TY - JOUR AU - Park, Jin-Hyun AU - Jeong, Inyong AU - Ko, Gang-Jee AU - Jeong, Seogsong AU - Lee, Hwamin PY - 2025/5/2 TI - Development of a Predictive Model for Metabolic Syndrome Using Noninvasive Data and its Cardiovascular Disease Risk Assessments: Multicohort Validation Study JO - J Med Internet Res SP - e67525 VL - 27 KW - metabolic syndrome prediction KW - noninvasive data KW - clinical interpretable model KW - body composition data KW - early intervention N2 - 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. UR - https://www.jmir.org/2025/1/e67525 UR - http://dx.doi.org/10.2196/67525 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/67525 ER - TY - JOUR AU - Wang, Jun AU - Zhu, Jiajun AU - Li, Hui AU - Wu, Shili AU - Li, Siyang AU - Yao, Zhuoya AU - Zhu, Tongjian AU - Tang, Bi AU - Tang, Shengxing AU - Liu, Jinjun PY - 2025/5/1 TI - 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 JO - J Med Internet Res SP - e70587 VL - 27 KW - machine learning KW - interpretable models KW - heart failure with preserved ejection fraction KW - symptomatic aortic stenosis KW - transcatheter aortic valve replacement KW - major adverse cardiovascular and cerebrovascular events. N2 - 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. UR - https://www.jmir.org/2025/1/e70587 UR - http://dx.doi.org/10.2196/70587 UR - http://www.ncbi.nlm.nih.gov/pubmed/40310672 ID - info:doi/10.2196/70587 ER - TY - JOUR AU - Yang, Li-Tan AU - Wu, Chi-Han AU - Lee, Jen-Kuang AU - Wang, Wei-Jyun AU - Chen, Ying-Hsien AU - Huang, Ching-Chang AU - Hung, Chi-Sheng AU - Chiang, Kuang-Chien AU - Ho, Yi-Lwun AU - Wu, Hui-Wen PY - 2025/4/23 TI - Effects of a Cloud-Based Synchronous Telehealth Program on Valvular Regurgitation Regression: Retrospective Study JO - J Med Internet Res SP - e68929 VL - 27 KW - mitral regurgitation KW - tricuspid regurgitation KW - telehealth KW - telemedicine KW - cardiac remodeling N2 - 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. UR - https://publichealth.jmir.org/2025/1/e66218 UR - http://dx.doi.org/10.2196/66218 ID - info:doi/10.2196/66218 ER - TY - JOUR AU - Kou, Yanqi AU - Ye, Shicai AU - Tian, Yuan AU - Yang, Ke AU - Qin, Ling AU - Huang, Zhe AU - Luo, Botao AU - Ha, Yanping AU - Zhan, Liping AU - Ye, Ruyin AU - Huang, Yujie AU - Zhang, Qing AU - He, Kun AU - Liang, Mouji AU - Zheng, Jieming AU - Huang, Haoyuan AU - Wu, Chunyi AU - Ge, Lei AU - Yang, Yuping PY - 2025/1/30 TI - Risk Factors for Gastrointestinal Bleeding in Patients With Acute Myocardial Infarction: Multicenter Retrospective Cohort Study JO - J Med Internet Res SP - e67346 VL - 27 KW - acute myocardial infarction KW - gastrointestinal bleeding KW - machine learning KW - in-hospital KW - prediction model N2 - 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. UR - https://www.jmir.org/2025/1/e67346 UR - http://dx.doi.org/10.2196/67346 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/67346 ER - TY - JOUR AU - Joyce, Elizabeth AU - McMullen, James AU - Kong, Xiaowen AU - O'Hare, Connor AU - Gavrila, Valerie AU - Cuttitta, Anthony AU - Barnes, D. Geoffrey AU - Greineder, F. Colin PY - 2025/1/20 TI - Performance of an Electronic Health Record?Based Automated Pulmonary Embolism Severity Index Score Calculator: Cohort Study in the Emergency Department JO - JMIR Med Inform SP - e58800 VL - 13 KW - pulmonary embolism KW - low-risk pulmonary embolism KW - risk KW - artery KW - pulmonary embolism severity index KW - clinical decision support KW - emergency department KW - hospital KW - lung KW - blood KW - clot KW - clotting KW - cardiovascular KW - index KW - score KW - measure KW - scale KW - tomography KW - image KW - imaging KW - PESI KW - CDS KW - ED N2 - 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. UR - https://medinform.jmir.org/2025/1/e58800 UR - http://dx.doi.org/10.2196/58800 ID - info:doi/10.2196/58800 ER - TY - JOUR AU - Scholes, Shaun AU - Mindell, S. Jennifer AU - Toomse-Smith, Mari AU - Cois, Annibale AU - Adjaye-Gbewonyo, Kafui PY - 2025/1/20 TI - 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 JO - JMIR Cardio SP - e64893 VL - 9 KW - data harmonization KW - cardiovascular disease KW - CVD KW - CVD risk scores KW - trends KW - cross-country comparisons KW - public health KW - England KW - South Africa N2 - 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. UR - https://cardio.jmir.org/2025/1/e64893 