, and STR that showed high levels of internal and external validity. The integration of these indicators into the syndromic surveillance system for EDs could enable daily monitoring of NCD patterns and trends to enhance timely public health surveillance in Germany. %R 10.2196/66218 %U https://publichealth.jmir.org/2025/1/e66218 %U https://doi.org/10.2196/66218 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 27 %N %P e67346 %T Risk Factors for Gastrointestinal Bleeding in Patients With Acute Myocardial Infarction: Multicenter Retrospective Cohort Study %A Kou,Yanqi %A Ye,Shicai %A Tian,Yuan %A Yang,Ke %A Qin,Ling %A Huang,Zhe %A Luo,Botao %A Ha,Yanping %A Zhan,Liping %A Ye,Ruyin %A Huang,Yujie %A Zhang,Qing %A He,Kun %A Liang,Mouji %A Zheng,Jieming %A Huang,Haoyuan %A Wu,Chunyi %A Ge,Lei %A Yang,Yuping %+ Department of Gastroenterology, Affiliated Hospital of Guangdong Medical University, No. 2 Wenming East Road, Xiashan, Zhanjiang, Zhanjiang, 524000, China, 1 13106629993, yangyupingchn@163.com %K acute myocardial infarction %K gastrointestinal bleeding %K machine learning %K in-hospital %K prediction model %D 2025 %7 30.1.2025 %9 Original Paper %J J Med Internet Res %G English %X Background: Gastrointestinal bleeding (GIB) is a severe and potentially life-threatening complication in patients with acute myocardial infarction (AMI), significantly affecting prognosis during hospitalization. Early identification of high-risk patients is essential to reduce complications, improve outcomes, and guide clinical decision-making. Objective: This study aimed to develop and validate a machine learning (ML)–based model for predicting in-hospital GIB in patients with AMI, identify key risk factors, and evaluate the clinical applicability of the model for risk stratification and decision support. Methods: A multicenter retrospective cohort study was conducted, including 1910 patients with AMI from the Affiliated Hospital of Guangdong Medical University (2005-2024). Patients were divided into training (n=1575) and testing (n=335) cohorts based on admission dates. For external validation, 1746 patients with AMI were included in the publicly available MIMIC-IV (Medical Information Mart for Intensive Care IV) database. Propensity score matching was adjusted for demographics, and the Boruta algorithm identified key predictors. A total of 7 ML algorithms—logistic regression, k-nearest neighbors, support vector machine, decision tree, random forest (RF), extreme gradient boosting, and neural networks—were trained using 10-fold cross-validation. The models were evaluated for the area under the receiver operating characteristic curve, accuracy, sensitivity, specificity, recall, F1-score, and decision curve analysis. Shapley additive explanations analysis ranked variable importance. Kaplan-Meier survival analysis evaluated the impact of GIB on short-term survival. Multivariate logistic regression assessed the relationship between coronary heart disease (CHD) and in-hospital GIB after adjusting for clinical variables. Results: The RF model outperformed other ML models, achieving an area under the receiver operating characteristic curve of 0.77 in the training cohort, 0.77 in the testing cohort, and 0.75 in the validation cohort. Key predictors included red blood cell count, hemoglobin, maximal myoglobin, hematocrit, CHD, and other variables, all of which were strongly associated with GIB risk. Decision curve analysis demonstrated the clinical use of the RF model for early risk stratification. Kaplan-Meier survival analysis showed no significant differences in 7- and 15-day survival rates between patients with AMI with and without GIB (P=.83 for 7-day survival and P=.87 for 15-day survival). Multivariate logistic regression showed that CHD was an independent risk factor for in-hospital GIB (odds ratio 2.79, 95% CI 2.09-3.74). Stratified analyses by sex, age, occupation, marital status, and other subgroups consistently showed that the association between CHD and GIB remained robust across all subgroups. Conclusions: The ML-based RF model provides a robust and clinically applicable tool for predicting in-hospital GIB in patients with AMI. By leveraging routinely available clinical and laboratory data, the model supports early risk stratification and personalized preventive strategies. %M 39883922 %R 10.2196/67346 %U https://www.jmir.org/2025/1/e67346 %U https://doi.org/10.2196/67346 %U http://www.ncbi.nlm.nih.gov/pubmed/39883922 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 13 %N %P e58800 %T Performance of an Electronic Health Record–Based Automated Pulmonary Embolism Severity Index Score Calculator: Cohort Study in the Emergency Department %A Joyce,Elizabeth %A McMullen,James %A Kong,Xiaowen %A O'Hare,Connor %A Gavrila,Valerie %A Cuttitta,Anthony %A Barnes,Geoffrey D %A Greineder,Colin F %K pulmonary embolism %K low-risk pulmonary embolism %K risk %K artery %K pulmonary embolism severity index %K clinical decision support %K emergency department %K hospital %K lung %K blood %K clot %K clotting %K cardiovascular %K index %K score %K measure %K scale %K tomography %K image %K imaging %K PESI %K CDS %K ED %D 2025 %7 20.1.2025 %9 %J JMIR Med Inform %G English %X Background: Studies suggest that less than 4% of patients with pulmonary embolisms (PEs) are managed in the outpatient setting. Strong evidence and multiple guidelines support the use of the Pulmonary Embolism Severity Index (PESI) for the identification of acute PE patients appropriate for outpatient management. However, calculating the PESI score can be inconvenient in a busy emergency department (ED). To facilitate integration into ED workflow, we created a 2023 Epic-compatible clinical decision support tool that automatically calculates the PESI score in real-time with patients’ electronic health data (ePESI [Electronic Pulmonary Embolism Severity Index]). Objective: The primary objectives of this study were to determine the overall accuracy of ePESI and its ability to correctly distinguish high- and low-risk PESI scores within the Epic 2023 software. The secondary objective was to identify variables that impact ePESI accuracy. Methods: We collected ePESI scores on 500 consecutive patients at least 18 years old who underwent a computerized tomography-pulmonary embolism scan in the ED of our tertiary, academic health center between January 3 and February 15, 2023. We compared ePESI results to a PESI score calculated by 2 independent, medically-trained abstractors blinded to the ePESI and each other’s results. ePESI accuracy was calculated with binomial test. The odds ratio (OR) was calculated using logistic regression. Results: Of the 500 patients, a total of 203 (40.6%) and 297 (59.4%) patients had low- and high-risk PESI scores, respectively. The ePESI exactly matched the calculated PESI in 394 out of 500 cases, with an accuracy of 78.8% (95% CI 74.9%‐82.3%), and correctly identified low- versus high-risk in 477 out of 500 (95.4%) cases. The accuracy of the ePESI was higher for low-risk scores (OR 2.96, P<.001) and lower when patients were without prior encounters in the health system (OR 0.42, P=.008). Conclusions: In this single-center study, the ePESI was highly accurate in discriminating between low- and high-risk scores. The clinical decision support should facilitate real-time identification of patients who may be candidates for outpatient PE management. %R 10.2196/58800 %U https://medinform.jmir.org/2025/1/e58800 %U https://doi.org/10.2196/58800 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 9 %N %P e64893 %T Estimating Trends in Cardiovascular Disease Risk for the EXPOSE (Explaining Population Trends in Cardiovascular Risk: A Comparative Analysis of Health Transitions in South Africa and England) Study: Repeated Cross-Sectional Study %A Scholes,Shaun %A Mindell,Jennifer S %A Toomse-Smith,Mari %A Cois,Annibale %A Adjaye-Gbewonyo,Kafui %+ Department of Epidemiology and Public Health, University College London, 1-19 Torrington Place, London, WC1E 6BT, United Kingdom, 44 01207 679 1727, s.scholes@ucl.ac.uk %K data harmonization %K cardiovascular disease %K CVD %K CVD risk scores %K trends %K cross-country comparisons %K public health %K England %K South Africa %D 2025 %7 20.1.2025 %9 Original Paper %J JMIR Cardio %G English %X Background: Cardiovascular diseases (CVDs) are the leading cause of death globally. Demographic, behavioral, socioeconomic, health care, and psychosocial variables considered risk factors for CVD are routinely measured in population health surveys, providing opportunities to examine health transitions. Studying the drivers of health transitions in countries where multiple burdens of disease persist (eg, South Africa), compared with countries regarded as models of “epidemiologic transition” (eg, England), can provide knowledge on where best to intervene and direct resources to reduce the disease burden. Objective: The EXPOSE (Explaining Population Trends in Cardiovascular Risk: A Comparative Analysis of Health Transitions in South Africa and England) study analyzes microlevel data collected from multiple nationally representative population health surveys conducted in these 2 countries between 1998 and 2017. Creating a harmonized dataset by pooling repeated cross-sectional surveys to model trends in CVD risk is challenging due to changes in aspects such as survey content, question wording, inclusion of boost samples, weighting, measuring equipment, and guidelines for data protection. This study aimed to create a harmonized dataset based on the annual Health Surveys for England to estimate trends in mean predicted 10-year CVD risk (primary outcome) and its individual risk components (secondary outcome). Methods: We compiled a harmonized dataset to estimate trends between 1998 and 2017 in the English adult population, including the primary and secondary outcomes, and potential drivers of those trends. Laboratory- and non–laboratory-based World Health Organization (WHO) and Globorisk algorithms were used to calculate the predicted 10-year total (fatal and nonfatal) CVD risk. Sex-specific estimates of the mean 10-year CVD risk and its components by survey year were calculated, accounting for the complex survey design. Results: Laboratory- and non–laboratory-based 10-year CVD risk scores were calculated for 33,628 and 61,629 participants aged 40 to 74 years, respectively. The absolute predicted 10-year risk of CVD declined significantly on average over the last 2 decades in both sexes (for linear trend; all P<.001). In men, the mean of the laboratory-based WHO risk score was 10.1% (SE 0.2%) and 8.4% (SE 0.2%) in 1998 and 2017, respectively; corresponding figures in women were 5.6% (SE 0.1%) and 4.5% (SE 0.1%). In men, the mean of the non–laboratory-based WHO risk score was 9.6% (SE 0.1%) and 8.9% (SE 0.2%) in 1998 and 2017, respectively; corresponding figures in women were 5.8% (SE 0.1%) and 4.8% (SE 0.1%). Predicted CVD risk using the Globorisk algorithms was lower on average in absolute terms, but the pattern of change was very similar. Trends in the individual risk components showed a complex pattern. Conclusions: Harmonized data from repeated cross-sectional health surveys can be used to quantify the drivers of recent changes in CVD risk at the population level. %M 39832161 %R 10.2196/64893 %U https://cardio.jmir.org/2025/1/e64893 %U https://doi.org/10.2196/64893 %U http://www.ncbi.nlm.nih.gov/pubmed/39832161 %0 Journal Article %@ 2561-7605 %I JMIR Publications %V 8 %N %P e64374 %T Development and Validation of a Predictive Model Based on Serum Silent Information Regulator 6 Levels in Chinese Older Adult Patients: Cross-Sectional Descriptive Study %A You,Yuzi %A Liang,Wei %A Zhao,Yajie %K aging %K coronary artery disease %K nomogram %K SIRT6 %K TyG index %K silent information regulator 6 %K triglyceride glucose index %D 2025 %7 15.1.2025 %9 %J JMIR Aging %G English %X Background: Serum levels of silent information regulator 6 (SIRT6), a key biomarker of aging, were identified as a predictor of coronary artery disease (CAD), but whether SIRT6 can distinguish severity of coronary artery lesions in older adult patients is unknown. Objectives: This study developed a nomogram to demonstrate the functionality of SIRT6 in assessing severity of coronary artery atherosclerosis. Methods: Patients aged 60 years and older with angina pectoris were screened for this single-center clinical study between October 1, 2022, and March 31, 2023. Serum specimens of eligible patients were collected for SIRT6 detection by enzyme-linked immunosorbent assay. Clinical data and putative predictors, including 29 physiological characteristics, biochemical parameters, carotid artery ultrasonographic results, and complete coronary angiography findings, were evaluated, with CAD diagnosis as the primary outcome. The nomogram was derived from the Extreme Gradient Boosting (XGBoost) model, with logistic regression for variable selection. Model performance was assessed by examining discrimination, calibration, and clinical use separately. A 10-fold cross-validation technique was used to compare all models. The models’ performance was further evaluated on the internal validation set to ensure that the obtained results were not due to overoptimization. Results: Eligible patients (n=222) were divided into 2 cohorts: the development cohort (n=178) and the validation cohort (n=44). Serum SIRT6 levels were identified as both an independent risk factor and a predictor for CAD in older adults. The area under the receiver operating characteristic curve (AUROC) was 0.725 (95% CI 0.653‐0.797). The optimal cutoff value of SIRT6 for predicting CAD was 546.384 pg/mL. Predictors included in this nomogram were serum SIRT6 levels, triglyceride glucose (TyG) index, and apolipoprotein B. The model achieved an AUROC of 0.956 (95% CI 0.928‐0.983) in the development cohort. Similarly, in the internal validation cohort, the AUROC was 0.913 (95% CI 0.828‐0.999). All models demonstrated satisfactory calibration, with predicted outcomes closely aligning with actual results. Conclusions: SIRT6 shows promise in predicting CAD, with enhanced predictive abilities when combined with the TyG index. In clinical settings, monitoring fluctuations in SIRT6 and TyG may offer valuable insights for early CAD detection. The nomogram for CAD outcome prediction in older adult patients with angina pectoris may aid in clinical trial design and personalized clinical decision-making, particularly in institutions where SIRT6 is being explored as a biomarker for aging or cardiovascular health. %R 10.2196/64374 %U https://aging.jmir.org/2025/1/e64374 %U https://doi.org/10.2196/64374 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 9 %N %P e50627 %T Application of Dragonnet and Conformal Inference for Estimating Individualized Treatment Effects for Personalized Stroke Prevention: Retrospective Cohort Study %A Lolak,Sermkiat %A Attia,John %A McKay,Gareth J %A Thakkinstian,Ammarin %K stroke %K causal effect %K ITE %K individual treatment effect %K Dragonnet %K conformal inference %K mortality %K hospital records %K hypertension %K risk factor %K diabetes %K dyslipidemia %K atrial fibrillation %K machine learning %K treatment %D 2025 %7 8.1.2025 %9 %J JMIR Cardio %G English %X Background: Stroke is a major cause of death and disability worldwide. Identifying individuals who would benefit most from preventative interventions, such as antiplatelet therapy, is critical for personalized stroke prevention. However, traditional methods for estimating treatment effects often focus on the average effect across a population and do not account for individual variations in risk and treatment response. Objective: This study aimed to estimate the individualized treatment effects (ITEs) for stroke prevention using a novel combination of Dragonnet, a causal neural network, and conformal inference. The study also aimed to determine and validate the causal effects of known stroke risk factors—hypertension (HT), diabetes mellitus (DM), dyslipidemia (DLP), and atrial fibrillation (AF)—using both a conventional causal model and machine learning models. Methods: A retrospective cohort study was conducted using data from 275,247 high-risk patients treated at Ramathibodi Hospital, Thailand, between 2010 and 2020. Patients aged >18 years with HT, DM, DLP, or AF were eligible. The main outcome was ischemic or hemorrhagic stroke, identified using International Classification of Diseases, 10th Revision (ICD-10) codes. Causal effects of the risk factors were estimated using a range of methods, including: (1) propensity score–based methods, such as stratified propensity scores, inverse probability weighting, and doubly robust estimation; (2) structural causal models; (3) double machine learning; and (4) Dragonnet, a causal neural network, which was used together with weighted split-conformal quantile regression to estimate ITEs. Results: AF, HT, and DM were identified as significant stroke risk factors. Average causal risk effect estimates for these risk factors ranged from 0.075 to 0.097 for AF, 0.017 to 0.025 for HT, and 0.006 to 0.010 for DM, depending on the method used. Dragonnet yielded causal risk ratios of 4.56 for AF, 2.44 for HT, and 1.41 for DM, which is comparable to other causal models and the standard epidemiological case-control study. Mean ITE analysis indicated that several patients with DM or DM with HT, who were not receiving antiplatelet treatment at the time of data collection, showed reductions in total risk of −0.015 and −0.016, respectively. Conclusions: This study provides a comprehensive evaluation of stroke risk factors and demonstrates the feasibility of using Dragonnet and conformal inference to estimate ITEs of antiplatelet therapy for stroke prevention. The mean ITE analysis suggested that those with DM or DM with HT, who were not receiving antiplatelet treatment at the time of data collection, could potentially benefit from this therapy. The findings highlight the potential of these advanced techniques to inform personalized treatment strategies for stroke, enabling clinicians to identify individuals who are most likely to benefit from specific interventions. %R 10.2196/50627 %U https://cardio.jmir.org/2025/1/e50627 %U https://doi.org/10.2196/50627 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 12 %N %P e58812 %T Enhancing Clinical Decision Making by Predicting Readmission Risk in Patients With Heart Failure Using Machine Learning: Predictive Model Development Study %A Jiang,Xiangkui %A Wang,Bingquan %K prediction model %K heart failure %K hospital readmission %K machine learning %K cardiology %K admissions %K hospitalization %D 2024 %7 31.12.2024 %9 %J JMIR Med Inform %G English %X Background: Patients with heart failure frequently face the possibility of rehospitalization following an initial hospital stay, placing a significant burden on both patients and health care systems. Accurate predictive tools are crucial for guiding clinical decision-making and optimizing patient care. However, the effectiveness of existing models tailored specifically to the Chinese population is still limited. Objective: This study aimed to formulate a predictive model for assessing the likelihood of readmission among patients diagnosed with heart failure. Methods: In this study, we analyzed data from 1948 patients with heart failure in a hospital in Sichuan Province between 2016 and 2019. By applying 3 variable selection strategies, 29 relevant variables were identified. Subsequently, we constructed 6 predictive models using different algorithms: logistic regression, support vector machine, gradient boosting machine, Extreme Gradient Boosting, multilayer perception, and graph convolutional networks. Results: The graph convolutional network model showed the highest prediction accuracy with an area under the receiver operating characteristic curve of 0.831, accuracy of 75%, sensitivity of 52.12%, and specificity of 90.25%. Conclusions: The model crafted in this study proves its effectiveness in forecasting the likelihood of readmission among patients with heart failure, thus serving as a crucial reference for clinical decision-making. %R 10.2196/58812 %U https://medinform.jmir.org/2024/1/e58812 %U https://doi.org/10.2196/58812 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e60697 %T The Role of Machine Learning in the Detection of Cardiac Fibrosis in Electrocardiograms: Scoping Review %A Handra,Julia %A James,Hannah %A Mbilinyi,Ashery %A Moller-Hansen,Ashley %A O'Riley,Callum %A Andrade,Jason %A Deyell,Marc %A Hague,Cameron %A Hawkins,Nathaniel %A Ho,Kendall %A Hu,Ricky %A Leipsic,Jonathon %A Tam,Roger %+ Faculty of Medicine, University of British Columbia, 2194 Health Sciences Mall, Vancouver, BC, V6T 1Z3, Canada, 1 (604) 822 2421, jhandra@student.ubc.ca %K machine learning %K cardiac fibrosis %K electrocardiogram %K ECG %K detection %K ML %K cardiovascular disease %K review %D 2024 %7 30.12.2024 %9 Review %J JMIR Cardio %G English %X Background: Cardiovascular disease remains the leading cause of mortality worldwide. Cardiac fibrosis impacts the underlying pathophysiology of many cardiovascular diseases by altering structural integrity and impairing electrical conduction. Identifying cardiac fibrosis is essential for the prognosis and management of cardiovascular