UR - http://dx.doi.org/10.2196/64893 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/64893 ER - TY - JOUR AU - You, Yuzi AU - Liang, Wei AU - Zhao, Yajie PY - 2025/1/15 TI - Development and Validation of a Predictive Model Based on Serum Silent Information Regulator 6 Levels in Chinese Older Adult Patients: Cross-Sectional Descriptive Study JO - JMIR Aging SP - e64374 VL - 8 KW - aging KW - coronary artery disease KW - nomogram KW - SIRT6 KW - TyG index KW - silent information regulator 6 KW - triglyceride glucose index N2 - 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. UR - https://aging.jmir.org/2025/1/e64374 UR - http://dx.doi.org/10.2196/64374 ID - info:doi/10.2196/64374 ER - TY - JOUR AU - Lolak, Sermkiat AU - Attia, John AU - McKay, J. Gareth AU - Thakkinstian, Ammarin PY - 2025/1/8 TI - Application of Dragonnet and Conformal Inference for Estimating Individualized Treatment Effects for Personalized Stroke Prevention: Retrospective Cohort Study JO - JMIR Cardio SP - e50627 VL - 9 KW - stroke KW - causal effect KW - ITE KW - individual treatment effect KW - Dragonnet KW - conformal inference KW - mortality KW - hospital records KW - hypertension KW - risk factor KW - diabetes KW - dyslipidemia KW - atrial fibrillation KW - machine learning KW - treatment N2 - 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. UR - https://cardio.jmir.org/2025/1/e50627 UR - http://dx.doi.org/10.2196/50627 ID - info:doi/10.2196/50627 ER - TY - JOUR AU - Jiang, Xiangkui AU - Wang, Bingquan PY - 2024/12/31 TI - Enhancing Clinical Decision Making by Predicting Readmission Risk in Patients With Heart Failure Using Machine Learning: Predictive Model Development Study JO - JMIR Med Inform SP - e58812 VL - 12 KW - prediction model KW - heart failure KW - hospital readmission KW - machine learning KW - cardiology KW - admissions KW - hospitalization N2 - 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. UR - https://medinform.jmir.org/2024/1/e58812 UR - http://dx.doi.org/10.2196/58812 ID - info:doi/10.2196/58812 ER - TY - JOUR AU - Handra, Julia AU - James, Hannah AU - Mbilinyi, Ashery AU - Moller-Hansen, Ashley AU - O'Riley, Callum AU - Andrade, Jason AU - Deyell, Marc AU - Hague, Cameron AU - Hawkins, Nathaniel AU - Ho, Kendall AU - Hu, Ricky AU - Leipsic, Jonathon AU - Tam, Roger PY - 2024/12/30 TI - The Role of Machine Learning in the Detection of Cardiac Fibrosis in Electrocardiograms: Scoping Review JO - JMIR Cardio SP - e60697 VL - 8 KW - machine learning KW - cardiac fibrosis KW - electrocardiogram KW - ECG KW - detection KW - ML KW - cardiovascular disease KW - review N2 - 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. UR - https://cardio.jmir.org/2024/1/e60697 UR - http://dx.doi.org/10.2196/60697 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/60697 ER - TY - JOUR AU - Deady, Matthew AU - Duncan, Raymond AU - Sonesen, Matthew AU - Estiandan, Renier AU - Stimpert, Kelly AU - Cho, Sylvia AU - Beers, Jeffrey AU - Goodness, Brian AU - Jones, Daniel Lance AU - Forshee, Richard AU - Anderson, A. Steven AU - Ezzeldin, Hussein PY - 2024/11/25 TI - A Computable Phenotype Algorithm for Postvaccination Myocarditis/Pericarditis Detection Using Real-World Data: Validation Study JO - J Med Internet Res SP - e54597 VL - 26 KW - adverse event KW - vaccine safety KW - interoperability KW - computable phenotype KW - postmarket surveillance system KW - fast healthcare interoperability resources KW - FHIR KW - real-world data KW - validation study KW - Food and Drug Administration KW - electronic health records KW - COVID-19 vaccine N2 - 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. UR - https://www.jmir.org/2024/1/e54597 UR - http://dx.doi.org/10.2196/54597 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/54597 ER - TY - JOUR AU - Shimoo, Satoshi AU - Senoo, Keitaro AU - Okawa, Taku AU - Kawai, Kohei AU - Makino, Masahiro AU - Munakata, Jun AU - Tomura, Nobunari AU - Iwakoshi, Hibiki AU - Nishimura, Tetsuro AU - Shiraishi, Hirokazu AU - Inoue, Keiji AU - Matoba, Satoaki PY - 2024/11/22 TI - Using Machine Learning to Predict the Duration of Atrial Fibrillation: Model Development and Validation JO - JMIR Med Inform SP - e63795 VL - 12 KW - persistent atrial fibrillation KW - atrial fibrillation duration KW - 12-lead electrocardiogram KW - machine learning KW - support system N2 - 