disease; however, current diagnostic methods face challenges due to invasiveness, cost, and inaccessibility. Electrocardiograms (ECGs) are widely available and cost-effective for monitoring cardiac electrical activity. While ECG-based methods for inferring fibrosis exist, they are not commonly used due to accuracy limitations and the need for cardiac expertise. However, the ECG shows promise as a target for machine learning (ML) applications in fibrosis detection. Objective: This study aims to synthesize and critically evaluate the current state of ECG-based ML approaches for cardiac fibrosis detection. Methods: We conducted a scoping review of research in ECG-based ML applications to identify cardiac fibrosis. Comprehensive searches were performed in PubMed, IEEE Xplore, Scopus, Web of Science, and DBLP databases, including publications up to October 2024. Studies were included if they applied ML techniques to detect cardiac fibrosis using ECG or vectorcardiogram data and provided sufficient methodological details and outcome metrics. Two reviewers independently assessed eligibility and extracted data on the ML models used, their performance metrics, study designs, and limitations. Results: We identified 11 studies evaluating ML approaches for detecting cardiac fibrosis using ECG data. These studies used various ML techniques, including classical (8/11, 73%), ensemble (3/11, 27%), and deep learning models (4/11, 36%). Support vector machines were the most used classical model (6/11, 55%), with the best-performing models of each study achieving accuracies of 77% to 93%. Among deep learning approaches, convolutional neural networks showed promising results, with one study reporting an area under the receiver operating characteristic curve (AUC) of 0.89 when combined with clinical features. Notably, a large-scale convolutional neural network study (n=14,052) achieved an AUC of 0.84 for detecting cardiac fibrosis, outperforming cardiologists (AUC 0.63-0.66). However, many studies had limited sample sizes and lacked external validation, potentially impacting the generalizability of the findings. Variability in reporting methods may affect the reproducibility and applicability of these ML-based approaches. Conclusions: ML-augmented ECG analysis shows promise for accessible and cost-effective detection of cardiac fibrosis. However, there are common limitations with respect to study design and insufficient external validation, raising concerns about the generalizability and clinical applicability of the findings. Inconsistencies in methodologies and incomplete reporting further impede cross-study comparisons. Future work may benefit from using prospective study designs, larger and more clinically and demographically diverse datasets, advanced ML models, and rigorous external validation. Addressing these challenges could pave the way for the clinical implementation of ML-based ECG detection of cardiac fibrosis to improve patient outcomes and health care resource allocation. %M 39753213 %R 10.2196/60697 %U https://cardio.jmir.org/2024/1/e60697 %U https://doi.org/10.2196/60697 %U http://www.ncbi.nlm.nih.gov/pubmed/39753213 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e54597 %T A Computable Phenotype Algorithm for Postvaccination Myocarditis/Pericarditis Detection Using Real-World Data: Validation Study %A Deady,Matthew %A Duncan,Raymond %A Sonesen,Matthew %A Estiandan,Renier %A Stimpert,Kelly %A Cho,Sylvia %A Beers,Jeffrey %A Goodness,Brian %A Jones,Lance Daniel %A Forshee,Richard %A Anderson,Steven A %A Ezzeldin,Hussein %+ Center for Biologics Evaluation and Research, Food and Drug Administration, 10903 New Hampshire Ave, Silver Spring, MD, 20993, United States, 1 240 205 2215, hussein.ezzeldin@fda.hhs.gov %K adverse event %K vaccine safety %K interoperability %K computable phenotype %K postmarket surveillance system %K fast healthcare interoperability resources %K FHIR %K real-world data %K validation study %K Food and Drug Administration %K electronic health records %K COVID-19 vaccine %D 2024 %7 25.11.2024 %9 Original Paper %J J Med Internet Res %G English %X Background: Adverse events (AEs) associated with vaccination have traditionally been evaluated by epidemiological studies. More recently, they have gained attention due to the emergency use authorization of several COVID-19 vaccines. As part of its responsibility to conduct postmarket surveillance, the US Food and Drug Administration continues to monitor several AEs of interest to ensure the safety of vaccines, including those for COVID-19. Objective: This study is part of the Biologics Effectiveness and Safety Initiative, which aims to improve the US Food and Drug Administration’s postmarket surveillance capabilities while minimizing the burden of collecting clinical data on suspected postvaccination AEs. The objective of this study was to enhance active surveillance efforts through a pilot platform that can receive automatically reported AE cases through a health care data exchange. Methods: We detected cases by sharing and applying computable phenotype algorithms to real-world data in health care providers’ electronic health records databases. Using the fast healthcare interoperability resources standard for secure data transmission, we implemented a computable phenotype algorithm on a new health care system. The study focused on the algorithm's positive predictive value, validated through clinical records, assessing both the time required for implementation and the accuracy of AE detection. Results: The algorithm required 200-250 hours to implement and optimize. Of the 6,574,420 clinical encounters across 694,151 patients, 30 cases were identified as potential myocarditis/pericarditis. Of these, 26 cases were retrievable, and 24 underwent clinical validation. In total, 14 cases were confirmed as definite or probable myocarditis/pericarditis, yielding a positive predictive value of 58.3% (95% CI 37.3%-76.9%). These findings underscore the algorithm's capability for real-time detection of AEs, though they also highlight variability in performance across different health care systems. Conclusions: The study advocates for the ongoing refinement and application of distributed computable phenotype algorithms to enhance AE detection capabilities. These tools are crucial for comprehensive postmarket surveillance and improved vaccine safety monitoring. The outcomes suggest the need for further optimization to achieve more consistent results across diverse health care settings. %M 39586081 %R 10.2196/54597 %U https://www.jmir.org/2024/1/e54597 %U https://doi.org/10.2196/54597 %U http://www.ncbi.nlm.nih.gov/pubmed/39586081 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 12 %N %P e63795 %T Using Machine Learning to Predict the Duration of Atrial Fibrillation: Model Development and Validation %A Shimoo,Satoshi %A Senoo,Keitaro %A Okawa,Taku %A Kawai,Kohei %A Makino,Masahiro %A Munakata,Jun %A Tomura,Nobunari %A Iwakoshi,Hibiki %A Nishimura,Tetsuro %A Shiraishi,Hirokazu %A Inoue,Keiji %A Matoba,Satoaki %+ Department of Cardiac Arrhythmia Research and Innovation, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto-shi, Kamigyo-ku Kajii-cho 465, Kawaramachi-Hirokoji, Kyoto, 602-8566, Japan, 81 8031117168, k-senoo@koto.kpu-m.ac.jp %K persistent atrial fibrillation %K atrial fibrillation duration %K 12-lead electrocardiogram %K machine learning %K support system %D 2024 %7 22.11.2024 %9 Original Paper %J JMIR Med Inform %G English %X Background: Atrial fibrillation (AF) is a progressive disease, and its clinical type is classified according to the AF duration: paroxysmal AF, persistent AF (PeAF; AF duration of less than 1 year), and long-standing persistent AF (AF duration of more than 1 year). When considering the indication for catheter ablation, having a long AF duration is considered a risk factor for recurrence, and therefore, the duration of AF is an important factor in determining the treatment strategy for PeAF. Objective: This study aims to improve the accuracy of the cardiologists’ diagnosis of the AF duration, and the steps to achieve this goal are to develop a predictive model of the AF duration and validate the support performance of the prediction model. Methods: The study included 272 patients with PeAF (aged 20-90 years), with data obtained between January 1, 2015, and December 31, 2023. Of those, 189 (69.5%) were included in the study, excluding 83 (30.5%) who met the exclusion criteria. Of the 189 patients included, 145 (76.7%) were used as training data to build the machine learning (ML) model and 44 (23.3%) were used as test data for predictive ability of the ML model. Using a questionnaire, 10 cardiologists (group A) evaluated whether the test data (44 patients) included AF of more than a 1-year duration (phase 1). Next, the same questionnaire was performed again after providing the ML model’s answer (phase 2). Subsequently, another 10 cardiologists (group B) were shown the test results of group A, were made aware of the limitations of their own diagnostic abilities, and were then administered the same 2-stage test as group A. Results: The prediction results with the ML model using the test data provided 81.8% accuracy (72% sensitivity and 89% specificity). The mean percentage of correct answers in group A was 63.9% (SD 9.6%) for phase 1 and improved to 71.6% (SD 9.3%) for phase 2 (P=.01). The mean percentage of correct answers in group B was 59.8% (SD 5.3%) for phase 1 and improved to 68.2% (SD 5.9%) for phase 2 (P=.007). The mean percentage of answers that differed from the ML model’s prediction for phase 2 (percentage of answers where cardiologists did not trust the ML model and believed their own determination) was 17.3% (SD 10.3%) in group A and 20.9% (SD 5%) in group B and was not significantly different (P=.85). Conclusions: ML models predicting AF duration improved the diagnostic ability of cardiologists. However, cardiologists did not entirely rely on the ML model’s prediction, even if they were aware of their diagnostic capability limitations. %M 39576988 %R 10.2196/63795 %U https://medinform.jmir.org/2024/1/e63795 %U https://doi.org/10.2196/63795 %U http://www.ncbi.nlm.nih.gov/pubmed/39576988 %0 Journal Article %@ 2561-326X %I JMIR Publications %V 8 %N %P e54792 %T Associations Among Cardiometabolic Risk Factors, Sleep Duration, and Obstructive Sleep Apnea in a Southeastern US Rural Community: Cross-Sectional Analysis From the SLUMBRx-PONS Study %A Knowlden,Adam P %A Winchester,Lee J %A MacDonald,Hayley V %A Geyer,James D %A Higginbotham,John C %+ Department of Health Science, The University of Alabama, Russell Hall 104, Box 870313, Tuscaloosa, AL, 35487, United States, 1 2053481625, apknowlden@ua.edu %K obstructive sleep apnea %K obesity %K adiposity %K cardiometabolic %K cardiometabolic disease %K risk factors %K sleep %K sleep duration %K sleep apnea %K Short Sleep Undermines Cardiometabolic Health-Public Health Observational study %K SLUMBRx study %D 2024 %7 8.11.2024 %9 Original Paper %J JMIR Form Res %G English %X Background: Short sleep and obstructive sleep apnea are underrecognized strains on the public health infrastructure. In the United States, over 35% of adults report short sleep and more than 80% of individuals with obstructive sleep apnea remain undiagnosed. The associations between inadequate sleep and cardiometabolic disease risk factors have garnered increased attention. However, challenges persist in modeling sleep-associated cardiometabolic disease risk factors. Objective: This study aimed to report early findings from the Short Sleep Undermines Cardiometabolic Health-Public Health Observational study (SLUMBRx-PONS). Methods: Data for the SLUMBRx-PONS study were collected cross-sectionally and longitudinally from a nonclinical, rural community sample (n=47) in the southeast United States. Measures included 7 consecutive nights of wrist-based actigraphy (eg, mean of 7 consecutive nights of total sleep time [TST7N]), 1 night of sleep apnea home testing (eg, apnea-hypopnea index [AHI]), and a cross-sectional clinical sample of anthropometric (eg, BMI), cardiovascular (eg, blood pressure), and blood-based biomarkers (eg, triglycerides and glucose). Correlational analyses and regression models assessed the relationships between the cardiometabolic disease risk factors and the sleep indices (eg, TST7N and AHI). Linear regression models were constructed to examine associations between significant cardiometabolic indices of TST7N (model 1) and AHI (model 2). Results: Correlational assessment in model 1 identified significant associations between TST7N and AHI (r=–0.45, P=.004), BMI (r=–0.38, P=.02), systolic blood pressure (r=0.40, P=.01), and diastolic blood pressure (r=0.32, P=.049). Pertaining to model 1, composite measures of AHI, BMI, systolic blood pressure, and diastolic blood pressure accounted for 25.1% of the variance in TST7N (R2adjusted=0.25; F2,38=7.37; P=.002). Correlational analyses in model 2 revealed significant relationships between AHI and TST7N (r=–0.45, P<.001), BMI (r=0.71, P<.001), triglycerides (r=0.36, P=.03), and glucose (r=0.34, P=.04). Results from model 2 found that TST7N, triglycerides, and glucose accounted for 37.6% of the variance in the composite measure of AHI and BMI (R2adjusted=0.38; F3,38=8.63; P<.001). Conclusions: Results from the SLUMBRx-PONS study highlight the complex interplay between sleep-associated risk factors for cardiometabolic disease. Early findings underscore the need for further investigations incorporating the collection of clinical, epidemiological, and ambulatory measures to inform public health, health promotion, and health education interventions addressing the cardiometabolic consequences of inadequate sleep. International Registered Report Identifier (IRRID): RR2-10.2196/27139 %M 39514856 %R 10.2196/54792 %U https://formative.jmir.org/2024/1/e54792 %U https://doi.org/10.2196/54792 %U http://www.ncbi.nlm.nih.gov/pubmed/39514856 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e54746 %T Comparison of Auscultation Quality Using Contemporary Digital Stethoscopes %A Saraya,Norah %A McBride,Jonathon %A Singh,Karandeep %A Sohail,Omar %A Das,Porag Jeet %+ Department of Learning Health Sciences, University of Michigan, North Ingalls Building, 300 N Ingalls St, Ann Arbor, MI, 48109, United States, 1 734 936 1649, karandeep@health.ucsd.edu %K auscultation %K digital stethoscopes %K valvular heart disease %D 2024 %7 8.11.2024 %9 Research Letter %J JMIR Cardio %G English %X %M 39514245 %R 10.2196/54746 %U https://cardio.jmir.org/2024/1/e54746 %U https://doi.org/10.2196/54746 %U http://www.ncbi.nlm.nih.gov/pubmed/39514245 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e52794 %T Machine Learning–Based Prediction for Incident Hypertension Based on Regular Health Checkup Data: Derivation and Validation in 2 Independent Nationwide Cohorts in South Korea and Japan %A Hwang,Seung Ha %A Lee,Hayeon %A Lee,Jun Hyuk %A Lee,Myeongcheol %A Koyanagi,Ai %A Smith,Lee %A Rhee,Sang Youl %A Yon,Dong Keon %A Lee,Jinseok %+ Department of Biomedical Engineering, Kyung Hee University, 1732 Deogyeong-daero, Yongin, 17104, Republic of Korea, 82 312012570, gonasago@khu.ac.kr %K machine learning %K hypertension %K cardiovascular disease %K artificial intelligence %K cause of death %K cardiovascular risk %K predictive analytics %D 2024 %7 5.11.2024 %9 Original Paper %J J Med Internet Res %G English %X Background: Worldwide, cardiovascular diseases are the primary cause of death, with hypertension as a key contributor. In 2019, cardiovascular diseases led to 17.9 million deaths, predicted to reach 23 million by 2030. Objective: This study presents a new method to predict hypertension using demographic data, using 6 machine learning models for enhanced reliability and applicability. The goal is to harness artificial intelligence for early and accurate hypertension diagnosis across diverse populations. Methods: Data from 2 national cohort studies, National Health Insurance Service-National Sample Cohort (South Korea, n=244,814), conducted between 2002 and 2013 were used to train and test machine learning models designed to anticipate incident hypertension within 5 years of a health checkup involving those aged ≥20 years, and Japanese Medical Data Center cohort (Japan, n=1,296,649) were used for extra validation. An ensemble from 6 diverse machine learning models was used to identify the 5 most salient features contributing to hypertension by presenting a feature importance analysis to confirm the contribution of each future. Results: The Adaptive Boosting and logistic regression ensemble showed superior balanced accuracy (0.812, sensitivity 0.806, specificity 0.818, and area under the receiver operating characteristic curve 0.901). The 5 key hypertension indicators were age, diastolic blood pressure, BMI, systolic blood pressure, and fasting blood glucose. The Japanese Medical Data Center cohort dataset (extra validation set) corroborated these findings (balanced accuracy 0.741 and area under the receiver operating characteristic curve 0.824). The ensemble model was integrated into a public web portal for predicting hypertension onset based on health checkup data. Conclusions: Comparative evaluation of our machine learning models against classical statistical models across 2 distinct studies emphasized the former’s enhanced stability, generalizability, and reproducibility in predicting hypertension onset. %M 39499554 %R 10.2196/52794 %U https://www.jmir.org/2024/1/e52794 %U https://doi.org/10.2196/52794 %U http://www.ncbi.nlm.nih.gov/pubmed/39499554 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 12 %N %P e58732 %T Predictive Models for Sustained, Uncontrolled Hypertension and Hypertensive Crisis Based on Electronic Health Record Data: Algorithm Development and Validation %A Nguyen,Hieu Minh %A Anderson,William %A Chou,Shih-Hsiung %A McWilliams,Andrew %A Zhao,Jing %A Pajewski,Nicholas %A Taylor,Yhenneko %K machine learning %K risk prediction %K predictive model %K decision support %K blood pressure %K cardiovascular %K electronic health record %D 2024 %7 28.10.2024 %9 %J JMIR Med Inform %G English %X Background: Assessing disease progression among patients with uncontrolled hypertension is important for identifying opportunities for intervention. Objective: We aim to develop and validate 2 models, one to predict sustained, uncontrolled hypertension (≥2 blood pressure [BP] readings ≥140/90 mm Hg or ≥1 BP reading ≥180/120 mm Hg) and one to predict hypertensive crisis (≥1 BP reading ≥180/120 mm Hg) within 1 year of an index visit (outpatient or ambulatory encounter in which an uncontrolled BP reading was recorded). Methods: Data from 142,897 patients with uncontrolled hypertension within Atrium Health Greater Charlotte in 2018 were used. Electronic health record–based predictors were based on the 1-year period before a patient’s index visit. The dataset was randomly split (80:20) into a training set and a validation set. In total, 4 machine learning frameworks were considered: L2-regularized logistic regression, multilayer perceptron, gradient boosting machines, and random forest. Model selection was performed with 10-fold cross-validation. The final models were assessed on discrimination (C-statistic), calibration (eg, integrated calibration index), and net benefit (with decision curve analysis). Additionally, internal-external cross-validation was performed at the county level to assess performance with new populations and summarized using random-effect meta-analyses. Results: In internal validation, the C-statistic and integrated calibration index were 0.72 (95% CI 0.71‐0.72) and 0.015 (95% CI 0.012‐0.020) for the sustained, uncontrolled hypertension model, and 0.81 (95% CI 0.79‐0.82) and 0.009 (95% CI 0.007‐0.011) for the hypertensive crisis model. The models had higher net benefit than the default policies (ie, treat-all and treat-none) across different decision thresholds. In internal-external cross-validation, the pooled performance was consistent with internal validation results; in particular, the pooled C-statistics were 0.70 (95% CI 0.69‐0.71) and 0.79 (95% CI 0.78‐0.81) for the sustained, uncontrolled hypertension model and hypertensive crisis model, respectively. Conclusions: An electronic health record–based model predicted hypertensive crisis reasonably well in internal and internal-external validations. The model can potentially be used to support population health surveillance and hypertension management. Further studies are needed to improve the ability to predict sustained, uncontrolled hypertension. %R 10.2196/58732 %U https://medinform.jmir.org/2024/1/e58732 %U https://doi.org/10.2196/58732 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e54242 %T Gender Bias in AI's Perception of Cardiovascular Risk %A Achtari,Margaux %A Salihu,Adil %A Muller,Olivier %A Abbé,Emmanuel %A Clair,Carole %A Schwarz,Joëlle %A Fournier,Stephane %+ Department of Cardiology, Lausanne University Hospital and University of Lausanne, 21 Rue Du Bugnon, Lausanne, CH-1011, Switzerland, 41 21 314 00 12, stephane.fournier@chuv.ch %K artificial intelligence %K gender equity %K coronary artery disease %K AI %K cardiovascular %K risk %K CAD %K artery %K coronary %K chatbot: health care %K men: women %K gender bias %K gender %D 2024 %7 22.10.2024 %9 Research Letter %J J Med Internet Res %G English %X The study investigated gender bias in GPT-4’s assessment of coronary artery disease risk by presenting identical clinical vignettes of men and women with and without psychiatric comorbidities. Results suggest that psychiatric conditions may influence GPT-4’s coronary artery disease risk assessment among men and women. %M 39437384 %R 10.2196/54242 %U https://www.jmir.org/2024/1/e54242 %U https://doi.org/10.2196/54242 %U http://www.ncbi.nlm.nih.gov/pubmed/39437384 %0 Journal Article %@ 1929-073X %I JMIR Publications %V 13 %N %P e56207 %T Dynamics of Blood Lipids Before, During, and After Diurnal Fasting in Inactive Men: Quasi-Experimental Study %A Aljaloud,Khalid %A Al-Barha,Naif %A Noman,Abeer %A Aldayel,Abdulaziz %A Alsharif,Yahya %A Alshuwaier,Ghareeb %+ Department of Exercise Physiology, College of Sport Sciences and Physical Activity, King Saud University, P O Box 2454, Riyadh, 11451, Saudi Arabia, 966 0118063100, khaljaloud@ksu.edu.sa %K cardiovascular diseases %K cardiovascular risk factors %K lipids %K glucose measurement %K fasting %K Ramadan %K body composition %D 2024 %7 17.10.2024 %9 Original Paper %J Interact J Med Res %G English %X Background: There is a lack of investigation into the dynamics of blood lipids before, during, and after diurnal fasting, especially in inactive men. Objective: This study determined dynamic changes in blood lipids in inactive men before, during, and after they underwent diurnal fasting. Methods: A total of 44 young men aged a mean 27.6 (SD 5.8) years were recruited to evaluate their habitual physical activity and diet using a questionnaire developed for this study. Body composition was evaluated using a bioelectrical impedance analysis machine (Tanita BC-980). An 8-ml blood sample was collected to evaluate blood lipids and glucose. All measurements were taken 2-3 days before Ramadan, during Ramadan (at week 2 and week 3), and 1 month after Ramadan. A 1-way repeated measures ANOVA was used to compare the measured variables before, during, and after the month of Ramadan. When a significant difference was found, post hoc testing was used. Differences were considered significant at P<.05. Results: There was a significant reduction in low-density lipoprotein during Ramadan compared to before and after Ramadan (83.49 mg/dl at week 3 vs 93.11 mg/dl before Ramadan [P=.02] and 101.59 mg/dl after Ramadan [P=.007]). There were significant elevations in fasting blood glucose (74.60 mmol/L before Ramadan vs 81.52 mmol/L at week 3 [P=.03] and 86.51 mmol/L after Ramadan [P=.01]) and blood pressure (109 mm Hg before Ramadan vs 114 mm Hg after Ramadan; P=.02) reported during and even after the month of Ramadan, although both fasting blood glucose and blood pressure were within normal levels. Conclusions: Ramadan fasting could be an independent factor in reducing low-density lipoprotein. Further investigations are encouraged to clarify the impact of diurnal fasting on blood lipids in people with special conditions. %M 39419506 %R 10.2196/56207 %U https://www.i-jmr.org/2024/1/e56207 %U https://doi.org/10.2196/56207 %U http://www.ncbi.nlm.nih.gov/pubmed/39419506 %0 Journal Article %@ 2369-2960 %I JMIR Publications %V 10 %N %P e60128 %T The Role of Visualization in Estimating Cardiovascular Disease Risk: Scoping Review %A Svenšek,Adrijana %A Lorber,Mateja %A Gosak,Lucija %A Verbert,Katrien %A Klemenc-Ketis,Zalika %A Stiglic,Gregor %+ Faculty of Health Sciences, University of Maribor, Žitna ulica 15, Maribor, 2000, Slovenia, 386 2 30 04 762, adrijana.svensek1@um.si %K cardiovascular disease prevention %K risk factors %K visual analytics %K visualization %K mobile phone %K PRISMA %D 2024 %7 14.10.2024 %9 Review %J JMIR Public Health Surveill %G English %X Background: Supporting and understanding the health of patients with chronic diseases and cardiovascular disease (CVD) risk is often a major challenge. Health data are often used in providing feedback to patients, and visualization plays an important role in facilitating the interpretation and understanding of data and, thus, influencing patients’ behavior. Visual analytics enable efficient analysis and understanding of large datasets in real time. Digital health technologies can promote healthy lifestyle choices and assist in estimating CVD risk. Objective: This review aims to present the most-used visualization techniques to estimate CVD risk. Methods: In this scoping review, we followed the Joanna Briggs Institute PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. The search strategy involved searching databases, including PubMed, CINAHL Ultimate, MEDLINE, and Web of Science, and gray literature from Google Scholar. This review included English-language articles on digital health, mobile health, mobile apps, images, charts, and decision support systems for estimating CVD risk, as well as empirical studies, excluding irrelevant studies and commentaries, editorials, and systematic reviews. Results: We found 774 articles and screened them against the inclusion and exclusion criteria. The final scoping review included 17 studies that used different methodologies, including descriptive, quantitative, and population-based studies. Some prognostic models, such as the Framingham Risk Profile, World Health Organization and International Society of Hypertension risk prediction charts, Cardiovascular Risk Score, and a simplified Persian atherosclerotic CVD risk stratification, were simpler and did not require laboratory tests, whereas others, including the Joint British Societies recommendations on the prevention of CVD, Systematic Coronary Risk Evaluation, and Framingham-Registre Gironí del COR, were more complex and required laboratory testing–related results. The most frequently used prognostic risk factors were age, sex, and blood pressure (16/17, 94% of the studies); smoking status (14/17, 82%); diabetes status (11/17, 65%); family history (10/17, 59%); high-density lipoprotein and total cholesterol (9/17, 53%); and triglycerides and low-density lipoprotein cholesterol (6/17, 35%). The most frequently used visualization techniques in the studies were visual cues (10/17, 59%), followed by bar charts (5/17, 29%) and graphs (4/17, 24%). Conclusions: On the basis of the scoping review, we found that visualization is very rarely included in the prognostic models themselves even though technology-based interventions improve health care worker performance, knowledge, motivation, and compliance by integrating machine learning and visual analytics into applications to identify and respond to estimation of CVD risk. Visualization aids in understanding risk factors and disease outcomes, improving bioinformatics and biomedicine. However, evidence on mobile health’s effectiveness in improving CVD outcomes is limited. %M 39401079 %R 10.2196/60128 %U https://publichealth.jmir.org/2024/1/e60128 %U https://doi.org/10.2196/60128 %U http://www.ncbi.nlm.nih.gov/pubmed/39401079 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e51321 %T The Influence of Physical Activity and Diet Mobile Apps on Cardiovascular Disease Risk Factors: Meta-Review %A Bushey,Erica %A Wu,Yin %A Wright,Alexander %A Pescatello,Linda %+ University of Connecticut, 2098 Hillside Rd, Storrs, CT, United States, 1 860 486 0008, erica.bushey@uconn.edu %K physical activity %K diet %K mobile applications %K obesity %K hypertension %K dyslipidemia %K diabetes %K mobile phone %D 2024 %7 9.10.2024 %9 Review %J J Med Internet Res %G English %X Background: The literature on whether physical activity (PA) and PA and diet (PA+Diet) mobile apps improve cardiovascular disease (CVD) risk factors is promising. Objective: The aim of this meta-review is to provide an evidence synthesis of systematic reviews and meta-analyses examining the influence of PA and PA+Diet apps on the major CVD risk factors. Methods: We systematically searched 5 databases until January 12, 2022. Included systematic reviews and meta-analyses (1) reported the CVD risk factor outcomes of BMI, waist circumference, body weight, blood pressure (BP), hemoglobin A1c (HbA1c), fasting blood glucose, blood lipids, or PA; (2) enrolled healthy participants ≥18 years who may or may not have the metabolic syndrome, diabetes mellitus, or preexisting CVD risk factors; (3) reviewed PA or PA+Diet app interventions integrating behavioral change techniques (BCT) to deliver their information; and (4) had a nonapp control. Results: In total, 17 reviews (9 systematic reviews and 8 meta-analyses) published between 2012 and 2021 qualified. Participants were middle-aged, mostly women ranging in number from 10 to 62,219. Interventions lasted from 1 to 24 months, with the most common behavioral strategies being personalized feedback (n=8), self-monitoring (n=7), and goal setting (n=5). Of the PA app systematic reviews (N=4), the following CVD risk factors improved: body weight and BMI (n=2, 50%), BP (n=1, 25%), HbA1c (n=1, 25%), and blood lipids (n=1, 25%) decreased, while PA (n=4, 100%) increased. Of the PA+Diet app systematic reviews (N=5), the following CVD risk factors improved: body weight and BMI (n=3, 60%), BP (n=1, 20%), and HbA1c (n=3, 60%) decreased, while PA (n=3, 60%) increased. Of the PA app meta-analyses (N=1), the following CVD risk factors improved: body weight decreased (–0.73 kg, 95% CI –1.45 to –0.01; P=.05) and PA increased by 25 minutes/week (95% CI 0.58-1.68; P<.001), while BMI (–0.09 kg/m2, 95% CI –0.29 to 0.10; P=.35) and waist circumference (–1.92 cm, 95% CI –3.94 to 0.09; P=.06) tended to decrease. Of the PA+Diet app meta-analyses (n=4), the following CVD risk factors improved: body weight (n=4, 100%; from –1.79 kg 95% CI –3.17 to –0.41; P=.01 to –2.80 kg 95% CI –4.54 to –1.06, P=.002), BMI (n=1, 25%; –0.64 kg/m2, 95% CI –1.09 to –0.18; P=.01), waist circumference (n=1, 25%; –2.46 cm, 95% CI –4.56 to –0.36; P=.02), systolic/diastolic BP (n=1, 25%; –4.22/–2.87 mm Hg, 95% CI –6.54 to –1.91/ –4.44 to –1.29; P<.01), and HbA1c (n=1, 25%; –0.43%, 95% CI –0.68 to –0.19; P<.001) decreased. Conclusions: PA and PA+Diet apps appear to be most consistent in improving PA and anthropometric measures with favorable but less consistent effects on other CVD risk factors. Future studies are needed that directly compare and better quantify the effects of PA and PA+Diet apps on CVD risk factors. Trial Registration: PROSPERO CRD42023392359; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=392359 %M 39382958 %R 10.2196/51321 %U https://www.jmir.org/2024/1/e51321 %U https://doi.org/10.2196/51321 %U http://www.ncbi.nlm.nih.gov/pubmed/39382958 %0 Journal Article %@ 2369-2960 %I JMIR Publications %V 10 %N %P e55261 %T Changes in 10-Year Predicted Cardiovascular Disease Risk for a Multiethnic Semirural Population in South East Asia: Prospective Study %A Johar,Hamimatunnisa %A Ang,Chiew Way %A Ismail,Roshidi %A Kassim,Zaid %A Su,Tin Tin %+ South East Asia Community Observatory (SEACO) & Global Public Health, Jeffrey Cheah School of Medicine and Health Sciences, Monash University Malaysia, Jalan Lagoon Selatan, Bandar Sunway, Subang Jaya, 47500, Malaysia, 60 55146000, TinTin.Su@monash.edu %K cardiovascular risk trajectory %K Framingham risk score %K population-based study %K low- and middle-income countries %D 2024 %7 26.9.2024 %9 Original Paper %J JMIR Public Health Surveill %G English %X Background: Cardiovascular disease (CVD) risk factors tend to cluster and interact multiplicatively and have been incorporated into risk equations such as the Framingham risk score, which can reasonably predict CVD over short- and long-term periods. Beyond risk factor levels at a single time point, recent evidence demonstrated that risk trajectories are differentially related to CVD risk. However, factors associated with suboptimal control or unstable CVD risk trajectories are not yet established. Objective: This study aims to examine factors associated with CVD risk trajectories in a semirural, multiethnic community-dwelling population. Methods: Data on demographic, socioeconomic, lifestyle, mental health, and cardiovascular factors were measured at baseline (2013) and during follow-up (2018) of the South East Asia Community Observatory cohort. The 10-year CVD risk change transition was computed. The trajectory patterns identified were improved; remained unchanged in low, moderate, or high CVD risk clusters; and worsened CVD risk trajectories. Multivariable regression analyses were used to examine the association between risk factors and changes in Framingham risk score and predicted CVD risk trajectory patterns with adjustments for concurrent risk factors. Results: Of the 6599 multiethnic community-dwelling individuals (n=3954, 59.92% female participants and n=2645, 40.08% male participants; mean age 55.3, SD 10.6 years), CVD risk increased over time in 33.37% (n=2202) of the sample population, while 24.38% (n=1609 remained in the high-risk trajectory pattern, which was reflected by the increased prevalence of all major CVD risk factors over the 5-year follow-up. Meanwhile, sex-specific prevalence data indicate that 21.44% (n=567) of male and 41.35% (n=1635) of female participants experienced an increase in CVD risk. However, a stark sex difference was observed in those remaining in the high CVD risk cluster, with 45.1% (n=1193) male participants and 10.52% (n=416) female participants. Regarding specific CVD risk factors, male participants exhibited a higher percentage increase in the prevalence of hypertension, antihypertensive medication use, smoking, and obesity, while female participants showed a higher prevalence of diabetes. Further regression analyses identified that Malay compared to Chinese (P<.001) and Indian (P=.04) ethnicity, nonmarried status (P<.001), full-time employment (P<.001), and depressive symptoms (P=.04) were all significantly associated with increased CVD risk scores. In addition, lower educational levels and frequently having meals from outside were significantly associated to higher odds of both worsening and remaining in high CVD risk trajectories. Conclusions: Sociodemographics and mental health were found to be differently associated with CVD risk trajectories, warranting future research to disentangle the role of psychosocial disparities in CVD. Our findings carry public health implications, suggesting that the rise in major risk factors along with psychosocial disparities could potentially elevate CVD risk among individuals in underserved settings. More prevention efforts that continuously monitor CVD risk and consider changes in risk factors among vulnerable populations should be emphasized. %M 39326046 %R 10.2196/55261 %U https://publichealth.jmir.org/2024/1/e55261 %U https://doi.org/10.2196/55261 %U http://www.ncbi.nlm.nih.gov/pubmed/39326046 %0 Journal Article %@ 2369-2960 %I JMIR Publications %V 10 %N %P e53371 %T Social Determinants of Health Phenotypes and Cardiometabolic Condition Prevalence Among Patients in a Large Academic Health System: Latent Class Analysis %A Howell,Carrie R %A Zhang,Li %A Clay,Olivio J %A Dutton,Gareth %A Horton,Trudi %A Mugavero,Michael J %A Cherrington,Andrea L %K social determinants of health %K electronic medical record %K phenotypes %K diabetes %K obesity %K cardiovascular disease %K obese %K social determinants %K social determinant %K cardiometabolic %K risk factors %K risk factor %K latent class analysis %K cardiometabolic disease %K EMR %K EHR %K electronic medical record %K electronic health record %D 2024 %7 7.8.2024 %9 %J JMIR Public Health Surveill %G English %X Background: Adverse social determinants of health (SDoH) have been associated with cardiometabolic disease; however, disparities in cardiometabolic outcomes are rarely the result of a single risk factor. Objective: This study aimed to identify and characterize SDoH phenotypes based on patient-reported and neighborhood-level data from the institutional electronic medical record and evaluate the prevalence of diabetes, obesity, and other cardiometabolic diseases by phenotype status. Methods: Patient-reported SDoH were collected (January to December 2020) and neighborhood-level social vulnerability, neighborhood socioeconomic status, and rurality were linked via census tract to geocoded patient addresses. Diabetes status was coded in the electronic medical record using International Classification of Diseases codes; obesity was defined using measured BMI ≥30 kg/m2. Latent class analysis was used to identify clusters of SDoH (eg, phenotypes); we then examined differences in the prevalence of cardiometabolic conditions based on phenotype status using prevalence ratios (PRs). Results: Complete data were available for analysis for 2380 patients (mean age 53, SD 16 years; n=1405, 59% female; n=1198, 50% non-White). Roughly 8% (n=179) reported housing insecurity, 30% (n=710) reported resource needs (food, health care, or utilities), and 49% (n=1158) lived in a high-vulnerability census tract. We identified 3 patient SDoH phenotypes: (1) high social risk, defined largely by self-reported SDoH (n=217, 9%); (2) adverse neighborhood SDoH (n=1353, 56%), defined largely by adverse neighborhood-level measures; and (3) low social risk (n=810, 34%), defined as low individual- and neighborhood-level risks. Patients with an adverse neighborhood SDoH phenotype had higher prevalence of diagnosed type 2 diabetes (PR 1.19, 95% CI 1.06‐1.33), hypertension (PR 1.14, 95% CI 1.02‐1.27), peripheral vascular disease (PR 1.46, 95% CI 1.09‐1.97), and heart failure (PR 1.46, 95% CI 1.20‐1.79). Conclusions: Patients with the adverse neighborhood SDoH phenotype had higher prevalence of poor cardiometabolic conditions compared to phenotypes determined by individual-level characteristics, suggesting that neighborhood environment plays a role, even if individual measures of socioeconomic status are not suboptimal. %R 10.2196/53371 %U https://publichealth.jmir.org/2024/1/e53371 %U https://doi.org/10.2196/53371 %0 Journal Article %@ 2292-9495 %I JMIR Publications %V 11 %N %P e48584 %T Assessing Patient Trust in Automation in Health Care Systems: Within-Subjects Experimental Study %A Nare,Matthew %A Jurewicz,Katherina %+ School of Industrial Engineering and Management, Oklahoma State University, 329 Engineering North, Stillwater, OK, 74078, United States, 1 405 744 4167, katie.jurewicz@okstate.edu %K automation %K emergency department %K trust %K health care %K artificial intelligence %K emergency %K perceptions %K attitude %K opinions %K belief %K automated %K trust ratings %D 2024 %7 6.8.2024 %9 Original Paper %J JMIR Hum Factors %G English %X Background: Health care technology has the ability to change patient outcomes for the betterment when designed appropriately. Automation is becoming smarter and is increasingly being integrated into health care work systems. Objective: This study focuses on investigating trust between patients and an automated cardiac risk assessment tool (CRAT) in a simulated emergency department setting. Methods: A within-subjects experimental study was performed to investigate differences in automation modes for the CRAT: (1) no automation, (2) automation only, and (3) semiautomation. Participants were asked to enter their simulated symptoms for each scenario into the CRAT as instructed by the experimenter, and they would automatically be classified as high, medium, or low risk depending on the symptoms entered. Participants were asked to provide their trust ratings for each combination of risk classification and automation mode on a scale of 1 to 10 (1=absolutely no trust and 10=complete trust). Results: Results from this study indicate that the participants significantly trusted the semiautomation condition more compared to the automation-only condition (P=.002), and they trusted the no automation condition significantly more than the automation-only condition (P=.03). Additionally, participants significantly trusted the CRAT more in the high-severity scenario compared to the medium-severity scenario (P=.004). Conclusions: The findings from this study emphasize the importance of the human component of automation when designing automated technology in health care systems. Automation and artificially intelligent systems are becoming more prevalent in health care systems, and this work emphasizes the need to consider the human element when designing automation into care delivery. %M 39106096 %R 10.2196/48584 %U https://humanfactors.jmir.org/2024/1/e48584 %U https://doi.org/10.2196/48584 %U http://www.ncbi.nlm.nih.gov/pubmed/39106096 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e50067 %T A Machine Learning Model for Predicting In-Hospital Mortality in Chinese Patients With ST-Segment Elevation Myocardial Infarction: Findings From the China Myocardial Infarction Registry %A Yang,Jingang %A Li,Yingxue %A Li,Xiang %A Tao,Shuiying %A Zhang,Yuan %A Chen,Tiange %A Xie,Guotong %A Xu,Haiyan %A Gao,Xiaojin %A Yang,Yuejin %+ State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College, No 167, Beilishi Road, Xicheng District, Beijing, 100037, China, 86 13701151408, Yangyjfw@126.com %K ST-elevation myocardial infarction %K in-hospital mortality %K risk prediction %K explainable machine learning %K machine learning %K acute myocardial infarction %K myocardial infarction %K mortality %K risk %K predication model %K china %K clinical practice %K