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. UR - https://medinform.jmir.org/2024/1/e63795 UR - http://dx.doi.org/10.2196/63795 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/63795 ER - TY - JOUR AU - Knowlden, P. Adam AU - Winchester, J. Lee AU - MacDonald, V. Hayley AU - Geyer, D. James AU - Higginbotham, C. John PY - 2024/11/8 TI - 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 JO - JMIR Form Res SP - e54792 VL - 8 KW - obstructive sleep apnea KW - obesity KW - adiposity KW - cardiometabolic KW - cardiometabolic disease KW - risk factors KW - sleep KW - sleep duration KW - sleep apnea KW - Short Sleep Undermines Cardiometabolic Health-Public Health Observational study KW - SLUMBRx study N2 - 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 UR - https://formative.jmir.org/2024/1/e54792 UR - http://dx.doi.org/10.2196/54792 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/54792 ER - TY - JOUR AU - Saraya, Norah AU - McBride, Jonathon AU - Singh, Karandeep AU - Sohail, Omar AU - Das, Jeet Porag PY - 2024/11/8 TI - Comparison of Auscultation Quality Using Contemporary Digital Stethoscopes JO - JMIR Cardio SP - e54746 VL - 8 KW - auscultation KW - digital stethoscopes KW - valvular heart disease UR - https://cardio.jmir.org/2024/1/e54746 UR - http://dx.doi.org/10.2196/54746 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/54746 ER - TY - JOUR AU - Hwang, Ha Seung AU - Lee, Hayeon AU - Lee, Hyuk Jun AU - Lee, Myeongcheol AU - Koyanagi, Ai AU - Smith, Lee AU - Rhee, Youl Sang AU - Yon, Keon Dong AU - Lee, Jinseok PY - 2024/11/5 TI - 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 JO - J Med Internet Res SP - e52794 VL - 26 KW - machine learning KW - hypertension KW - cardiovascular disease KW - artificial intelligence KW - cause of death KW - cardiovascular risk KW - predictive analytics N2 - 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. UR - https://www.jmir.org/2024/1/e52794 UR - http://dx.doi.org/10.2196/52794 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/52794 ER - TY - JOUR AU - Nguyen, Minh Hieu AU - Anderson, William AU - Chou, Shih-Hsiung AU - McWilliams, Andrew AU - Zhao, Jing AU - Pajewski, Nicholas AU - Taylor, Yhenneko PY - 2024/10/28 TI - Predictive Models for Sustained, Uncontrolled Hypertension and Hypertensive Crisis Based on Electronic Health Record Data: Algorithm Development and Validation JO - JMIR Med Inform SP - e58732 VL - 12 KW - machine learning KW - risk prediction KW - predictive model KW - decision support KW - blood pressure KW - cardiovascular KW - electronic health record N2 - 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. UR - https://medinform.jmir.org/2024/1/e58732 UR - http://dx.doi.org/10.2196/58732 ID - info:doi/10.2196/58732 ER - TY - JOUR AU - Achtari, Margaux AU - Salihu, Adil AU - Muller, Olivier AU - Abbé, Emmanuel AU - Clair, Carole AU - Schwarz, Joëlle AU - Fournier, Stephane PY - 2024/10/22 TI - Gender Bias in AI's Perception of Cardiovascular Risk JO - J Med Internet Res SP - e54242 VL - 26 KW - artificial intelligence KW - gender equity KW - coronary artery disease KW - AI KW - cardiovascular KW - risk KW - CAD KW - artery KW - coronary KW - chatbot: health care KW - men: women KW - gender bias KW - gender UR - https://www.jmir.org/2024/1/e54242 UR - http://dx.doi.org/10.2196/54242 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/54242 ER - TY - JOUR AU - Aljaloud, Khalid AU - Al-Barha, Naif AU - Noman, Abeer AU - Aldayel, Abdulaziz AU - Alsharif, Yahya AU - Alshuwaier, Ghareeb PY - 2024/10/17 TI - Dynamics of Blood Lipids Before, During, and After Diurnal Fasting in Inactive Men: Quasi-Experimental Study JO - Interact J Med Res SP - e56207 VL - 13 KW - cardiovascular diseases KW - cardiovascular risk factors KW - lipids KW - glucose measurement KW - fasting KW - Ramadan KW - body composition N2 - 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. UR - https://www.i-jmr.org/2024/1/e56207 UR - http://dx.doi.org/10.2196/56207 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/56207 ER - TY - JOUR AU - Sven?ek, Adrijana AU - Lorber, Mateja AU - Gosak, Lucija AU - Verbert, Katrien AU - Klemenc-Ketis, Zalika AU - Stiglic, Gregor PY - 2024/10/14 TI - The Role of Visualization in Estimating Cardiovascular Disease Risk: Scoping Review JO - JMIR Public Health Surveill SP - e60128 VL - 10 KW - cardiovascular disease prevention KW - risk factors KW - visual analytics KW - visualization KW - mobile phone KW - PRISMA N2 - 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. UR - https://publichealth.jmir.org/2024/1/e60128 UR - http://dx.doi.org/10.2196/60128 UR - http://www.ncbi.nlm.nih.gov/pubmed/39401079 ID - info:doi/10.2196/60128 ER - TY - JOUR AU - Bushey, Erica AU - Wu, Yin AU - Wright, Alexander AU - Pescatello, Linda PY - 2024/10/9 TI - The Influence of Physical Activity and Diet Mobile Apps on Cardiovascular Disease Risk Factors: Meta-Review JO - J Med Internet Res SP - e51321 VL - 26 KW - physical activity KW - diet KW - mobile applications KW - obesity KW - hypertension KW - dyslipidemia KW - diabetes KW - mobile phone N2 - 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 UR - https://www.jmir.org/2024/1/e51321 UR - http://dx.doi.org/10.2196/51321 UR - http://www.ncbi.nlm.nih.gov/pubmed/39382958 ID - info:doi/10.2196/51321 ER - TY - JOUR AU - Johar, Hamimatunnisa AU - Ang, Way Chiew AU - Ismail, Roshidi AU - Kassim, Zaid AU - Su, Tin Tin PY - 2024/9/26 TI - Changes in 10-Year Predicted Cardiovascular Disease Risk for a Multiethnic Semirural Population in South East Asia: Prospective Study JO - JMIR Public Health Surveill SP - e55261 VL - 10 KW - cardiovascular risk trajectory KW - Framingham risk score KW - population-based study KW - low- and middle-income countries N2 - 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. UR - https://publichealth.jmir.org/2024/1/e55261 UR - http://dx.doi.org/10.2196/55261 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/55261 ER - TY - JOUR AU - Howell, R. Carrie AU - Zhang, Li AU - Clay, J. Olivio AU - Dutton, Gareth AU - Horton, Trudi AU - Mugavero, J. Michael AU - Cherrington, L. Andrea PY - 2024/8/7 TI - Social Determinants of Health Phenotypes and Cardiometabolic Condition Prevalence Among Patients in a Large Academic Health System: Latent Class Analysis JO - JMIR Public Health Surveill SP - e53371 VL - 10 KW - social determinants of health KW - electronic medical record KW - phenotypes KW - diabetes KW - obesity KW - cardiovascular disease KW - obese KW - social determinants KW - social determinant KW - cardiometabolic KW - risk factors KW - risk factor KW - latent class analysis KW - cardiometabolic disease KW - EMR KW - EHR KW - electronic health record N2 - 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. UR - https://publichealth.jmir.org/2024/1/e53371 UR - http://dx.doi.org/10.2196/53371 ID - info:doi/10.2196/53371 ER - TY - JOUR AU - Nare, Matthew AU - Jurewicz, Katherina PY - 2024/8/6 TI - Assessing Patient Trust in Automation in Health Care Systems: Within-Subjects Experimental Study JO - JMIR Hum Factors SP - e48584 VL - 11 KW - automation KW - emergency department KW - trust KW - health care KW - artificial intelligence KW - emergency KW - perceptions KW - attitude KW - opinions KW - belief KW - automated KW - trust ratings N2 - 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. UR - https://humanfactors.jmir.org/2024/1/e48584 UR - http://dx.doi.org/10.2196/48584 UR - http://www.ncbi.nlm.nih.gov/pubmed/39106096 ID - info:doi/10.2196/48584 ER - TY - JOUR AU - Yang, Jingang AU - Li, Yingxue AU - Li, Xiang AU - Tao, Shuiying AU - Zhang, Yuan AU - Chen, Tiange AU - Xie, Guotong AU - Xu, Haiyan AU - Gao, Xiaojin AU - Yang, Yuejin PY - 2024/7/30 TI - 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 JO - J Med Internet Res SP - e50067 VL - 26 KW - ST-elevation myocardial infarction KW - in-hospital mortality KW - risk prediction KW - explainable machine learning KW - machine learning KW - acute myocardial infarction KW - myocardial infarction KW - mortality KW - risk KW - predication model KW - china KW - clinical practice KW - validation KW - patient management KW - management N2 - 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 UR - https://www.jmir.org/2024/1/e50067 UR - http://dx.doi.org/10.2196/50067 UR - http://www.ncbi.nlm.nih.gov/pubmed/ ID - info:doi/10.2196/50067 ER - TY - JOUR AU - Liu, Chang AU - Zhang, Kai AU - Yang, Xiaodong AU - Meng, Bingbing AU - Lou, Jingsheng AU - Liu, Yanhong AU - Cao, Jiangbei AU - Liu, Kexuan AU - Mi, Weidong AU - Li, Hao PY - 2024/7/26 TI - Development and Validation of an Explainable Machine Learning Model for Predicting Myocardial Injury After Noncardiac Surgery in Two Centers in China: Retrospective Study JO - JMIR