validation %K patient management %K management %D 2024 %7 30.7.2024 %9 Original Paper %J J Med Internet Res %G English %X Background: Machine learning (ML) risk prediction models, although much more accurate than traditional statistical methods, are inconvenient to use in clinical practice due to their nontransparency and requirement of a large number of input variables. Objective: We aimed to develop a precise, explainable, and flexible ML model to predict the risk of in-hospital mortality in patients with ST-segment elevation myocardial infarction (STEMI). Methods: This study recruited 18,744 patients enrolled in the 2013 China Acute Myocardial Infarction (CAMI) registry and 12,018 patients from the China Patient-Centered Evaluative Assessment of Cardiac Events (PEACE)-Retrospective Acute Myocardial Infarction Study. The Extreme Gradient Boosting (XGBoost) model was derived from 9616 patients in the CAMI registry (2014, 89 variables) with 5-fold cross-validation and validated on both the 9125 patients in the CAMI registry (89 variables) and the independent China PEACE cohort (10 variables). The Shapley Additive Explanations (SHAP) approach was employed to interpret the complex relationships embedded in the proposed model. Results: In the XGBoost model for predicting all-cause in-hospital mortality, the variables with the top 8 most important scores were age, left ventricular ejection fraction, Killip class, heart rate, creatinine, blood glucose, white blood cell count, and use of angiotensin-converting enzyme inhibitors (ACEIs) and angiotensin II receptor blockers (ARBs). The area under the curve (AUC) on the CAMI validation set was 0.896 (95% CI 0.884-0.909), significantly higher than the previous models. The AUC for the Global Registry of Acute Coronary Events (GRACE) model was 0.809 (95% CI 0.790-0.828), and for the TIMI model, it was 0.782 (95% CI 0.763-0.800). Despite the China PEACE validation set only having 10 available variables, the AUC reached 0.840 (0.829-0.852), showing a substantial improvement to the GRACE (0.762, 95% CI 0.748-0.776) and TIMI (0.789, 95% CI 0.776-0.803) scores. Several novel and nonlinear relationships were discovered between patients’ characteristics and in-hospital mortality, including a U-shape pattern of high-density lipoprotein cholesterol (HDL-C). Conclusions: The proposed ML risk prediction model was highly accurate in predicting in-hospital mortality. Its flexible and explainable characteristics make the model convenient to use in clinical practice and could help guide patient management. Trial Registration: ClinicalTrials.gov NCT01874691; https://clinicaltrials.gov/study/NCT01874691 %M 39079111 %R 10.2196/50067 %U https://www.jmir.org/2024/1/e50067 %U https://doi.org/10.2196/50067 %U http://www.ncbi.nlm.nih.gov/pubmed/39079111 %0 Journal Article %@ 2561-7605 %I JMIR Publications %V 7 %N %P e54872 %T Development and Validation of an Explainable Machine Learning Model for Predicting Myocardial Injury After Noncardiac Surgery in Two Centers in China: Retrospective Study %A Liu,Chang %A Zhang,Kai %A Yang,Xiaodong %A Meng,Bingbing %A Lou,Jingsheng %A Liu,Yanhong %A Cao,Jiangbei %A Liu,Kexuan %A Mi,Weidong %A Li,Hao %K myocardial injury after noncardiac surgery %K older patients %K machine learning %K personalized prediction %K myocardial injury %K risk prediction %K noncardiac surgery %D 2024 %7 26.7.2024 %9 %J JMIR Aging %G English %X Background: Myocardial injury after noncardiac surgery (MINS) is an easily overlooked complication but closely related to postoperative cardiovascular adverse outcomes; therefore, the early diagnosis and prediction are particularly important. Objective: We aimed to develop and validate an explainable machine learning (ML) model for predicting MINS among older patients undergoing noncardiac surgery. Methods: The retrospective cohort study included older patients who had noncardiac surgery from 1 northern center and 1 southern center in China. The data sets from center 1 were divided into a training set and an internal validation set. The data set from center 2 was used as an external validation set. Before modeling, the least absolute shrinkage and selection operator and recursive feature elimination methods were used to reduce dimensions of data and select key features from all variables. Prediction models were developed based on the extracted features using several ML algorithms, including category boosting, random forest, logistic regression, naïve Bayes, light gradient boosting machine, extreme gradient boosting, support vector machine, and decision tree. Prediction performance was assessed by the area under the receiver operating characteristic (AUROC) curve as the main evaluation metric to select the best algorithms. The model performance was verified by internal and external validation data sets with the best algorithm and compared to the Revised Cardiac Risk Index. The Shapley Additive Explanations (SHAP) method was applied to calculate values for each feature, representing the contribution to the predicted risk of complication, and generate personalized explanations. Results: A total of 19,463 eligible patients were included; among those, 12,464 patients in center 1 were included as the training set; 4754 patients in center 1 were included as the internal validation set; and 2245 in center 2 were included as the external validation set. The best-performing model for prediction was the CatBoost algorithm, achieving the highest AUROC of 0.805 (95% CI 0.778‐0.831) in the training set, validating with an AUROC of 0.780 in the internal validation set and 0.70 in external validation set. Additionally, CatBoost demonstrated superior performance compared to the Revised Cardiac Risk Index (AUROC 0.636; P<.001). The SHAP values indicated the ranking of the level of importance of each variable, with preoperative serum creatinine concentration, red blood cell distribution width, and age accounting for the top three. The results from the SHAP method can predict events with positive values or nonevents with negative values, providing an explicit explanation of individualized risk predictions. Conclusions: The ML models can provide a personalized and fairly accurate risk prediction of MINS, and the explainable perspective can help identify potentially modifiable sources of risk at the patient level. %R 10.2196/54872 %U https://aging.jmir.org/2024/1/e54872 %U https://doi.org/10.2196/54872 %0 Journal Article %@ 2563-6316 %I %V 5 %N %P e45973 %T Performance Drift in Machine Learning Models for Cardiac Surgery Risk Prediction: Retrospective Analysis %A Dong,Tim %A Sinha,Shubhra %A Zhai,Ben %A Fudulu,Daniel %A Chan,Jeremy %A Narayan,Pradeep %A Judge,Andy %A Caputo,Massimo %A Dimagli,Arnaldo %A Benedetto,Umberto %A Angelini,Gianni D %K cardiac surgery %K artificial intelligence %K risk prediction %K machine learning %K operative mortality %K data set drift %K performance drift %K national data set %K adult %K data %K cardiac %K surgery %K cardiology %K heart %K risk %K prediction %K United Kingdom %K mortality %K performance %K model %D 2024 %7 12.6.2024 %9 %J JMIRx Med %G English %X Background: The Society of Thoracic Surgeons and European System for Cardiac Operative Risk Evaluation (EuroSCORE) II risk scores are the most commonly used risk prediction models for in-hospital mortality after adult cardiac surgery. However, they are prone to miscalibration over time and poor generalization across data sets; thus, their use remains controversial. Despite increased interest, a gap in understanding the effect of data set drift on the performance of machine learning (ML) over time remains a barrier to its wider use in clinical practice. Data set drift occurs when an ML system underperforms because of a mismatch between the data it was developed from and the data on which it is deployed. Objective: In this study, we analyzed the extent of performance drift using models built on a large UK cardiac surgery database. The objectives were to (1) rank and assess the extent of performance drift in cardiac surgery risk ML models over time and (2) investigate any potential influence of data set drift and variable importance drift on performance drift. Methods: We conducted a retrospective analysis of prospectively, routinely gathered data on adult patients undergoing cardiac surgery in the United Kingdom between 2012 and 2019. We temporally split the data 70:30 into a training and validation set and a holdout set. Five novel ML mortality prediction models were developed and assessed, along with EuroSCORE II, for relationships between and within variable importance drift, performance drift, and actual data set drift. Performance was assessed using a consensus metric. Results: A total of 227,087 adults underwent cardiac surgery during the study period, with a mortality rate of 2.76% (n=6258). There was strong evidence of a decrease in overall performance across all models (P<.0001). Extreme gradient boosting (clinical effectiveness metric [CEM] 0.728, 95% CI 0.728-0.729) and random forest (CEM 0.727, 95% CI 0.727-0.728) were the overall best-performing models, both temporally and nontemporally. EuroSCORE II performed the worst across all comparisons. Sharp changes in variable importance and data set drift from October to December 2017, from June to July 2018, and from December 2018 to February 2019 mirrored the effects of performance decrease across models. Conclusions: All models show a decrease in at least 3 of the 5 individual metrics. CEM and variable importance drift detection demonstrate the limitation of logistic regression methods used for cardiac surgery risk prediction and the effects of data set drift. Future work will be required to determine the interplay between ML models and whether ensemble models could improve on their respective performance advantages. %R 10.2196/45973 %U https://xmed.jmir.org/2024/1/e45973 %U https://doi.org/10.2196/45973 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e49848 %T Development and Validation of an Explainable Deep Learning Model to Predict In-Hospital Mortality for Patients With Acute Myocardial Infarction: Algorithm Development and Validation Study %A Xie,Puguang %A Wang,Hao %A Xiao,Jun %A Xu,Fan %A Liu,Jingyang %A Chen,Zihang %A Zhao,Weijie %A Hou,Siyu %A Wu,Dongdong %A Ma,Yu %A Xiao,Jingjing %+ Bio-Med Informatics Research Centre & Clinical Research Centre, Xinqiao Hospital, Army Medical University, No. 183 Xinqiao Street, Shapingba District, Chongqing, 400037, China, 86 18502299862, shine636363@sina.com %K acute myocardial infarction %K mortality %K deep learning %K explainable model %K prediction %D 2024 %7 10.5.2024 %9 Original Paper %J J Med Internet Res %G English %X Background: Acute myocardial infarction (AMI) is one of the most severe cardiovascular diseases and is associated with a high risk of in-hospital mortality. However, the current deep learning models for in-hospital mortality prediction lack interpretability. Objective: This study aims to establish an explainable deep learning model to provide individualized in-hospital mortality prediction and risk factor assessment for patients with AMI. Methods: In this retrospective multicenter study, we used data for consecutive patients hospitalized with AMI from the Chongqing University Central Hospital between July 2016 and December 2022 and the Electronic Intensive Care Unit Collaborative Research Database. These patients were randomly divided into training (7668/10,955, 70%) and internal test (3287/10,955, 30%) data sets. In addition, data of patients with AMI from the Medical Information Mart for Intensive Care database were used for external validation. Deep learning models were used to predict in-hospital mortality in patients with AMI, and they were compared with linear and tree-based models. The Shapley Additive Explanations method was used to explain the model with the highest area under the receiver operating characteristic curve in both the internal test and external validation data sets to quantify and visualize the features that drive predictions. Results: A total of 10,955 patients with AMI who were admitted to Chongqing University Central Hospital or included in the Electronic Intensive Care Unit Collaborative Research Database were randomly divided into a training data set of 7668 (70%) patients and an internal test data set of 3287 (30%) patients. A total of 9355 patients from the Medical Information Mart for Intensive Care database were included for independent external validation. In-hospital mortality occurred in 8.74% (670/7668), 8.73% (287/3287), and 9.12% (853/9355) of the patients in the training, internal test, and external validation cohorts, respectively. The Self-Attention and Intersample Attention Transformer model performed best in both the internal test data set and the external validation data set among the 9 prediction models, with the highest area under the receiver operating characteristic curve of 0.86 (95% CI 0.84-0.88) and 0.85 (95% CI 0.84-0.87), respectively. Older age, high heart rate, and low body temperature were the 3 most important predictors of increased mortality, according to the explanations of the Self-Attention and Intersample Attention Transformer model. Conclusions: The explainable deep learning model that we developed could provide estimates of mortality and visual contribution of the features to the prediction for a patient with AMI. The explanations suggested that older age, unstable vital signs, and metabolic disorders may increase the risk of mortality in patients with AMI. %M 38728685 %R 10.2196/49848 %U https://www.jmir.org/2024/1/e49848 %U https://doi.org/10.2196/49848 %U http://www.ncbi.nlm.nih.gov/pubmed/38728685 %0 Journal Article %@ 2369-2960 %I JMIR Publications %V 10 %N %P e46821 %T Assessing Global, Regional, and National Time Trends and Associated Risk Factors of the Mortality in Ischemic Heart Disease Through Global Burden of Disease 2019 Study: Population-Based Study %A Shu,Tingting %A Tang,Ming %A He,Bo %A Liu,Xiaozhu %A Han,Yu %A Liu,Chang %A Jose,Pedro A %A Wang,Hongyong %A Zhang,Qing-Wei %A Zeng,Chunyu %+ Department of Cardiology, Daping Hospital, The Third Military Medical University (Army Medical University), 10 Daping Branch Road, Yuzhong District, Chongqing, 400016, China, 86 023 68729501, chunyuzeng01@163.com %K age-period-cohort analysis %K GBD 2019 %K Global Burden of Disease 2019 study %K ischemic heart disease %K mortality %K risk factors %D 2024 %7 24.1.2024 %9 Original Paper %J JMIR Public Health Surveill %G English %X Background: Ischemic heart disease (IHD) is the leading cause of death among noncommunicable diseases worldwide, but data on current epidemiological patterns and associated risk factors are lacking. Objective: This study assessed the global, regional, and national trends in IHD mortality and attributable risks since 1990. Methods: Mortality data were obtained from the Global Burden of Disease 2019 Study. We used an age-period-cohort model to calculate longitudinal age curves (expected longitudinal age-specific rate), net drift (overall annual percentage change), and local drift (annual percentage change in each age group) from 15 to >95 years of age and estimate cohort and period effects between 1990 and 2019. Deaths from IHD attributable to each risk factor were estimated on the basis of risk exposure, relative risks, and theoretical minimum risk exposure level. Results: IHD is the leading cause of death in noncommunicable disease–related mortality (118.1/598.8, 19.7%). However, the age-standardized mortality rate for IHD decreased by 30.8% (95% CI –34.83% to –27.17%) over the past 30 years, and its net drift ranged from –2.89% (95% CI –3.07% to –2.71%) in high sociodemographic index (SDI) region to –0.24% (95% CI –0.32% to –0.16%) in low-middle–SDI region. The greatest decrease in IHD mortality occurred in the Republic of Korea (high SDI) with net drift –6.06% (95% CI –6.23% to –5.88%), followed by 5 high-SDI nations (Denmark, Norway, Estonia, the Netherlands, and Ireland) and 2 high-middle–SDI nations (Israel and Bahrain) with net drift less than –5.00%. Globally, age groups of >60 years continued to have the largest proportion of IHD-related mortality, with slightly higher mortality in male than female group. For period and birth cohort effects, the trend of rate ratios for IHD mortality declined across successive period groups from 2000 to 2004 and birth cohort groups from 1985 to 2000, with noticeable improvements in high-SDI regions. In low-SDI regions, IHD mortality significantly declined in female group but fluctuated in male group across successive periods; sex differences were greater in those born after 1945 in middle- and low-middle–SDI regions and after 1970 in low-SDI regions. Metabolic risks were the leading cause of mortality from IHD worldwide in 2019. Moreover, smoking, particulate matter pollution, and dietary risks were also important risk factors, increasingly occurring at a younger age. Diets low in whole grains and legumes were prominent dietary risks in both male and female groups, and smoking and high-sodium diet mainly affect male group. Conclusions: IHD, a major concern, needs focused health care attention, especially for older male individuals and those in low-SDI regions. Metabolic risks should be prioritized for prevention, and behavioral and environmental risks should attract more attention to decrease IHD mortality. %M 38265846 %R 10.2196/46821 %U https://publichealth.jmir.org/2024/1/e46821 %U https://doi.org/10.2196/46821 %U http://www.ncbi.nlm.nih.gov/pubmed/38265846 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 26 %N %P e46277 %T Association Between the Composite Cardiovascular Risk and mHealth Use Among Adults in the 2017-2020 Health Information National Trends Survey: Cross-Sectional Study %A Chen,Yuling %A Turkson-Ocran,Ruth-Alma %A Koirala,Binu %A Davidson,Patricia M %A Commodore-Mensah,Yvonne %A Himmelfarb,Cheryl Dennison %+ Johns Hopkins University School of Nursing, 525 North Wolfe Street, Baltimore, MD, 21205, United States, 1 443 514 7323, chimmelfarb@jhu.edu %K mobile health %K usage %K cardiovascular risk %K association %K mobile phone %D 2024 %7 4.1.2024 %9 Original Paper %J J Med Internet Res %G English %X Background: Numerous studies have suggested that the relationship between cardiovascular disease (CVD) risk and the usage of mobile health (mHealth) technology may vary depending on the total number of CVD risk factors present. However, whether higher CVD risk is associated with a greater likelihood of engaging in specific mHealth use among US adults is currently unknown. Objective: We aim to assess the associations between the composite CVD risk and each component of mHealth use among US adults regardless of whether they have a history of CVD or not. Methods: This study used cross-sectional data from the 2017 to 2020 Health Information National Trends Survey. The exposure was CVD risk (diabetes, hypertension, smoking, physical inactivity, and overweight or obesity). We defined low, moderate, and high CVD risk as having 0-1, 2-3, and 4-5 CVD risk factors, respectively. The outcome variables of interest were each component of mHealth use, including using mHealth to make health decisions, track health progress, share health information, and discuss health decisions with health providers. We used multivariable logistic regression models to examine the association between CVD risk and mHealth use adjusted for demographic factors. Results: We included 10,531 adults, with a mean age of 54 (SD 16.2) years. Among the included participants, 50.2% were men, 65.4% were non-Hispanic White, 41.9% used mHealth to make health decisions, 50.8% used mHealth to track health progress toward a health-related goal, 18.3% used mHealth to share health information with health providers, and 37.7% used mHealth to discuss health decisions with health providers (all are weighted percentages). Adults with moderate CVD risk were more likely to use mHealth to share health information with health providers (adjusted odds ratio 1.49, 95% CI 1.24-1.80) and discuss health decisions with health providers (1.22, 95% CI 1.04-1.44) compared to those with low CVD risk. Similarly, having high CVD risk was associated with higher odds of using mHealth to share health information with health providers (2.61, 95% CI 1.93-3.54) and discuss health decisions with health providers (1.56, 95% CI 1.17-2.10) compared to those with low CVD risk. Upon stratifying by age and gender, we observed age and gender disparities in the relationship between CVD risk and the usage of mHealth to discuss health decisions with health providers. Conclusions: Adults with a greater number of CVD risk factors were more likely to use mHealth to share health information with health providers and discuss health decisions with health providers. These findings suggest a promising avenue for enhancing health care communication and advancing both primary and secondary prevention efforts related to managing CVD risk factors through the effective usage of mHealth technology. %M 38175685 %R 10.2196/46277 %U https://www.jmir.org/2024/1/e46277 %U https://doi.org/10.2196/46277 %U http://www.ncbi.nlm.nih.gov/pubmed/38175685 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 25 %N %P e47664 %T Development and Validation of Machine Learning–Based Models to Predict In-Hospital Mortality in Life-Threatening Ventricular Arrhythmias: Retrospective Cohort Study %A Li,Le %A Ding,Ligang %A Zhang,Zhuxin %A Zhou,Likun %A Zhang,Zhenhao %A Xiong,Yulong %A Hu,Zhao %A Yao,Yan %+ National Center for Cardiovascular Diseases, Fu Wai Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Beilishi Road 167, Beijing, 100037, China, 86 88322405, ianyao@263.net.cn %K life-threatening ventricular arrhythmia %K mortality %K prediction model %K machine learning %K critical care %K cardiac %K mortality %D 2023 %7 15.11.2023 %9 Original Paper %J J Med Internet Res %G English %X Background: Life-threatening ventricular arrhythmias (LTVAs) are main causes of sudden cardiac arrest and are highly associated with an increased risk of mortality. A prediction model that enables early identification of the high-risk individuals is still lacking. Objective: We aimed to build machine learning (ML)–based models to predict in-hospital mortality in patients with LTVA. Methods: A total of 3140 patients with LTVA were randomly divided into training (n=2512, 80%) and internal validation (n=628, 20%) sets. Moreover, data of 2851 patients from another database were collected as the external validation set. The primary output was the probability of in-hospital mortality. The discriminatory ability was evaluated by the area under the receiver operating characteristic curve (AUC). The prediction performances of 5 ML algorithms were compared with 2 conventional scoring systems, namely, the simplified acute physiology score (SAPS-II) and the logistic organ dysfunction system (LODS). Results: The prediction performance of the 5 ML algorithms significantly outperformed the traditional models in predicting in-hospital mortality. CatBoost showed the highest AUC of 90.5% (95% CI 87.5%-93.5%), followed by LightGBM with an AUC of 90.1% (95% CI 86.8%-93.4%). Conversely, the predictive values of SAPS-II and LODS were unsatisfactory, with AUCs of 78.0% (95% CI 71.7%-84.3%) and 74.9% (95% CI 67.2%-82.6%), respectively. The superiority of ML-based models was also shown in the external validation set. Conclusions: ML-based models could improve the predictive values of in-hospital mortality prediction for patients with LTVA compared with traditional scoring systems. %M 37966870 %R 10.2196/47664 %U https://www.jmir.org/2023/1/e47664 %U https://doi.org/10.2196/47664 %U http://www.ncbi.nlm.nih.gov/pubmed/37966870 %0 Journal Article %@ 2561-326X %I JMIR Publications %V 7 %N %P e42756 %T Identification of Risk Groups for and Factors Affecting Metabolic Syndrome in South Korean Single-Person Households Using Latent Class Analysis and Machine Learning Techniques: Secondary Analysis Study %A Lee,Ji-Soo %A Lee,Soo-Kyoung %+ Big Data Convergence and Open Sharing System, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, 08826, Republic of Korea, 82 2 889 5710, soo1005s@gmail.com %K latent class analysis %K machine learning %K metabolic syndrome %K risk factor %K single-person households %D 2023 %7 12.9.2023 %9 Original Paper %J JMIR Form Res %G English %X Background: The rapid increase of single-person households in South Korea is leading to an increase in the incidence of metabolic syndrome, which causes cardiovascular and cerebrovascular diseases, due to lifestyle changes. It is necessary to analyze the complex effects of metabolic syndrome risk factors in South Korean single-person households, which differ from one household to another, considering the diversity of single-person households. Objective: This study aimed to identify the factors affecting metabolic syndrome in single-person households using machine learning techniques and categorically characterize the risk factors through latent class analysis (LCA). Methods: This cross-sectional study included 10-year secondary data obtained from the National Health and Nutrition Examination Survey (2009-2018). We selected 1371 participants belonging to single-person households. Data were analyzed using SPSS (version 25.0; IBM Corp), Mplus (version 8.0; Muthen & Muthen), and Python (version 3.0; Plone & Python). We applied 4 machine learning algorithms (logistic regression, decision tree, random forest, and extreme gradient boost) to identify important factors and then applied LCA to categorize the risk groups of metabolic syndromes in single-person households. Results: Through LCA, participants were classified into 4 groups (group 1: intense physical activity in early adulthood, group 2: hypertension among middle-aged female respondents, group 3: smoking and drinking among middle-aged male respondents, and group 4: obesity and abdominal obesity among middle-aged respondents). In addition, age, BMI, obesity, subjective body shape recognition, alcohol consumption, smoking, binge drinking frequency, and job type were investigated as common factors that affect metabolic syndrome in single-person households through machine learning techniques. Group 4 was the most susceptible and at-risk group for metabolic syndrome (odds ratio 17.67, 95% CI 14.5-25.3; P<.001), and obesity and abdominal obesity were the most influential risk factors for metabolic syndrome. Conclusions: This study identified risk groups and factors affecting metabolic syndrome in single-person households through machine learning techniques and LCA. Through these findings, customized interventions for each generational risk factor for metabolic syndrome can be implemented, leading to the prevention of metabolic syndrome, which causes cardiovascular and cerebrovascular diseases. In conclusion, this study contributes to the prevention of metabolic syndrome in single-person households by providing new insights and priority groups for the development of customized interventions using classification. %M 37698907 %R 10.2196/42756 %U https://formative.jmir.org/2023/1/e42756 %U https://doi.org/10.2196/42756 %U http://www.ncbi.nlm.nih.gov/pubmed/37698907 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 7 %N %P e46533 %T A Web-Based Application for Risk Stratification and Optimization in Patients With Cardiovascular Disease: Pilot Study %A Pandey,Avinash %A D'Souza,Marie Michelle %A Pandey,Amritanshu Shekhar %A Mir,Hassan %+ Department of Medicine, University of Ottawa, 451 Smyth Rd #2044, Ottawa, ON, K1H 8M5, Canada, 1 (613) 562 5409, avinash.pandey@medportal.ca %K atherosclerotic cardiovascular disease %K guideline-directed medical therapy %K mHealth %K mobile health %K risk stratification %K secondary prevention %K web application %D 2023 %7 3.8.2023 %9 Original Paper %J JMIR Cardio %G English %X Background: In addition to aspirin, angiotensin-converting enzyme inhibitors, statins, and lifestyle modification interventions, novel pharmacological agents have been shown to reduce morbidity and mortality in atherosclerotic cardiovascular disease patients, including new antithrombotics, antihyperglycemics, and lipid-modulating therapies. Despite their benefits, the uptake of these guideline-directed therapies remains a challenge. There is a need to develop strategies to support knowledge translation for the uptake of secondary prevention therapies. Objective: The goal of this study was to test the feasibility and usability of Stratification and Optimization in Patients With Cardiovascular Disease (STOP-CVD), a point-of-care application that was designed to facilitate knowledge translation by providing individualized risk stratification and optimization guidance. Methods: Using the REACH (Reduction of Atherothrombosis for Continued Health) Registry trial and predictive modeling (which included 67,888 patients), we designed a free web-based secondary risk calculator. Based on demographic and comorbidity profiles, the application was used to predict an individual’s 20-month risk of cardiovascular events and cardiovascular mortality and provides a comparison to an age-matched control with an optimized cardiovascular risk profile to illustrate the modifiable residual risk. Additionally, the application used the patient’s risk profile to provide specific guidance for possible therapeutic interventions based on a novel algorithm. During an initial 3-month adoption phase, 1-time invitations were sent through email and telephone to 240 physicians that refer to a regional cardiovascular clinic. After 3 months, a survey of user experience was sent to all users. Following this, no further marketing of the application was performed. Google Analytics was collected postimplementation from January 2021 to December 2021. These were used to tabulate the total number of distinct users and the total number of monthly uses of the application. Results: During the 1-year pilot, 47 of the 240 invited clinicians used the application 1573 times, an average of 131 times per month, with sustained usage over time. All 24 postimplementation survey respondents confirmed that the application was functional, easy to use, and useful. Conclusions: This pilot suggests that the STOP-CVD application is feasible and usable, with high clinician satisfaction. This tool can be easily scaled to support the uptake of guideline-directed medical therapy, which could improve clinical outcomes. Future research will be focused on evaluating the impact of this tool on clinician management and patient outcomes. %M 37535400 %R 10.2196/46533 %U https://cardio.jmir.org/2023/1/e46533 %U https://doi.org/10.2196/46533 %U http://www.ncbi.nlm.nih.gov/pubmed/37535400 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 7 %N %P e39097 %T The Impact and Perception of England’s Web-Based Heart Age Test of Cardiovascular Disease Risk: Mixed Methods Study %A Riley,Victoria %A Gidlow,Christopher %A Fedorowicz,Sophia %A Lagord,Catherine %A Thompson,Katherine %A Woolner,Joshua %A Taylor,Rosie %A Clark,Jade %A Lloyd-Harris,Andrew %+ Centre for Health and Development, Staffordshire University, Ashley Building, Leek Road, Stoke-on-Trent, ST4 2DF, United Kingdom, 44 01782294330 ext 4430, c.gidlow@staffs.ac.uk %K heart age %K cardiovascular disease %K CVD prevention %K web-based risk assessment %K CVD risk %K qualitative research %K cross-sectional design %K cardiology %K risk assessment %K cardiovascular risk %K heart health %K user perception %K risk knowledge %K engagement %K web-based %D 2023 %7 6.2.2023 %9 Original Paper %J JMIR Cardio %G English %X Background: It is well documented that individuals struggle to understand cardiovascular disease (CVD) percentage risk scores, which led to the development of heart age as a means of communicating risk. Developed for clinical use, its application in raising public awareness of heart health as part of a self-directed digital test has not been considered previously. Objective: This study aimed to understand who accesses England’s heart age test (HAT) and its effect on user perception, knowledge, and understanding of CVD risk; future behavior intentions; and potential engagement with primary care services. Methods: There were 3 sources of data: routinely gathered data on all individuals accessing the HAT (February 2015 to June 2020); web-based survey, distributed between January 2021 and March 2021; and interviews with a subsample of survey respondents (February 2021 to March 2021). Data were used to describe the test user population and explore knowledge and understanding of CVD risk, confidence in interpreting and controlling CVD risk, and effect on future behavior intentions and potential engagement with primary care. Interviews were analyzed using reflexive thematic analysis. Results: Between February 2015 and June 2020, the HAT was completed approximately 5 million times, with more completions by men (2,682,544/4,898,532, 54.76%), those aged between 50 to 59 years (1,334,195/4,898,532, 27.24%), those from White ethnic background (3,972,293/4,898,532, 81.09%), and those living in the least deprived 20% of areas (707,747/4,898,532, 14.45%). The study concluded with 819 survey responses and 33 semistructured interviews. Participants stated that they understood the meaning of high estimated heart age and self-reported at least some improvement in the understanding and confidence in understanding and controlling CVD risk. Negative emotional responses were provoked among users when estimated heart age did not equate to their previous risk perceptions. The limited information needed to complete it or the production of a result when physiological risk factor information was missing (ie, blood pressure and cholesterol level) led some users to question the credibility of the test. However, most participants who were interviewed mentioned that they would recommend or had already recommended the test to others, would use it again in the future, and would be more likely to take up the offer of a National Health Service Health Check and self-reported that they had made or intended to make changes to their health behavior or felt encouraged to continue to make changes to their health behavior. Conclusions: England’s web-based HAT has engaged large number of people in their heart health. Improvements to England’s HAT, noted in this paper, may enhance user satisfaction and prevent confusion. Future studies to understand the long-term benefit of the test on behavioral outcomes are warranted. %M 36745500 %R 10.2196/39097 %U https://cardio.jmir.org/2023/1/e39097 %U https://doi.org/10.2196/39097 %U http://www.ncbi.nlm.nih.gov/pubmed/36745500 %0 Journal Article %@ 2368-7959 %I JMIR Publications %V 10 %N %P e40342 %T When Heart Beats Differently in Depression: Review of Nonlinear Heart Rate Variability Measures %A Čukić,Milena %A Savić,Danka %A Sidorova,Julia %+ Empa Materials Science and Technology, Empa Swiss Federal Institute, Lerchenfeldstrasse 5, St Gallen, 9014, Switzerland, 41 +41587657070, milena.cukic@gmail.com %K heart rate variability %K HRV %K electrocardiogram %K ECG %K depression %K autonomous nervous system %K ANS %K nonlinear measures %K cardiac risk %K cardiovascular %K mortality %K heart dynamics %K ECG analysis %K analysis %K online %D 2023 %7 17.1.2023 %9 Review %J JMIR Ment Health %G English %X Background: Disturbed heart dynamics in depression seriously increases mortality risk. Heart rate variability (HRV) is a rich source of information for studying this dynamics. This paper is a meta-analytic review with methodological commentary of the application of nonlinear analysis of HRV and its possibility to address cardiovascular diseases in depression. Objective: This paper aimed to appeal for the introduction of cardiological screening to patients with depression, because it is still far from established practice. The other (main) objective of the paper was to show that nonlinear methods in HRV analysis give better results than standard ones. Methods: We systematically searched on the web for papers on nonlinear analyses of HRV in depression, in line with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 framework recommendations. We scrutinized the chosen publications and performed random-effects meta-analysis, using the esci module in jamovi software where standardized effect sizes (ESs) are corrected to yield the proof of the practical utility of their results. Results: In all, 26 publications on the connection of nonlinear HRV measures and depression meeting our inclusion criteria were selected, examining a total of 1537 patients diagnosed with depression and 1041 healthy controls (N=2578). The overall ES (unbiased) was 1.03 (95% CI 0.703-1.35; diamond ratio 3.60). We performed 3 more meta-analytic comparisons, demonstrating the overall effectiveness of 3 groups of nonlinear analysis: detrended fluctuation analysis (overall ES 0.364, 95% CI 0.237-0.491), entropy-based measures (overall ES 1.05, 95% CI 0.572-1.52), and all other nonlinear measures (overall ES 0.702, 95% CI 0.422-0.982). The effectiveness of the applied methods of electrocardiogram analysis was compared and discussed in the light of detection and prevention of depression-related cardiovascular risk. Conclusions: We compared the ESs of nonlinear and conventional time and spectral methods (found in the literature) and demonstrated that those of the former are larger, which recommends their use for the early screening of cardiovascular abnormalities in patients with depression to prevent possible deleterious events. %M 36649063 %R 10.2196/40342 %U https://mental.jmir.org/2023/1/e40342 %U https://doi.org/10.2196/40342 %U http://www.ncbi.nlm.nih.gov/pubmed/36649063 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 6 %N 2 %P e38040 %T The Impact of Time Horizon on Classification Accuracy: Application of Machine Learning to Prediction of Incident Coronary Heart Disease %A Simon,Steven %A Mandair,Divneet %A Albakri,Abdel %A Fohner,Alison %A Simon,Noah %A Lange,Leslie %A Biggs,Mary %A Mukamal,Kenneth %A Psaty,Bruce %A Rosenberg,Michael %+ Division of Cardiology, University of Colorado School of Medicine, 13001 E 17th Pl, Aurora, CO, 80045, United States, 1 303 724 6946, steven.simon@cuanschutz.edu %K coronary heart disease %K risk prediction %K machine learning %K heart %K heart disease %K clinical %K risk %K myocardial %K gender %D 2022 %7 2.11.2022 %9 Original Paper %J JMIR Cardio %G English %X Background: Many machine learning approaches are limited to classification of outcomes rather than longitudinal prediction. One strategy to use machine learning in clinical risk prediction is to classify outcomes over a given time horizon. However, it is not well-known how to identify the optimal time horizon for risk prediction. Objective: In this study, we aim to identify an optimal time horizon for classification of incident myocardial infarction (MI) using machine learning approaches looped over outcomes with increasing time horizons. Additionally, we sought to compare the performance of these models with the traditional Framingham Heart Study (FHS) coronary heart disease gender-specific Cox proportional hazards regression model. Methods: We analyzed data from a single clinic visit of 5201 participants of a cardiovascular health study. We examined 61 variables collected from this baseline exam, including demographic and biologic data, medical history, medications, serum biomarkers, electrocardiographic, and echocardiographic data. We compared several machine learning methods (eg, random forest, L1 regression, gradient boosted decision tree, support vector machine, and k-nearest neighbor) trained to predict incident MI that occurred within time horizons ranging from 500-10,000 days of follow-up. Models were compared on a 20% held-out testing set using area under the receiver operating characteristic curve (AUROC). Variable importance was performed for random forest and L1 regression models across time points. We compared results with the FHS coronary heart disease gender-specific Cox proportional hazards regression functions. Results: There were 4190 participants included in the analysis, with 2522 (60.2%) female participants and an average age of 72.6 years. Over 10,000 days of follow-up, there were 813 incident MI events. The machine learning models were most predictive over moderate follow-up time horizons (ie, 1500-2500 days). Overall, the L1 (Lasso) logistic regression demonstrated the strongest classification accuracy across all time horizons. This model was most predictive at 1500 days follow-up, with an AUROC of 0.71. The most influential variables differed by follow-up time and model, with gender being the most important feature for the L1 regression and weight for the random forest model across all time frames. Compared with the Framingham Cox function, the L1 and random forest models performed better across all time frames beyond 1500 days. Conclusions: In a population free of coronary heart disease, machine learning techniques can be used to predict incident MI at varying time horizons with reasonable accuracy, with the strongest prediction accuracy in moderate follow-up periods. Validation across additional populations is needed to confirm the validity of this approach in risk prediction. %M 36322114 %R 10.2196/38040 %U https://cardio.jmir.org/2022/2/e38040 %U https://doi.org/10.2196/38040 %U http://www.ncbi.nlm.nih.gov/pubmed/36322114 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 6 %N 2 %P e31302 %T Home Telemonitoring and a Diagnostic Algorithm in the Management of Heart Failure in the Netherlands: Cost-effectiveness Analysis %A Albuquerque de Almeida,Fernando %A Corro Ramos,Isaac %A Al,Maiwenn %A Rutten-van Mölken,Maureen %+ Erasmus School of Health Policy and Management, Erasmus University Rotterdam, P.O. Box 1738, Rotterdam, 3000 DR, Netherlands, 351 918795283, albuquerquedealmeida@eshpm.eur.nl %K discrete event simulation %K cost-effectiveness %K early warning systems %K home telemonitoring %K diagnostic algorithm %K heart failure %D 2022 %7 4.8.2022 %9 Original Paper %J JMIR Cardio %G English %X Background: Heart failure is a major health concern associated with significant morbidity, mortality, and reduced quality of life in patients. Home telemonitoring (HTM) facilitates frequent or continuous assessment of disease signs and symptoms, and it has shown to improve compliance by involving patients in their own care and prevent emergency admissions by facilitating early detection of clinically significant changes. Diagnostic algorithms (DAs) are predictive mathematical relationships that make