Aging SP - e54872 VL - 7 KW - myocardial injury after noncardiac surgery KW - older patients KW - machine learning KW - personalized prediction KW - myocardial injury KW - risk prediction KW - noncardiac surgery N2 - 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. UR - https://aging.jmir.org/2024/1/e54872 UR - http://dx.doi.org/10.2196/54872 ID - info:doi/10.2196/54872 ER - TY - JOUR AU - Dong, Tim AU - Sinha, Shubhra AU - Zhai, Ben AU - Fudulu, Daniel AU - Chan, Jeremy AU - Narayan, Pradeep AU - Judge, Andy AU - Caputo, Massimo AU - Dimagli, Arnaldo AU - Benedetto, Umberto AU - Angelini, D. Gianni PY - 2024/6/12 TI - Performance Drift in Machine Learning Models for Cardiac Surgery Risk Prediction: Retrospective Analysis JO - JMIRx Med SP - e45973 VL - 5 KW - cardiac surgery KW - artificial intelligence KW - risk prediction KW - machine learning KW - operative mortality KW - data set drift KW - performance drift KW - national data set KW - adult KW - data KW - cardiac KW - surgery KW - cardiology KW - heart KW - risk KW - prediction KW - United Kingdom KW - mortality KW - performance KW - model N2 - 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. UR - https://xmed.jmir.org/2024/1/e45973 UR - http://dx.doi.org/10.2196/45973 ID - info:doi/10.2196/45973 ER - TY - JOUR AU - Xie, Puguang AU - Wang, Hao AU - Xiao, Jun AU - Xu, Fan AU - Liu, Jingyang AU - Chen, Zihang AU - Zhao, Weijie AU - Hou, Siyu AU - Wu, Dongdong AU - Ma, Yu AU - Xiao, Jingjing PY - 2024/5/10 TI - 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 JO - J Med Internet Res SP - e49848 VL - 26 KW - acute myocardial infarction KW - mortality KW - deep learning KW - explainable model KW - prediction N2 - 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. UR - https://www.jmir.org/2024/1/e49848 UR - http://dx.doi.org/10.2196/49848 UR - http://www.ncbi.nlm.nih.gov/pubmed/38728685 ID - info:doi/10.2196/49848 ER - TY - JOUR AU - Shu, Tingting AU - Tang, Ming AU - He, Bo AU - Liu, Xiaozhu AU - Han, Yu AU - Liu, Chang AU - Jose, A. Pedro AU - Wang, Hongyong AU - Zhang, Qing-Wei AU - Zeng, Chunyu PY - 2024/1/24 TI - 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 JO - JMIR Public Health Surveill SP - e46821 VL - 10 KW - age-period-cohort analysis KW - GBD 2019 KW - Global Burden of Disease 2019 study KW - ischemic heart disease KW - mortality KW - risk factors N2 - 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. UR - https://publichealth.jmir.org/2024/1/e46821 UR - http://dx.doi.org/10.2196/46821 UR - http://www.ncbi.nlm.nih.gov/pubmed/38265846 ID - info:doi/10.2196/46821 ER - TY - JOUR AU - Chen, Yuling AU - Turkson-Ocran, Ruth-Alma AU - Koirala, Binu AU - Davidson, M. Patricia AU - Commodore-Mensah, Yvonne AU - Himmelfarb, Dennison Cheryl PY - 2024/1/4 TI - Association Between the Composite Cardiovascular Risk and mHealth Use Among Adults in the 2017-2020 Health Information National Trends Survey: Cross-Sectional Study JO - J Med Internet Res SP - e46277 VL - 26 KW - mobile health KW - usage KW - cardiovascular risk KW - association KW - mobile phone N2 - 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. UR - https://www.jmir.org/2024/1/e46277 UR - http://dx.doi.org/10.2196/46277 UR - http://www.ncbi.nlm.nih.gov/pubmed/38175685 ID - info:doi/10.2196/46277 ER - TY - JOUR AU - Li, Le AU - Ding, Ligang AU - Zhang, Zhuxin AU - Zhou, Likun AU - Zhang, Zhenhao AU - Xiong, Yulong AU - Hu, Zhao AU - Yao, Yan PY - 2023/11/15 TI - Development and Validation of Machine Learning?Based Models to Predict In-Hospital Mortality in Life-Threatening Ventricular Arrhythmias: Retrospective Cohort Study JO - J Med Internet Res SP - e47664 VL - 25 KW - life-threatening ventricular arrhythmia KW - mortality KW - prediction model KW - machine learning KW - critical care KW - cardiac N2 - 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. UR - https://www.jmir.org/2023/1/e47664 UR - http://dx.doi.org/10.2196/47664 UR - http://www.ncbi.nlm.nih.gov/pubmed/37966870 ID - info:doi/10.2196/47664 ER - TY - JOUR AU - Lee, Ji-Soo AU - Lee, Soo-Kyoung PY - 2023/9/12 TI - 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 JO - JMIR Form Res SP - e42756 VL - 7 KW - latent class analysis KW - machine learning KW - metabolic syndrome KW - risk factor KW - single-person households N2 - 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. UR - https://formative.jmir.org/2023/1/e42756 UR - http://dx.doi.org/10.2196/42756 UR - http://www.ncbi.nlm.nih.gov/pubmed/37698907 ID - info:doi/10.2196/42756 ER - TY - JOUR AU - Pandey, Avinash AU - D'Souza, Michelle Marie AU - Pandey, Shekhar Amritanshu AU - Mir, Hassan PY - 2023/8/3 TI - A Web-Based Application for Risk Stratification and Optimization in Patients With Cardiovascular Disease: Pilot Study JO - JMIR Cardio SP - e46533 VL - 7 KW - atherosclerotic cardiovascular disease KW - guideline-directed medical therapy KW - mHealth KW - mobile health KW - risk stratification KW - secondary prevention KW - web application N2 - 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. UR - https://cardio.jmir.org/2023/1/e46533 UR - http://dx.doi.org/10.2196/46533 UR - http://www.ncbi.nlm.nih.gov/pubmed/37535400 ID - info:doi/10.2196/46533 ER - TY - JOUR AU - Riley, Victoria AU - Gidlow, Christopher AU - Fedorowicz, Sophia AU - Lagord, Catherine AU - Thompson, Katherine AU - Woolner, Joshua AU - Taylor, Rosie AU - Clark, Jade AU - Lloyd-Harris, Andrew PY - 2023/2/6 TI - The Impact and Perception of England?s Web-Based Heart Age Test of Cardiovascular Disease Risk: Mixed Methods Study JO - JMIR Cardio SP - e39097 VL - 7 KW - heart age KW - cardiovascular disease KW - CVD prevention KW - web-based risk assessment KW - CVD risk KW - qualitative research KW - cross-sectional design KW - cardiology KW - risk assessment KW - cardiovascular risk KW - heart health KW - user perception KW - risk knowledge KW - engagement KW - web-based N2 - 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. UR - https://cardio.jmir.org/2023/1/e39097 UR - http://dx.doi.org/10.2196/39097 UR - http://www.ncbi.nlm.nih.gov/pubmed/36745500 ID - info:doi/10.2196/39097 ER - TY - JOUR AU - ?uki?, Milena AU - Savi?, Danka AU - Sidorova, Julia PY - 2023/1/17 TI - When Heart Beats Differently in Depression: Review of Nonlinear Heart Rate Variability Measures JO - JMIR Ment Health SP - e40342 VL - 10 KW - heart rate variability KW - HRV KW - electrocardiogram KW - ECG KW - depression KW - autonomous nervous system KW - ANS KW - nonlinear measures KW - cardiac risk KW - cardiovascular KW - mortality KW - heart dynamics KW - ECG analysis KW - analysis KW - online N2 - 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. UR - https://mental.jmir.org/2023/1/e40342 UR - http://dx.doi.org/10.2196/40342 UR - http://www.ncbi.nlm.nih.gov/pubmed/36649063 ID - info:doi/10.2196/40342 ER - TY - JOUR AU - Simon, Steven AU - Mandair, Divneet AU - Albakri, Abdel AU - Fohner, Alison AU - Simon, Noah AU - Lange, Leslie AU - Biggs, Mary AU - Mukamal, Kenneth AU - Psaty, Bruce AU - Rosenberg, Michael PY - 2022/11/2 TI - The Impact of Time Horizon on Classification Accuracy: Application of Machine Learning to Prediction of Incident Coronary Heart Disease JO - JMIR Cardio SP - e38040 VL - 6 IS - 2 KW - coronary heart disease KW - risk prediction KW - machine learning KW - heart KW - heart disease KW - clinical KW - risk KW - myocardial KW - gender N2 - 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. UR - https://cardio.jmir.org/2022/2/e38040 UR - http://dx.doi.org/10.2196/38040 UR - http://www.ncbi.nlm.nih.gov/pubmed/36322114 ID - info:doi/10.2196/38040 ER - TY - JOUR AU - Albuquerque de Almeida, Fernando AU - Corro Ramos, Isaac AU - Al, Maiwenn AU - Rutten-van Mölken, Maureen PY - 2022/8/4 TI - Home Telemonitoring and a Diagnostic Algorithm in the Management of Heart Failure in the Netherlands: Cost-effectiveness Analysis JO - JMIR Cardio SP - e31302 VL - 6 IS - 2 KW - discrete event simulation KW - cost-effectiveness KW - early warning systems KW - home telemonitoring KW - diagnostic algorithm KW - heart failure N2 - 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. UR - https://cardio.jmir.org/2022/2/e31302 UR - http://dx.doi.org/10.2196/31302 UR - http://www.ncbi.nlm.nih.gov/pubmed/35925670 ID - info:doi/10.2196/31302 ER - TY - JOUR AU - Wang, Jinwan AU - Wang, Shuai AU - Zhu, Xuefang Mark AU - Yang, Tao AU - Yin, Qingfeng AU - Hou, Ya PY - 2022/4/20 TI - Risk Prediction of Major Adverse Cardiovascular Events Occurrence Within 6 Months After Coronary Revascularization: Machine Learning Study JO - JMIR Med Inform SP - e33395 VL - 10 IS - 4 KW - major adverse cardiovascular events KW - risk prediction KW - machine learning KW - oversampling KW - data imbalance N2 - 