use of a wide range of collected data for calculating the likelihood of a particular event and use this output for prioritizing patients with regard to their treatment. Objective: This study aims to assess the cost-effectiveness of HTM and a DA in the management of heart failure in the Netherlands. Three interventions were analyzed: usual care, HTM, and HTM plus a DA. Methods: A previously published discrete event simulation model was used. The base-case analysis was performed according to the Dutch guidelines for economic evaluation. Sensitivity, scenario, and value of information analyses were performed. Particular attention was given to the cost-effectiveness of the DA at various levels of diagnostic accuracy of event prediction and to different patient subgroups. Results: HTM plus the DA extendedly dominates HTM alone, and it has a deterministic incremental cost-effectiveness ratio compared with usual care of €27,712 (currency conversion rate in purchasing power parity at the time of study: €1=US $1.29; further conversions are not applicable in cost-effectiveness terms) per quality-adjusted life year. The model showed robustness in the sensitivity and scenario analyses. HTM plus the DA had a 96.0% probability of being cost-effective at the appropriate €80,000 per quality-adjusted life year threshold. An optimal point for the threshold value for the alarm of the DA in terms of its cost-effectiveness was estimated. New York Heart Association class IV patients were the subgroup with the worst cost-effectiveness results versus usual care, while HTM plus the DA was found to be the most cost-effective for patients aged <65 years and for patients in New York Heart Association class I. Conclusions: Although the increased costs of adopting HTM plus the DA in the management of heart failure may seemingly be an additional strain on scarce health care resources, the results of this study demonstrate that, by increasing patient life expectancy by 1.28 years and reducing their hospitalization rate by 23% when compared with usual care, the use of this technology may be seen as an investment, as HTM plus the DA in its current form extendedly dominates HTM alone and is cost-effective compared with usual care at normally accepted thresholds in the Netherlands. %M 35925670 %R 10.2196/31302 %U https://cardio.jmir.org/2022/2/e31302 %U https://doi.org/10.2196/31302 %U http://www.ncbi.nlm.nih.gov/pubmed/35925670 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 10 %N 4 %P e33395 %T Risk Prediction of Major Adverse Cardiovascular Events Occurrence Within 6 Months After Coronary Revascularization: Machine Learning Study %A Wang,Jinwan %A Wang,Shuai %A Zhu,Mark Xuefang %A Yang,Tao %A Yin,Qingfeng %A Hou,Ya %+ School of Information Management, Nanjing University, No163 Xianlin Road, Qixia District, Nanjing, 210023, China, 86 13770727298, xfzhu@nju.edu.cn %K major adverse cardiovascular events %K risk prediction %K machine learning %K oversampling %K data imbalance %D 2022 %7 20.4.2022 %9 Original Paper %J JMIR Med Inform %G English %X Background: As a major health hazard, the incidence of coronary heart disease has been increasing year by year. Although coronary revascularization, mainly percutaneous coronary intervention, has played an important role in the treatment of coronary heart disease, major adverse cardiovascular events (MACE) such as recurrent or persistent angina pectoris after coronary revascularization remain a very difficult problem in clinical practice. Objective: Given the high probability of MACE after coronary revascularization, the aim of this study was to develop and validate a predictive model for MACE occurrence within 6 months based on machine learning algorithms. Methods: A retrospective study was performed including 1004 patients who had undergone coronary revascularization at The People’s Hospital of Liaoning Province and Affiliated Hospital of Liaoning University of Traditional Chinese Medicine from June 2019 to December 2020. According to the characteristics of available data, an oversampling strategy was adopted for initial preprocessing. We then employed six machine learning algorithms, including decision tree, random forest, logistic regression, naïve Bayes, support vector machine, and extreme gradient boosting (XGBoost), to develop prediction models for MACE depending on clinical information and 6-month follow-up information. Among all samples, 70% were randomly selected for training and the remaining 30% were used for model validation. Model performance was assessed based on accuracy, precision, recall, F1-score, confusion matrix, area under the receiver operating characteristic (ROC) curve (AUC), and visualization of the ROC curve. Results: Univariate analysis showed that 21 patient characteristic variables were statistically significant (P<.05) between the groups without and with MACE. Coupled with these significant factors, among the six machine learning algorithms, XGBoost stood out with an accuracy of 0.7788, precision of 0.8058, recall of 0.7345, F1-score of 0.7685, and AUC of 0.8599. Further exploration of the models to identify factors affecting the occurrence of MACE revealed that use of anticoagulant drugs and course of the disease consistently ranked in the top two predictive factors in three developed models. Conclusions: The machine learning risk models constructed in this study can achieve acceptable performance of MACE prediction, with XGBoost performing the best, providing a valuable reference for pointed intervention and clinical decision-making in MACE prevention. %M 35442202 %R 10.2196/33395 %U https://medinform.jmir.org/2022/4/e33395 %U https://doi.org/10.2196/33395 %U http://www.ncbi.nlm.nih.gov/pubmed/35442202 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 6 %N 1 %P e36801 %T Authors’ Reply to: Using Caution When Interpreting Gender-Based Relative Risk. Comment on “The Effect of Cardiovascular Comorbidities on Women Compared to Men: Longitudinal Retrospective Analysis” %A Dervic,Elma %A Deischinger,Carola %A Haug,Nina %A Leutner,Michael %A Kautzky-Willer,Alexandra %A Klimek,Peter %+ Section for Science of Complex Systems, Center for Medical Statistics, Informatics and Intelligent Systems, Medical University of Vienna, Spitalgasse 23, Vienna, 1090, Austria, 43 1 40160 362, peter.klimek@meduniwien.ac.at %K gender gap %K sex differences %K cardiovascular diseases %K acute myocardial infarction %K chronic ischemic heart disease %K gender %K diabetes %K smoking %K risk factors %K comorbidities %K relative risk %K interaction %D 2022 %7 25.3.2022 %9 Letter to the Editor %J JMIR Cardio %G English %X   %M 35333178 %R 10.2196/36801 %U https://cardio.jmir.org/2022/1/e36801 %U https://doi.org/10.2196/36801 %U http://www.ncbi.nlm.nih.gov/pubmed/35333178 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 6 %N 1 %P e34647 %T Using Caution When Interpreting Gender-Based Relative Risk. Comment on “The Effect of Cardiovascular Comorbidities on Women Compared to Men: Longitudinal Retrospective Analysis” %A Janszky,Imre %+ Department of Public Health and Nursing, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, Håkon Jarls Gate 11, Trondheim, N-7491, Norway, 47 73597575, imre.janszky@ntnu.no %K gender gap %K sex differences %K cardiovascular diseases %K acute myocardial infarction %K chronic ischemic heart disease %K gender %K diabetes %K smoking %K risk factors %K comorbidities %K relative risk %K interaction %D 2022 %7 25.3.2022 %9 Letter to the Editor %J JMIR Cardio %G English %X   %M 35333181 %R 10.2196/34647 %U https://cardio.jmir.org/2022/1/e34647 %U https://doi.org/10.2196/34647 %U http://www.ncbi.nlm.nih.gov/pubmed/35333181 %0 Journal Article %@ 2292-9495 %I JMIR Publications %V 9 %N 1 %P e32568 %T Web-Based Tool (FH Family Share) to Increase Uptake of Cascade Testing for Familial Hypercholesterolemia: Development and Evaluation %A Bangash,Hana %A Makkawy,Ahmed %A Gundelach,Justin H %A Miller,Alexandra A %A Jacobson,Kimberly A %A Kullo,Iftikhar J %+ Mayo Clinic, 200 First Street SW, Rochester, MN, 55905, United States, 1 5072845467, kullo.iftikhar@mayo.edu %K familial hypercholesterolemia %K cascade testing %K communication %K genetic counselors %K digital tools %K website %K usability %K user experience %K public health %D 2022 %7 15.2.2022 %9 Original Paper %J JMIR Hum Factors %G English %X Background: Familial hypercholesterolemia, a prevalent genetic disorder, remains significantly underdiagnosed in the United States. Cascade testing, wherein individuals diagnosed with familial hypercholesterolemia— probands—contact their family members to inform them of their risk for familial hypercholesterolemia, has low uptake in the United States. Digital tools are needed to facilitate communication between familial hypercholesterolemia probands and their family members and to promote sharing of familial hypercholesterolemia–related risk information. Objective: We aimed to create and evaluate a web-based tool designed to enhance familial communication and promote cascade testing for familial hypercholesterolemia. Methods: A hybrid type 1 implementation science framework and a user-centered design process were used to develop an interactive web-based tool—FH Family Share—that enables familial hypercholesterolemia probands to communicate information about their familial hypercholesterolemia diagnosis with at-risk relatives. Probands can also use the tool to draw a family pedigree and learn more about familial hypercholesterolemia through education modules and curated knowledge resources. Usability guidelines and standards were taken into account during the design and development of the tool. The initial prototype underwent a cognitive walkthrough, which was followed by usability testing with key stakeholders including genetic counselors and patients with familial hypercholesterolemia. Participants navigated the prototype using the think-aloud technique, and their feedback was used to refine features of the tool. Results: Key themes that emerged from the cognitive walkthrough were design, format, navigation, terminology, instructions, and learnability. Expert feedback from the cognitive walkthrough resulted in a rebuild of the web-based tool to align it with institutional standards. Usability testing with genetic counselors and patients with familial hypercholesterolemia provided insights on user experience, satisfaction and interface design and highlighted specific modifications that were made to refine the features of FH Family Share. Genetic counselors and patients with familial hypercholesterolemia suggested inclusion of the following features in the web-based tool: (1) a letter-to-family-member email template, (2) education modules, and (3) knowledge resources. Surveys revealed that 6 of 9 (67%) genetic counselors found information within FH Family Share very easy to find, and 5 of 9 (56%) genetic counselors found information very easy to understand; 5 of 9 (56%) patients found information very easy to find within the website, and 7 of 9 (78%) patients found information very easy to understand. All genetic counselors and patients indicated that FH Family Share was a resource worth returning to. Conclusions: FH Family Share facilitates communication between probands and their relatives. Once informed, at-risk family members have the option to seek testing and treatment for familial hypercholesterolemia. %M 35166678 %R 10.2196/32568 %U https://humanfactors.jmir.org/2022/1/e32568 %U https://doi.org/10.2196/32568 %U http://www.ncbi.nlm.nih.gov/pubmed/35166678 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 11 %N 2 %P e31885 %T Investigating Genetic and Other Determinants of First-Onset Myocardial Infarction in Malaysia: Protocol for the Malaysian Acute Vascular Events Risk Study %A Chowdhury,Rajiv %A Noh,Mohd Fairulnizal Md %A Ismail,Sophia Rasheeqa %A van Daalen,Kim Robin %A Kamaruddin,Puteri Sofia Nadira Megat %A Zulkiply,Siti Hafizah %A Azizul,Nur Hayati %A Khalid,Norhayati Mustafa %A Ali,Azizan %A Idris,Izyan Mohd %A Mei,Yong Shih %A Abdullah,Shazana Rifham %A Faridus,Norfashihah %A Yusof,Nur Azirah Md %A Yusoff,Nur Najwa Farahin M %A Jamal,Rahman %A Rahim,Aizai Azan Abdul %A Ghapar,Abdul Kahar Abdul %A Radhakrishnan,Ammu Kutty %A Fong,Alan Yean Yip %A Ismail,Omar %A Krishinan,Saravanan %A Lee,Chuey Yan %A Bang,Liew Houng %A Mageswaren,Eashwary %A Mahendran,Kauthaman %A Amin,Nor Hanim Mohd %A Muthusamy,Gunavathy %A Jin,Aaron Ong Hean %A Ramli,Ahmad Wazi %A Ross,Noel Thomas %A Ruhani,Anwar Irawan %A Yahya,Mansor %A Yusoff,Yusniza %A Abidin,Siti Khairani Zainal %A Amado,Laryssa %A Bolton,Thomas %A Weston,Sophie %A Crawte,Jason %A Ovenden,Niko %A Michielsen,Ank %A Monower,Md Mostafa %A Mahiyuddin,Wan Rozita Wan %A Wood,Angela %A Di Angelantonio,Emanuele %A Sulaiman,Nur Suffia %A Danesh,John %A Butterworth,Adam S %+ British Heart Foundation Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge, Cambridge, United Kingdom, 44 01223 748600, asb38@medschl.cam.ac.uk %K myocardial infarction %K cardiovascular disease %K case-control study %K Malaysia %D 2022 %7 10.2.2022 %9 Protocol %J JMIR Res Protoc %G English %X Background: Although the burden of premature myocardial infarction (MI) is high in Malaysia, direct evidence on the determinants of MI in this multi-ethnic population remains sparse. Objective: The Malaysian Acute Vascular Events Risk (MAVERIK) study is a retrospective case-control study established to investigate the genomic, lipid-related, and other determinants of acute MI in Malaysia. In this paper, we report the study protocol and early results. Methods: By June 2019, we had enrolled approximately 2500 patients with their first MI and 2500 controls without cardiovascular disease, who were frequency-matched by age, sex, and ethnicity, from 17 hospitals in Malaysia. For each participant, serum and whole blood have been collected and stored. Clinical, demographic, and behavioral information has been obtained using a 200-item questionnaire. Results: Tobacco consumption, a history of diabetes, hypertension, markers of visceral adiposity, indicators of lower socioeconomic status, and a family history of coronary disease were more prevalent in cases than in controls. Adjusted (age and sex) logistic regression models for traditional risk factors indicated that current smoking (odds ratio [OR] 4.11, 95% CI 3.56-4.75; P<.001), previous smoking (OR 1.34, 95% CI 1.12-1.60; P=.001), a history of high blood pressure (OR 2.13, 95% CI 1.86-2.44; P<.001), a history of diabetes mellitus (OR 2.72, 95% CI 2.34-3.17; P<.001), a family history of coronary heart disease (OR 1.28, 95% CI 1.07-1.55; P=.009), and obesity (BMI >30 kg/m2; OR 1.19, 95% CI 1.05-1.34; P=.009) were associated with MI in age- and sex-adjusted models. Conclusions: The MAVERIK study can serve as a useful platform to investigate genetic and other risk factors for MI in an understudied Southeast Asian population. It should help to hasten the discovery of disease-causing pathways and inform regionally appropriate strategies that optimize public health action. International Registered Report Identifier (IRRID): RR1-10.2196/31885 %M 35142634 %R 10.2196/31885 %U https://www.researchprotocols.org/2022/2/e31885 %U https://doi.org/10.2196/31885 %U http://www.ncbi.nlm.nih.gov/pubmed/35142634 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 10 %N 1 %P e29434 %T Machine Learning for Cardiovascular Outcomes From Wearable Data: Systematic Review From a Technology Readiness Level Point of View %A Naseri Jahfari,Arman %A Tax,David %A Reinders,Marcel %A van der Bilt,Ivo %+ Pattern Recognition and Bioinformatics, Delft University of Technology, van Mourik Broekmanweg 6, Delft, 2628 XE, Netherlands, 31 152786052, a.naserijahfari@tudelft.nl %K mHealth %K wearable %K machine learning %K cardiovascular disease %K digital health %K review %K mobile phone %D 2022 %7 19.1.2022 %9 Review %J JMIR Med Inform %G English %X Background: Wearable technology has the potential to improve cardiovascular health monitoring by using machine learning. Such technology enables remote health monitoring and allows for the diagnosis and prevention of cardiovascular diseases. In addition to the detection of cardiovascular disease, it can exclude this diagnosis in symptomatic patients, thereby preventing unnecessary hospital visits. In addition, early warning systems can aid cardiologists in timely treatment and prevention. Objective: This study aims to systematically assess the literature on detecting and predicting outcomes of patients with cardiovascular diseases by using machine learning with data obtained from wearables to gain insights into the current state, challenges, and limitations of this technology. Methods: We searched PubMed, Scopus, and IEEE Xplore on September 26, 2020, with no restrictions on the publication date and by using keywords such as “wearables,” “machine learning,” and “cardiovascular disease.” Methodologies were categorized and analyzed according to machine learning–based technology readiness levels (TRLs), which score studies on their potential to be deployed in an operational setting from 1 to 9 (most ready). Results: After the removal of duplicates, application of exclusion criteria, and full-text screening, 55 eligible studies were included in the analysis, covering a variety of cardiovascular diseases. We assessed the quality of the included studies and found that none of the studies were integrated into a health care system (TRL<6), prospective phase 2 and phase 3 trials were absent (TRL<7 and 8), and group cross-validation was rarely used. These issues limited these studies’ ability to demonstrate the effectiveness of their methodologies. Furthermore, there seemed to be no agreement on the sample size needed to train these studies’ models, the size of the observation window used to make predictions, how long participants should be observed, and the type of machine learning model that is suitable for predicting cardiovascular outcomes. Conclusions: Although current studies show the potential of wearables to monitor cardiovascular events, their deployment as a diagnostic or prognostic cardiovascular clinical tool is hampered by the lack of a realistic data set and proper systematic and prospective evaluation. %M 35044316 %R 10.2196/29434 %U https://medinform.jmir.org/2022/1/e29434 %U https://doi.org/10.2196/29434 %U http://www.ncbi.nlm.nih.gov/pubmed/35044316 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 12 %P e30798 %T Artificial Intelligence in Predicting Cardiac Arrest: Scoping Review %A Alamgir,Asma %A Mousa,Osama %A Shah,Zubair %+ College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation, Education City, PO BOX 34110, Street 2731, Al Luqta St, Ar-Rayyan, Doha, Qatar, 974 5074 4851, zshah@hbku.edu.qa %K artificial intelligence %K machine learning %K deep learning %K cardiac arrest %K predict %D 2021 %7 17.12.2021 %9 Review %J JMIR Med Inform %G English %X Background: Cardiac arrest is a life-threatening cessation of activity in the heart. Early prediction of cardiac arrest is important, as it allows for the necessary measures to be taken to prevent or intervene during the onset. Artificial intelligence (AI) technologies and big data have been increasingly used to enhance the ability to predict and prepare for the patients at risk. Objective: This study aims to explore the use of AI technology in predicting cardiac arrest as reported in the literature. Methods: A scoping review was conducted in line with the guidelines of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) extension for scoping reviews. Scopus, ScienceDirect, Embase, the Institute of Electrical and Electronics Engineers, and Google Scholar were searched to identify relevant studies. Backward reference list checks of the included studies were also conducted. Study selection and data extraction were independently conducted by 2 reviewers. Data extracted from the included studies were synthesized narratively. Results: Out of 697 citations retrieved, 41 studies were included in the review, and 6 were added after backward citation checking. The included studies reported the use of AI in the prediction of cardiac arrest. Of the 47 studies, we were able to classify the approaches taken by the studies into 3 different categories: 26 (55%) studies predicted cardiac arrest by analyzing specific parameters or variables of the patients, whereas 16 (34%) studies developed an AI-based warning system. The remaining 11% (5/47) of studies focused on distinguishing patients at high risk of cardiac arrest from patients who were not at risk. Two studies focused on the pediatric population, and the rest focused on adults (45/47, 96%). Most of the studies used data sets with a size of <10,000 samples (32/47, 68%). Machine learning models were the most prominent branch of AI used in the prediction of cardiac arrest in the studies (38/47, 81%), and the most used algorithm was the neural network (23/47, 49%). K-fold cross-validation was the most used algorithm evaluation tool reported in the studies (24/47, 51%). Conclusions: AI is extensively used to predict cardiac arrest in different patient settings. Technology is expected to play an integral role in improving cardiac medicine. There is a need for more reviews to learn the obstacles to the implementation of AI technologies in clinical settings. Moreover, research