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. UR - https://medinform.jmir.org/2022/4/e33395 UR - http://dx.doi.org/10.2196/33395 UR - http://www.ncbi.nlm.nih.gov/pubmed/35442202 ID - info:doi/10.2196/33395 ER - TY - JOUR AU - Dervic, Elma AU - Deischinger, Carola AU - Haug, Nina AU - Leutner, Michael AU - Kautzky-Willer, Alexandra AU - Klimek, Peter PY - 2022/3/25 TI - 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? JO - JMIR Cardio SP - e36801 VL - 6 IS - 1 KW - gender gap KW - sex differences KW - cardiovascular diseases KW - acute myocardial infarction KW - chronic ischemic heart disease KW - gender KW - diabetes KW - smoking KW - risk factors KW - comorbidities KW - relative risk KW - interaction UR - https://cardio.jmir.org/2022/1/e36801 UR - http://dx.doi.org/10.2196/36801 UR - http://www.ncbi.nlm.nih.gov/pubmed/35333178 ID - info:doi/10.2196/36801 ER - TY - JOUR AU - Janszky, Imre PY - 2022/3/25 TI - Using Caution When Interpreting Gender-Based Relative Risk. Comment on ?The Effect of Cardiovascular Comorbidities on Women Compared to Men: Longitudinal Retrospective Analysis? JO - JMIR Cardio SP - e34647 VL - 6 IS - 1 KW - gender gap KW - sex differences KW - cardiovascular diseases KW - acute myocardial infarction KW - chronic ischemic heart disease KW - gender KW - diabetes KW - smoking KW - risk factors KW - comorbidities KW - relative risk KW - interaction UR - https://cardio.jmir.org/2022/1/e34647 UR - http://dx.doi.org/10.2196/34647 UR - http://www.ncbi.nlm.nih.gov/pubmed/35333181 ID - info:doi/10.2196/34647 ER - TY - JOUR AU - Bangash, Hana AU - Makkawy, Ahmed AU - Gundelach, H. Justin AU - Miller, A. Alexandra AU - Jacobson, A. Kimberly AU - Kullo, J. Iftikhar PY - 2022/2/15 TI - Web-Based Tool (FH Family Share) to Increase Uptake of Cascade Testing for Familial Hypercholesterolemia: Development and Evaluation JO - JMIR Hum Factors SP - e32568 VL - 9 IS - 1 KW - familial hypercholesterolemia KW - cascade testing KW - communication KW - genetic counselors KW - digital tools KW - website KW - usability KW - user experience KW - public health N2 - 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. UR - https://humanfactors.jmir.org/2022/1/e32568 UR - http://dx.doi.org/10.2196/32568 UR - http://www.ncbi.nlm.nih.gov/pubmed/35166678 ID - info:doi/10.2196/32568 ER - TY - JOUR AU - Chowdhury, Rajiv AU - Noh, Md Mohd Fairulnizal AU - Ismail, Rasheeqa Sophia AU - van Daalen, Robin Kim AU - Kamaruddin, Megat Puteri Sofia Nadira AU - Zulkiply, Hafizah Siti AU - Azizul, Hayati Nur AU - Khalid, Mustafa Norhayati AU - Ali, Azizan AU - Idris, Mohd Izyan AU - Mei, Shih Yong AU - Abdullah, Rifham Shazana AU - Faridus, Norfashihah AU - Yusof, Md Nur Azirah AU - Yusoff, M. Nur Najwa Farahin AU - Jamal, Rahman AU - Rahim, Abdul Aizai Azan AU - Ghapar, Abdul Abdul Kahar AU - Radhakrishnan, Kutty Ammu AU - Fong, Yip Alan Yean AU - Ismail, Omar AU - Krishinan, Saravanan AU - Lee, Yan Chuey AU - Bang, Houng Liew AU - Mageswaren, Eashwary AU - Mahendran, Kauthaman AU - Amin, Mohd Nor Hanim AU - Muthusamy, Gunavathy AU - Jin, Hean Aaron Ong AU - Ramli, Wazi Ahmad AU - Ross, Thomas Noel AU - Ruhani, Irawan Anwar AU - Yahya, Mansor AU - Yusoff, Yusniza AU - Abidin, Zainal Siti Khairani AU - Amado, Laryssa AU - Bolton, Thomas AU - Weston, Sophie AU - Crawte, Jason AU - Ovenden, Niko AU - Michielsen, Ank AU - Monower, Mostafa Md AU - Mahiyuddin, Wan Wan Rozita AU - Wood, Angela AU - Di Angelantonio, Emanuele AU - Sulaiman, Suffia Nur AU - Danesh, John AU - Butterworth, S. Adam PY - 2022/2/10 TI - Investigating Genetic and Other Determinants of First-Onset Myocardial Infarction in Malaysia: Protocol for the Malaysian Acute Vascular Events Risk Study JO - JMIR Res Protoc SP - e31885 VL - 11 IS - 2 KW - myocardial infarction KW - cardiovascular disease KW - case-control study KW - Malaysia N2 - 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 UR - https://www.researchprotocols.org/2022/2/e31885 UR - http://dx.doi.org/10.2196/31885 UR - http://www.ncbi.nlm.nih.gov/pubmed/35142634 ID - info:doi/10.2196/31885 ER - TY - JOUR AU - Naseri Jahfari, Arman AU - Tax, David AU - Reinders, Marcel AU - van der Bilt, Ivo PY - 2022/1/19 TI - Machine Learning for Cardiovascular Outcomes From Wearable Data: Systematic Review From a Technology Readiness Level Point of View JO - JMIR Med Inform SP - e29434 VL - 10 IS - 1 KW - mHealth KW - wearable