focusing on how to best provide clinicians with support to understand, adapt, and implement this technology in their practice is also necessary. %M 34927595 %R 10.2196/30798 %U https://medinform.jmir.org/2021/12/e30798 %U https://doi.org/10.2196/30798 %U http://www.ncbi.nlm.nih.gov/pubmed/34927595 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 5 %N 2 %P e31056 %T Interventions Using Heart Age for Cardiovascular Disease Risk Communication: Systematic Review of Psychological, Behavioral, and Clinical Effects %A Bonner,Carissa %A Batcup,Carys %A Cornell,Samuel %A Fajardo,Michael Anthony %A Hawkes,Anna L %A Trevena,Lyndal %A Doust,Jenny %+ School of Public Health, Faculty of Medicine and Health, University of Sydney, Edward Ford Building A27, Sydney, 2006, Australia, 61 29351 7125, carissa.bonner@sydney.edu.au %K heart age %K cardiovascular disease %K risk assessment %K risk communication %K prevention %D 2021 %7 5.11.2021 %9 Review %J JMIR Cardio %G English %X Background: Cardiovascular disease (CVD) risk communication is a challenge for clinical practice, where physicians find it difficult to explain the absolute risk of a CVD event to patients with varying health literacy. Converting the probability to heart age is increasingly used to promote lifestyle change, but a rapid review of biological age interventions found no clear evidence that they motivate behavior change. Objective: In this review, we aim to identify the content and effects of heart age interventions. Methods: We conducted a systematic review of studies presenting heart age interventions to adults for CVD risk communication in April 2020 (later updated in March 2021). The Johanna Briggs risk of bias assessment tool was applied to randomized studies. Behavior change techniques described in the intervention methods were coded. Results: From a total of 7926 results, 16 eligible studies were identified; these included 5 randomized web-based experiments, 5 randomized clinical trials, 2 mixed methods studies with quantitative outcomes, and 4 studies with qualitative analysis. Direct comparisons between heart age and absolute risk in the 5 web-based experiments, comprising 5514 consumers, found that heart age increased positive or negative emotional responses (4/5 studies), increased risk perception (4/5 studies; but not necessarily more accurate) and recall (4/4 studies), reduced credibility (2/3 studies), and generally had no effect on lifestyle intentions (4/5 studies). One study compared heart age and absolute risk to fitness age and found reduced lifestyle intentions for fitness age. Heart age combined with additional strategies (eg, in-person or phone counseling) in applied settings for 9582 patients improved risk control (eg, reduced cholesterol levels and absolute risk) compared with usual care in most trials (4/5 studies) up to 1 year. However, clinical outcomes were no different when directly compared with absolute risk (1/1 study). Mixed methods studies identified consultation time and content as important outcomes in actual consultations using heart age tools. There were differences between people receiving an older heart age result and those receiving a younger or equal to current heart age result. The heart age interventions included a wide range of behavior change techniques, and conclusions were sometimes biased in favor of heart age with insufficient supporting evidence. The risk of bias assessment indicated issues with all randomized clinical trials. Conclusions: The findings of this review provide little evidence that heart age motivates lifestyle behavior change more than absolute risk, but either format can improve clinical outcomes when combined with other behavior change strategies. The label for the heart age concept can affect outcomes and should be pretested with the intended audience. Future research should consider consultation time and differentiate between results of older and younger heart age. International Registered Report Identifier (IRRID): NPRR2-10.1101/2020.05.03.20089938 %M 34738908 %R 10.2196/31056 %U https://cardio.jmir.org/2021/2/e31056 %U https://doi.org/10.2196/31056 %U http://www.ncbi.nlm.nih.gov/pubmed/34738908 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 5 %N 2 %P e28015 %T The Effect of Cardiovascular Comorbidities on Women Compared to Men: Longitudinal Retrospective Analysis %A Dervic,Elma %A Deischinger,Carola %A Haug,Nils %A Leutner,Michael %A Kautzky-Willer,Alexandra %A Klimek,Peter %+ Section for Science of Complex Systems, Center for Medical Statistics, Informatics and Intelligent Systems, Medical University of Vienna, Spitalgasse 23, Vienna, 1090, Austria, 43 1 40160 36252, Peter.Klimek@meduniwien.ac.at %K gender gap %K sex differences %K cardiovascular diseases %K acute myocardial infarction %K chronic ischemic heart disease %K gender %K diabetes %K smoking %K risk factors %K comorbidities %D 2021 %7 4.10.2021 %9 Original Paper %J JMIR Cardio %G English %X Background: Although men are more prone to developing cardiovascular disease (CVD) than women, risk factors for CVD, such as nicotine abuse and diabetes mellitus, have been shown to be more detrimental in women than in men. Objective: We developed a method to systematically investigate population-wide electronic health records for all possible associations between risk factors for CVD and other diagnoses. The developed structured approach allows an exploratory and comprehensive screening of all possible comorbidities of CVD, which are more connected to CVD in either men or women. Methods: Based on a population-wide medical claims dataset comprising 44 million records of inpatient stays in Austria from 2003 to 2014, we determined comorbidities of acute myocardial infarction (AMI; International Classification of Diseases, Tenth Revision [ICD-10] code I21) and chronic ischemic heart disease (CHD; ICD-10 code I25) with a significantly different prevalence in men and women. We introduced a measure of sex difference as a measure of differences in logarithmic odds ratios (ORs) between male and female patients in units of pooled standard errors. Results: Except for lipid metabolism disorders (OR for females [ORf]=6.68, 95% confidence interval [CI]=6.57-6.79, OR for males [ORm]=8.31, 95% CI=8.21-8.41), all identified comorbidities were more likely to be associated with AMI and CHD in females than in males: nicotine dependence (ORf=6.16, 95% CI=5.96-6.36, ORm=4.43, 95% CI=4.35-4.5), diabetes mellitus (ORf=3.52, 95% CI=3.45-3.59, ORm=3.13, 95% CI=3.07-3.19), obesity (ORf=3.64, 95% CI=3.56-3.72, ORm=3.33, 95% CI=3.27-3.39), renal disorders (ORf=4.27, 95% CI=4.11-4.44, ORm=3.74, 95% CI=3.67-3.81), asthma (ORf=2.09, 95% CI=1.96-2.23, ORm=1.59, 95% CI=1.5-1.68), and COPD (ORf=2.09, 95% CI 1.96-2.23, ORm=1.59, 95% CI 1.5-1.68). Similar results could be observed for AMI. Conclusions: Although AMI and CHD are more prevalent in men, women appear to be more affected by certain comorbidities of AMI and CHD in their risk for developing CVD. %M 34605767 %R 10.2196/28015 %U https://cardio.jmir.org/2021/2/e28015 %U https://doi.org/10.2196/28015 %U http://www.ncbi.nlm.nih.gov/pubmed/34605767 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 10 %N 9 %P e28669 %T Multiscale Biology of Cardiovascular Risk in Psoriasis: Protocol for a Case-Control Study %A Kaiser,Hannah %A Kvist-Hansen,Amanda %A Becker,Christine %A Wang,Xing %A McCauley,Benjamin D %A Krakauer,Martin %A Gørtz,Peter Michael %A Henningsen,Kristoffer Mads Aaris %A Zachariae,Claus %A Skov,Lone %A Hansen,Peter Riis %+ Department of Dermatology and Allergy, Copenhagen University Hospital Herlev and Gentofte, Gentofte Hospitalsvej 15, Hellerup, 2900, Denmark, 45 38673144, amanda.kvist-hansen@regionh.dk %K cardiovascular disease %K psoriasis %K study protocol %K cardiovascular imaging %K proteomics %K lipidomics %K microbiome %K mass cytometry %K bioinformatics %K system biology %D 2021 %7 28.9.2021 %9 Protocol %J JMIR Res Protoc %G English %X Background: Patients with psoriasis have increased risk of cardiovascular disease (CVD) independent of traditional risk factors. The molecular mechanisms underlying the psoriasis-CVD connection are not fully understood. Advances in high-throughput molecular profiling technologies and computational analysis techniques offer new opportunities to improve the understanding of disease connections. Objective: We aim to characterize the complexity of cardiovascular risk in patients with psoriasis by integrating deep phenotypic data with systems biology techniques to perform comprehensive multiomic analyses and construct network models of the two interacting diseases. Methods: The study aims to include 120 adult patients with psoriasis (60 with prior atherosclerotic CVD and 60 without CVD). Half of the patients are already receiving systemic antipsoriatic treatment. All patients complete a questionnaire, and a medical interview is conducted to collect medical history and information on, for example, socioeconomics, mental health, diet, and physical exercise. Participants are examined clinically with assessment of the Psoriasis Area and Severity Index and undergo imaging by transthoracic echocardiography, 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG-PET/CT), and carotid artery ultrasonography. Skin swabs are collected for analysis of microbiome metagenomics; skin biopsies and blood samples are collected for transcriptomic profiling by RNA sequencing; skin biopsies are collected for immunohistochemistry; plasma samples are collected for analyses of proteomics, lipidomics, and metabolomics; blood samples are collected for high-dimensional mass cytometry; and feces samples are collected for gut microbiome metagenomics. Bioinformatics and systems biology techniques are utilized to analyze the multiomic data and to integrate data into a network model of CVD in patients with psoriasis. Results: Recruitment was completed in September 2020. Preliminary results of 18F-FDG-PET/CT data have recently been published, where vascular inflammation was reduced in the ascending aorta (P=.046) and aortic arch (P=.04) in patients treated with statins and was positively associated with inflammation in the visceral adipose tissue (P<.001), subcutaneous adipose tissue (P=.007), pericardial adipose tissue (P<.001), spleen (P=.001), and bone marrow (P<.001). Conclusions: This systems biology approach with integration of multiomics and clinical data in patients with psoriasis with or without CVD is likely to provide novel insights into the biological mechanisms underlying these diseases and their interplay that can impact future treatment. International Registered Report Identifier (IRRID): DERR1-10.2196/28669 %M 34581684 %R 10.2196/28669 %U https://www.researchprotocols.org/2021/9/e28669 %U https://doi.org/10.2196/28669 %U http://www.ncbi.nlm.nih.gov/pubmed/34581684 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 23 %N 9 %P e27798 %T Predicting the Mortality and Readmission of In-Hospital Cardiac Arrest Patients With Electronic Health Records: A Machine Learning Approach %A Chi,Chien-Yu %A Ao,Shuang %A Winkler,Adrian %A Fu,Kuan-Chun %A Xu,Jie %A Ho,Yi-Lwun %A Huang,Chien-Hua %A Soltani,Rohollah %+ Department of Emergency Medicine, National Taiwan University Hospital, #7 Chung-Shan South Road, Taipei, 100, Taiwan, 886 0972651304, chhuang5940@ntu.edu.tw %K in-hospital cardiac arrest %K 30-day mortality %K 30-day readmission %K machine learning %K imbalanced dataset %D 2021 %7 13.9.2021 %9 Original Paper %J J Med Internet Res %G English %X Background: In-hospital cardiac arrest (IHCA) is associated with high mortality and health care costs in the recovery phase. Predicting adverse outcome events, including readmission, improves the chance for appropriate interventions and reduces health care costs. However, studies related to the early prediction of adverse events of IHCA survivors are rare. Therefore, we used a deep learning model for prediction in this study. Objective: This study aimed to demonstrate that with the proper data set and learning strategies, we can predict the 30-day mortality and readmission of IHCA survivors based on their historical claims. Methods: National Health Insurance Research Database claims data, including 168,693 patients who had experienced IHCA at least once and 1,569,478 clinical records, were obtained to generate a data set for outcome prediction. We predicted the 30-day mortality/readmission after each current record (ALL-mortality/ALL-readmission) and 30-day mortality/readmission after IHCA (cardiac arrest [CA]-mortality/CA-readmission). We developed a hierarchical vectorizer (HVec) deep learning model to extract patients’ information and predict mortality and readmission. To embed the textual medical concepts of the clinical records into our deep learning model, we used Text2Node to compute the distributed representations of all medical concept codes as a 128-dimensional vector. Along with the patient’s demographic information, our novel HVec model generated embedding vectors to hierarchically describe the health status at the record-level and patient-level. Multitask learning involving two main tasks and auxiliary tasks was proposed. As CA-mortality and CA-readmission were rare, person upsampling of patients with CA and weighting of CA records were used to improve prediction performance. Results: With the multitask learning setting in the model learning process, we achieved an area under the receiver operating characteristic of 0.752 for CA-mortality, 0.711 for ALL-mortality, 0.852 for CA-readmission, and 0.889 for ALL-readmission. The area under the receiver operating characteristic was improved to 0.808 for CA-mortality and 0.862 for CA-readmission after solving the extremely imbalanced issue for CA-mortality/CA-readmission by upsampling and weighting. Conclusions: This study demonstrated the potential of predicting future outcomes for IHCA survivors by machine learning. The results showed that our proposed approach could effectively alleviate data imbalance problems and train a better model for outcome prediction. %M 34515639 %R 10.2196/27798 %U https://www.jmir.org/2021/9/e27798 %U https://doi.org/10.2196/27798 %U http://www.ncbi.nlm.nih.gov/pubmed/34515639 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 10 %N 7 %P e29631 %T Predictive Monitoring–Impact in Acute Care Cardiology Trial (PM-IMPACCT): Protocol for a Randomized Controlled Trial %A Keim-Malpass,Jessica %A Ratcliffe,Sarah J %A Moorman,Liza P %A Clark,Matthew T %A Krahn,Katy N %A Monfredi,Oliver J %A Hamil,Susan %A Yousefvand,Gholamreza %A Moorman,J Randall %A Bourque,Jamieson M %+ University of Virginia, PO Box 800782, Charlottesville, VA, 22908, United States, 1 434 243 3961, jesskeim@gmail.com %K predictive analytics monitoring %K AI %K randomized controlled trial %K risk estimation %K clinical deterioration %K visual analytics %K artificial intelligence %K monitoring %K risk %K prediction %K impact %K cardiology %K acute care %D 2021 %7 2.7.2021 %9 Protocol %J JMIR Res Protoc %G English %X Background: Patients in acute care wards who deteriorate and are emergently transferred to intensive care units (ICUs) have poor outcomes. Early identification of patients who are decompensating might allow for earlier clinical intervention and reduced morbidity and mortality. Advances in bedside continuous predictive analytics monitoring (ie, artificial intelligence [AI]–based risk prediction) have made complex data easily available to health care providers and have provided early warning of potentially catastrophic clinical events. We present a dynamic, visual, predictive analytics monitoring tool that integrates real-time bedside telemetric physiologic data into robust clinical models to estimate and communicate risk of imminent events. This tool, Continuous Monitoring of Event Trajectories (CoMET), has been shown in retrospective observational studies to predict clinical decompensation on the acute care ward. There is a need to more definitively study this advanced predictive analytics or AI monitoring system in a prospective, randomized controlled, clinical trial. Objective: The goal of this trial is to determine the impact of an AI-based visual risk analytic, CoMET, on improving patient outcomes related to clinical deterioration, response time to proactive clinical action, and costs to the health care system. Methods: We propose a cluster randomized controlled trial to test the impact of using the CoMET display in an acute care cardiology and cardiothoracic surgery hospital floor. The number of admissions to a room undergoing cluster randomization was estimated to be 10,424 over the 20-month study period. Cluster randomization based on bed number will occur every 2 months. The intervention cluster will have the CoMET score displayed (along with standard of care), while the usual care group will receive standard of care only. Results: The primary outcome will be hours free from events of clinical deterioration. Hours of acute clinical events are defined as time when one or more of the following occur: emergent ICU transfer, emergent surgery prior to ICU transfer, cardiac arrest prior to ICU transfer, emergent intubation, or death. The clinical trial began randomization in January 2021. Conclusions: Very few AI-based health analytics have been translated from algorithm to real-world use. This study will use robust, prospective, randomized controlled, clinical trial methodology to assess the effectiveness of an advanced AI predictive analytics monitoring system in incorporating real-time telemetric data for identifying clinical deterioration on acute care wards. This analysis will strengthen the ability of health care organizations to evolve as learning health systems, in which bioinformatics data are applied to improve patient outcomes by incorporating AI into knowledge tools that are successfully integrated into clinical practice by health care providers. Trial Registration: ClinicalTrials.gov NCT04359641; https://clinicaltrials.gov/ct2/show/NCT04359641 International Registered Report Identifier (IRRID): DERR1-10.2196/29631 %M 34043525 %R 10.2196/29631 %U https://www.researchprotocols.org/2021/7/e29631 %U https://doi.org/10.2196/29631 %U http://www.ncbi.nlm.nih.gov/pubmed/34043525 %0 Journal Article %@ 2291-9694 %I JMIR Publications %V 9 %N 4 %P e25000 %T Mortality Prediction of Patients With Cardiovascular Disease Using Medical Claims Data Under Artificial Intelligence Architectures: Validation Study %A Tran,Linh %A Chi,Lianhua %A Bonti,Alessio %A Abdelrazek,Mohamed %A Chen,Yi-Ping Phoebe %+ Department of Computer Science and Information Technology, La Trobe University, Beth Gleeson Bldg, 2rd Fl, #242, La Trobe University, Bundoora, 3086, Australia, 61 94792454, l.chi@latrobe.edu.au %K mortality %K cardiovascular %K medical claims data %K imbalanced data %K machine learning %K deep learning %D 2021 %7 1.4.2021 %9 Original Paper %J JMIR Med Inform %G English %X Background: Cardiovascular disease (CVD) is the greatest health problem in Australia, which kills more people than any other disease and incurs enormous costs for the health care system. In this study, we present a benchmark comparison of various artificial intelligence (AI) architectures for predicting the mortality rate of patients with CVD using structured medical claims data. Compared with other research in the clinical literature, our models are more efficient because we use a smaller number of features, and this study could help health professionals accurately choose AI models to predict mortality among patients with CVD using only claims data before a clinic visit. Objective: This study aims to support health clinicians in accurately predicting mortality among patients with CVD using only claims data before a clinic visit. Methods: The data set was obtained from the Medicare Benefits Scheme and Pharmaceutical Benefits Scheme service information in the period between 2004 and 2014, released by the Department of Health Australia in 2016. It included 346,201 records, corresponding to 346,201 patients. A total of five AI algorithms, including four classical machine learning algorithms (logistic regression [LR], random forest [RF], extra trees [ET], and gradient boosting trees [GBT]) and a deep learning algorithm, which is a densely connected neural network (DNN), were developed and compared in this study. In addition, because of the minority of deceased patients in the data set, a separate experiment using the Synthetic Minority Oversampling Technique (SMOTE) was conducted to enrich the data. Results: Regarding model performance, in terms of discrimination, GBT and RF were the models with the highest area under the receiver operating characteristic curve (97.8% and 97.7%, respectively), followed by ET (96.8%) and LR (96.4%), whereas DNN was the least discriminative (95.3%). In terms of reliability, LR predictions were the least calibrated compared with the other four algorithms. In this study, despite increasing the training time, SMOTE was proven to further improve the model performance of LR, whereas other algorithms, especially GBT and DNN, worked well with class imbalanced data. Conclusions: Compared with other research in the clinical literature involving AI models using claims data to predict patient health outcomes, our models are more efficient because we use a smaller number of features but still achieve high performance. This study could help health professionals accurately choose AI models to predict mortality among patients with CVD using only claims data before a clinic visit. %M 33792549 %R 10.2196/25000 %U https://medinform.jmir.org/2021/4/e25000 %U https://doi.org/10.2196/25000 %U http://www.ncbi.nlm.nih.gov/pubmed/33792549 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 5 %N 1 %P e24473 %T Predicting Cardiovascular Risk Using Social Media Data: Performance Evaluation of Machine-Learning Models %A Andy,Anietie U %A Guntuku,Sharath C %A Adusumalli,Srinath %A Asch,David A %A Groeneveld,Peter W %A Ungar,Lyle H %A Merchant,Raina M %+ Penn Medicine Center for Digital Health, University of Pennsylvania, Philadelphia, PA, United States, 1 202 486 4095, Anietie.Andy@pennmedicine.upenn.edu %K ASCVD %K machine learning %K natural language processing %K atherosclerotic %K cardiovascular disease %K social media language %K social media %D 2021 %7 19.2.2021 %9 Original Paper %J JMIR Cardio %G English %X Background: Current atherosclerotic cardiovascular disease (ASCVD) predictive models have limitations; thus, efforts are underway to improve the discriminatory power of ASCVD models. Objective: We sought to evaluate the discriminatory power of social media posts to predict the 10-year risk for ASCVD as compared to that of pooled cohort risk equations (PCEs). Methods: We consented patients receiving care in an urban academic emergency department to share access to their Facebook posts and electronic medical records (EMRs). We retrieved Facebook status updates up to 5 years prior to study enrollment for all consenting patients. We identified patients (N=181) without a prior history of coronary heart disease, an ASCVD score in their EMR, and more than 200 words in their Facebook posts. Using Facebook posts from these patients, we applied a machine-learning model to predict 10-year ASCVD risk scores. Using a machine-learning model and a psycholinguistic dictionary, Linguistic Inquiry and Word Count, we evaluated if language from posts alone could predict differences in risk scores and the association of certain words with risk categories, respectively. Results: The machine-learning model predicted the 10-year ASCVD risk scores for the categories <5%, 5%-7.4%, 7.5%-9.9%, and ≥10% with area under the curve (AUC) values of 0.78, 0.57, 0.72, and 0.61, respectively. The machine-learning model distinguished between low risk (<10%) and high risk (>10%) with an AUC of 0.69. Additionally, the machine-learning model predicted the ASCVD risk score with Pearson r=0.26. Using Linguistic Inquiry and Word Count, patients with higher ASCVD scores were more likely to use words associated with sadness (r=0.32). Conclusions: Language used on social media can provide insights about an individual’s ASCVD risk and inform approaches to risk modification. %M 33605888 %R 10.2196/24473 %U http://cardio.jmir.org/2021/1/e24473/ %U https://doi.org/10.2196/24473 %U http://www.ncbi.nlm.nih.gov/pubmed/33605888 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 10 %N 2 %P e24186 %T Cardiomyocyte Injury Following Acute Ischemic Stroke: Protocol for a Prospective Observational Cohort Study %A Stengl,Helena %A Ganeshan,Ramanan %A Hellwig,Simon %A Blaszczyk,Edyta %A Fiebach,Jochen B %A Nolte,Christian H %A Bauer,Axel %A Schulz-Menger,Jeanette %A Endres,Matthias %A Scheitz,Jan F %+ Department of Neurology, Charité - Universitätsmedizin Berlin, , Berlin, , Germany, 49 030 450560693, helena.stengl@charite.de %K ischemic stroke %K troponin T %K myocardial ischemia %K myocardial injury %K stroke-heart syndrome %K cardiac imaging techniques %K magnetic resonance imaging %K Takotsubo syndrome %K autonomic nervous system %D 2021 %7 5.2.2021 %9 Protocol %J JMIR Res Protoc %G English %X Background: Elevated cardiac troponin, which indicates cardiomyocyte injury, is common after acute ischemic stroke and is associated with poor functional outcome. Myocardial injury is part of a broad spectrum of cardiac complications that may occur after acute ischemic stroke. Previous studies have shown that in most patients, the underlying mechanism of stroke-associated myocardial injury may not be a concomitant acute coronary syndrome. Evidence from animal research and clinical and neuroimaging studies suggest that functional and structural alterations in the central autonomic network leading to stress-mediated neurocardiogenic injury may be a key underlying mechanism (ie, stroke-heart syndrome). However, the exact pathophysiological cascade remains unclear, and the diagnostic and therapeutic implications are unknown. Objective: The aim of this CORONA-IS (Cardiomyocyte injury following Acute Ischemic Stroke) study is to quantify autonomic dysfunction and to decipher downstream cardiac mechanisms leading to myocardial injury after acute ischemic stroke. Methods: In this prospective, observational, single-center cohort study, 300 patients with acute ischemic stroke, confirmed via cerebral magnetic resonance imaging (MRI) and presenting within 48 hours of symptom onset, will be recruited during in-hospital stay. On the basis of high-sensitivity cardiac troponin levels and corresponding to the fourth universal definition of myocardial infarction, 3 groups are defined (ie, no myocardial injury [no cardiac troponin elevation], chronic myocardial injury [stable elevation], and acute myocardial injury [dynamic rise/fall pattern]). Each group will include approximately 100 patients. Study patients will receive routine diagnostic care. In addition, they will receive 3 Tesla cardiovascular MRI and transthoracic echocardiography within 5 days of symptom onset to provide myocardial tissue characterization and assess cardiac function, 20-min high-resolution electrocardiogram for analysis of cardiac autonomic function, and extensive biobanking. A follow-up for cardiovascular events will be conducted 3 and 12 months after inclusion. Results: After a 4-month pilot phase, recruitment began in April 2019. We estimate a recruitment period of approximately 3 years to include 300 patients with a complete cardiovascular MRI protocol. Conclusions: Stroke-associated myocardial injury is a common and relevant complication. Our study has the potential to provide a better mechanistic understanding of heart and brain interactions in the setting of acute stroke. Thus, it is essential to develop algorithms for recognizing patients at risk and to refine diagnostic and therapeutic procedures. Trial Registration: Clinicaltrials.gov NCT03892226; https://www.clinicaltrials.gov/ct2/show/NCT03892226. International Registered Report Identifier (IRRID): DERR1-10.2196/24186 %M 33544087 %R 10.2196/24186 %U http://www.researchprotocols.org/2021/2/e24186/ %U https://doi.org/10.2196/24186 %U http://www.ncbi.nlm.nih.gov/pubmed/33544087 %0 Journal Article %@ 1929-0748 %I JMIR Publications %V 10 %N 1 %P e22536 %T Novel Assessments of Technical and Nontechnical Cardiac Surgery Quality: Protocol for a Mixed Methods Study %A Likosky,Donald %A Yule,Steven J %A Mathis,Michael R %A Dias,Roger D %A Corso,Jason J %A Zhang,Min %A Krein,Sarah L %A Caldwell,Matthew D %A Louis,Nathan %A Janda,Allison M %A Shah,Nirav J %A Pagani,Francis D %A Stakich-Alpirez,Korana %A Manojlovich,Milisa M %+ Department of Cardiac Surgery, University of Michigan, 5346 CVC, Ann Arbor, MI, 48109, United States, 1 7342324216, likosky@umich.edu %K cardiac surgery %K quality %K protocol %K study %K coronary artery bypass grafting surgery %K complications %K patient risk %K variation %K intraoperative %K improvement %D 2021 %7 8.1.2021 %9 Protocol %J JMIR Res Protoc %G English %X Background: Of the 150,000 patients annually undergoing coronary artery bypass grafting, 35% develop complications that increase mortality 5 fold and expenditure by 50%. Differences in patient risk and operative approach explain only 2% of hospital variations in some complications. The intraoperative phase remains understudied as a source of variation, despite its complexity and amenability to improvement. Objective: The objectives of this study are to (1) investigate the relationship between peer assessments of intraoperative technical skills and nontechnical practices with risk-adjusted complication rates and (2) evaluate the feasibility of using computer-based metrics to automate the assessment of important intraoperative technical skills and nontechnical practices. Methods: This multicenter study will use video recording, established peer assessment tools, electronic health record data, registry data, and a high-dimensional computer vision approach to (1) investigate the relationship between peer assessments of surgeon technical skills and variability in risk-adjusted patient adverse events; (2) investigate the relationship between peer assessments of intraoperative team-based nontechnical practices and variability in risk-adjusted patient adverse events; and (3) use quantitative and qualitative methods to explore the feasibility of using objective, data-driven, computer-based assessments to automate the measurement of important intraoperative determinants of risk-adjusted patient adverse events. Results: The project has been funded by the National Heart, Lung and Blood Institute in 2019 (R01HL146619). Preliminary Institutional Review Board review has been completed at the University of Michigan by the Institutional Review Boards of the University of Michigan Medical School. Conclusions: We anticipate that this project will substantially increase our ability to assess determinants of variation in complication rates by specifically studying a surgeon’s technical skills and operating room team member nontechnical practices. These findings may provide effective targets for future trials or quality improvement initiatives to enhance the quality and safety of cardiac surgical patient care. International Registered Report Identifier (IRRID): PRR1-10.2196/22536 %M 33416505 %R 10.2196/22536 %U https://www.researchprotocols.org/2021/1/e22536 %U https://doi.org/10.2196/22536 %U http://www.ncbi.nlm.nih.gov/pubmed/33416505 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 4 %N 1 %P e16975 %T Minimal Patient Clinical Variables to Accurately Predict Stress Echocardiography Outcome: Validation Study Using Machine Learning Techniques %A Bennasar,Mohamed %A Banks,Duncan %A Price,Blaine A %A Kardos,Attila %+ School of Life, Health and Chemical Sciences, The Open University, Walton Hall, Milton Keynes, , United Kingdom, 44 190 865 9198, Duncan.Banks@open.ac.uk %K stress echocardiography %K coronary heart disease %K risk factors %K machine learning %K feature selection %K risk prediction %D 2020 %7 29.5.2020 %9 Original Paper %J JMIR Cardio %G English %X Background: Stress echocardiography is a well-established diagnostic tool for suspected coronary artery disease (CAD). Cardiovascular risk factors are used in the assessment of the probability of CAD. The link between the outcome of stress echocardiography and patients’ variables including risk factors, current medication, and anthropometric variables has not been widely investigated. Objective: This study aimed to use machine learning to predict significant CAD defined by positive stress echocardiography results in patients with chest pain based on anthropometrics, cardiovascular risk factors, and medication as variables. This could allow clinical prioritization of patients with likely prediction of CAD, thus saving clinician time and improving outcomes. Methods: A machine learning framework was proposed to automate the prediction of stress echocardiography results. The framework consisted of four stages: feature extraction, preprocessing, feature selection, and classification stage. A mutual information–based feature selection method was used to investigate the amount of information that each feature carried to define the positive outcome of stress echocardiography. Two classification algorithms, support vector machine (SVM) and random forest classifiers, have been deployed. Data from 529 patients were used to train and validate the framework. Patient mean age was 61 (SD 12) years. The data consists of anthropological data and cardiovascular risk factors such as gender, age, weight, family history, diabetes, smoking history, hypertension, hypercholesterolemia, prior diagnosis of CAD, and prescribed medications at the time of the test. There were 82 positive (abnormal) and 447 negative (normal) stress echocardiography results. The framework was evaluated using the whole dataset including cases with prior diagnosis of CAD. Five-fold cross-validation was used to validate the performance of the framework. We also investigated the model in the subset of patients with no prior CAD. Results: The feature selection methods showed that prior diagnosis of CAD, sex, and prescribed medications such as angiotensin-converting enzyme inhibitor/angiotensin receptor blocker were the features that shared the most information about the outcome of stress echocardiography. SVM classifiers showed the best trade-off between sensitivity and specificity and was achieved with three features. Using only these three features, we achieved an accuracy of 67.63% with sensitivity and specificity 72.87% and 66.67% respectively. However, for patients with no prior diagnosis of CAD, only two features (sex and angiotensin-converting enzyme inhibitor/angiotensin receptor blocker use) were needed to achieve accuracy of 70.32% with sensitivity and specificity at 70.24%. Conclusions: This study shows that machine learning can predict the outcome of stress echocardiography based on only a few features: patient prior cardiac history, gender, and prescribed medication. Further research recruiting higher number of patients who underwent stress echocardiography could further improve the performance of the proposed algorithm with the potential of facilitating patient selection for early treatment/intervention avoiding unnecessary downstream testing. %M 32469316 %R 10.2196/16975 %U http://cardio.jmir.org/2020/1/e16975/ %U https://doi.org/10.2196/16975 %U http://www.ncbi.nlm.nih.gov/pubmed/32469316 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 21 %N 1 %P e12790 %T Use of the CHA2DS2-VASc Score for Risk Stratification of Hospital Admissions Among Patients With Cardiovascular Diseases Receiving a Fourth-Generation Synchronous Telehealth Program: Retrospective Cohort Study %A Lee,Jen-Kuang %A Hung,Chi-Sheng %A Huang,Ching-Chang %A Chen,Ying-Hsien %A Chuang,Pao-Yu %A Yu,Jiun-Yu %A Ho,Yi-Lwun %+ Telehealth Center, National Taiwan University Hospital, No 7, Chung-Shan South Road, Taipei,, Taiwan, 886 2 23123456 ext 63651, ylho@ntu.edu.tw %K CHA2DS2-VASc score %K fourth-generation synchronous telehealth program %K hospitalization %K cardiovascular disease %D 2019 %7 31.01.2019 %9 Original Paper %J J Med Internet Res %G English %X Background: Telehealth programs are generally diverse in approaching patients, from traditional telephone calling and texting message and to the latest fourth-generation synchronous program. The predefined outcomes are also different, including hypertension control, lipid lowering, cardiovascular outcomes, and mortality. In previous studies, the telehealth program showed both positive and negative results, providing mixed and confusing clinical outcomes. A comprehensive and integrated approach is needed to determine which patients benefit from the program in order to improve clinical outcomes. Objective: The CHA2DS2-VASc (congestive heart failure, hypertension, age >75 years [doubled], type 2 diabetes mellitus, previous stroke, transient ischemic attack or thromboembolism [doubled], vascular disease, age of 65-75 years, and sex) score has been widely used for the prediction of stroke in patients with atrial fibrillation. This study investigated the CHA2DS2-VASc score to stratify patients with cardiovascular diseases receiving a fourth-generation synchronous telehealth program. Methods: This was a retrospective cohort study. We recruited patients with cardiovascular disease who received the fourth-generation synchronous telehealth program at the National Taiwan University Hospital between October 2012 and June 2015. We enrolled 431 patients who had joined a telehealth program and compared them to 1549 control patients. Risk of cardiovascular hospitalization was estimated with Kaplan-Meier curves. The CHA2DS2-VASc score was used as the composite parameter to stratify the severity of patients’ conditions. The association between baseline characteristics and clinical outcomes was assessed via the Cox proportional hazard model. Results: The mean follow-up duration was 886.1 (SD 531.0) days in patients receiving the fourth-generation synchronous telehealth program and 707.1 (SD 431.4) days in the control group (P<.001). The telehealth group had more comorbidities at baseline than the control group. Higher CHA2DS2-VASc scores (≥4) were associated with a lower estimated rate of remaining free from cardiovascular hospitalization (46.5% vs 54.8%, log-rank P=.003). Patients with CHA2DS2-VASc scores ≥4 receiving the telehealth program were less likely to be admitted for cardiovascular disease than patients not receiving the program. (61.5% vs 41.8%, log-rank P=.01). The telehealth program remained a significant prognostic factor after multivariable Cox analysis in patients with CHA2DS2-VASc scores ≥4 (hazard ratio=0.36 [CI 0.22-0.62], P<.001) Conclusions: A higher CHA2DS2-VASc score was associated with a higher risk of cardiovascular admissions. Patients accepting the fourth-generation telehealth program with CHA2DS2-VASc scores ≥4 benefit most by remaining free from cardiovascular hospitalization. %M 30702437 %R 10.2196/12790 %U https://www.jmir.org/2019/1/e12790/ %U https://doi.org/10.2196/12790 %U http://www.ncbi.nlm.nih.gov/pubmed/30702437 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 20 %N 3 %P e10093 %T Comment on: Clinical Validity, Understandability, and Actionability of Online Cardiovascular Disease Risk Calculators: Systematic Review %A Sisa,Ivan %+ School of Medicine, College of Health Sciences, Universidad San Francisco de Quito, Diego de Robles y Via Interoceanica, Quito,, Ecuador, 593 2 297 1700 ext 4017, isisa@usfq.edu.ec %K cardiovascular disease %K risk assessment %K risk model %D 2018 %7 05.03.2018 %9 Letter to the Editor %J J Med Internet Res %G English %X %M 29506971 %R 10.2196/10093 %U http://www.jmir.org/2018/3/e10093/ %U https://doi.org/10.2196/10093 %U http://www.ncbi.nlm.nih.gov/pubmed/29506971 %0 Journal Article %@ 1438-8871 %I JMIR Publications %V 20 %N 2 %P e29 %T Clinical Validity, Understandability, and Actionability of Online Cardiovascular Disease Risk Calculators: Systematic Review %A Bonner,Carissa %A Fajardo,Michael Anthony %A Hui,Samuel %A Stubbs,Renee %A Trevena,Lyndal %+ School of Public Health, The University of Sydney, Edward Ford Building (A27) Room 226A, Camperdown,, Australia, 61 2 9351 7125, carissa.bonner@sydney.edu.au %K cardiovascular disease %K risk assessment %K risk communication %K risk formats %D 2018 %7 01.02.2018 %9 Review %J J Med Internet Res %G English %X Background: Online health information is particularly important for cardiovascular disease (CVD) prevention, where lifestyle changes are recommended until risk becomes high enough to warrant pharmacological intervention. Online information is abundant, but the quality is often poor and many people do not have adequate health literacy to access, understand, and use it effectively. Objective: This project aimed to review and evaluate the suitability of online CVD risk calculators for use by low health literate consumers in terms of clinical validity, understandability, and actionability. Methods: This systematic review of public websites from August to November 2016 used evaluation of clinical validity based on a high-risk patient profile and assessment of understandability and actionability using Patient Education Material Evaluation Tool for Print Materials. Results: A total of 67 unique webpages and 73 unique CVD risk calculators were identified. The same high-risk patient profile produced widely variable CVD risk estimates, ranging from as little as 3% to as high as a 43% risk of a CVD event over the next 10 years. One-quarter (25%) of risk calculators did not specify what model these estimates were based on. The most common clinical model was Framingham (44%), and most calculators (77%) provided a 10-year CVD risk estimate. The calculators scored moderately on understandability (mean score 64%) and poorly on actionability (mean score 19%). The absolute percentage risk was stated in most (but not all) calculators (79%), and only 18% included graphical formats consistent with recommended risk communication guidelines. Conclusions: There is a plethora of online CVD risk calculators available, but they are not readily understandable and their actionability is poor. Entering the same clinical information produces widely varying results with little explanation. Developers need to address actionability as well as clinical validity and understandability to improve usefulness to consumers with low health literacy. %M 29391344 %R 10.2196/jmir.8538 %U http://www.jmir.org/2018/2/e29/ %U https://doi.org/10.2196/jmir.8538 %U http://www.ncbi.nlm.nih.gov/pubmed/29391344