KW - machine learning KW - cardiovascular disease KW - digital health KW - review KW - mobile phone N2 - 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. UR - https://medinform.jmir.org/2022/1/e29434 UR - http://dx.doi.org/10.2196/29434 UR - http://www.ncbi.nlm.nih.gov/pubmed/35044316 ID - info:doi/10.2196/29434 ER - TY - JOUR AU - Alamgir, Asma AU - Mousa, Osama AU - Shah, Zubair PY - 2021/12/17 TI - Artificial Intelligence in Predicting Cardiac Arrest: Scoping Review JO - JMIR Med Inform SP - e30798 VL - 9 IS - 12 KW - artificial intelligence KW - machine learning KW - deep learning KW - cardiac arrest KW - predict N2 - 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. UR - https://medinform.jmir.org/2021/12/e30798 UR - http://dx.doi.org/10.2196/30798 UR - http://www.ncbi.nlm.nih.gov/pubmed/34927595 ID - info:doi/10.2196/30798 ER - TY - JOUR AU - Bonner, Carissa AU - Batcup, Carys AU - Cornell, Samuel AU - Fajardo, Anthony Michael AU - Hawkes, L. Anna AU - Trevena, Lyndal AU - Doust, Jenny PY - 2021/11/5 TI - Interventions Using Heart Age for Cardiovascular Disease Risk Communication: Systematic Review of Psychological, Behavioral, and Clinical Effects JO - JMIR Cardio SP - e31056 VL - 5 IS - 2 KW - heart age KW - cardiovascular disease KW - risk assessment KW - risk communication KW - prevention N2 - 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 UR - https://cardio.jmir.org/2021/2/e31056 UR - http://dx.doi.org/10.2196/31056 UR - http://www.ncbi.nlm.nih.gov/pubmed/34738908 ID - info:doi/10.2196/31056 ER - TY - JOUR AU - Dervic, Elma AU - Deischinger, Carola AU - Haug, Nils AU - Leutner, Michael AU - Kautzky-Willer, Alexandra AU - Klimek, Peter PY - 2021/10/4 TI - The Effect of Cardiovascular Comorbidities on Women Compared to Men: Longitudinal Retrospective Analysis JO - JMIR Cardio SP - e28015 VL - 5 IS - 2 KW - gender gap KW - sex differences KW - cardiovascular diseases KW - acute myocardial infarction KW - chronic ischemic heart disease KW - gender KW - diabetes KW - smoking KW - risk factors KW - comorbidities N2 - 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. UR - https://cardio.jmir.org/2021/2/e28015 UR - http://dx.doi.org/10.2196/28015 UR - http://www.ncbi.nlm.nih.gov/pubmed/34605767 ID - info:doi/10.2196/28015 ER - TY - JOUR AU - Kaiser, Hannah AU - Kvist-Hansen, Amanda AU - Becker, Christine AU - Wang, Xing AU - McCauley, D. Benjamin AU - Krakauer, Martin AU - Gørtz, Michael Peter AU - Henningsen, Aaris Kristoffer Mads AU - Zachariae, Claus AU - Skov, Lone AU - Hansen, Riis Peter PY - 2021/9/28 TI - Multiscale Biology of Cardiovascular Risk in Psoriasis: Protocol for a Case-Control Study JO - JMIR Res Protoc SP - e28669 VL - 10 IS - 9 KW - cardiovascular disease KW - psoriasis KW - study protocol KW - cardiovascular imaging KW - proteomics KW - lipidomics KW - microbiome KW - mass cytometry KW - bioinformatics KW - system biology N2 - 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 UR - https://www.researchprotocols.org/2021/9/e28669 UR - http://dx.doi.org/10.2196/28669 UR - http://www.ncbi.nlm.nih.gov/pubmed/34581684 ID - info:doi/10.2196/28669 ER - TY - JOUR AU - Chi, Chien-Yu AU - Ao, Shuang AU - Winkler, Adrian AU - Fu, Kuan-Chun AU - Xu, Jie AU - Ho, Yi-Lwun AU - Huang, Chien-Hua AU - Soltani, Rohollah PY - 2021/9/13 TI - Predicting the Mortality and Readmission of In-Hospital Cardiac Arrest Patients With Electronic Health Records: A Machine Learning Approach JO - J Med Internet Res SP - e27798 VL - 23 IS - 9 KW - in-hospital cardiac arrest KW - 30-day mortality KW - 30-day readmission KW - machine learning KW - imbalanced dataset N2 - 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. UR - https://www.jmir.org/2021/9/e27798 UR - http://dx.doi.org/10.2196/27798 UR - http://www.ncbi.nlm.nih.gov/pubmed/34515639 ID - info:doi/10.2196/27798 ER - TY - JOUR AU - Keim-Malpass, Jessica AU - Ratcliffe, J. Sarah AU - Moorman, P. Liza AU - Clark, T. Matthew AU - Krahn, N. Katy AU - Monfredi, J. Oliver AU - Hamil, Susan AU - Yousefvand, Gholamreza AU - Moorman, Randall J. AU - Bourque, M. Jamieson PY - 2021/7/2 TI - Predictive Monitoring?Impact in Acute Care Cardiology Trial (PM-IMPACCT): Protocol for a Randomized Controlled Trial JO - JMIR Res Protoc SP - e29631 VL - 10 IS - 7 KW - predictive analytics monitoring KW - AI KW - randomized controlled trial KW - risk estimation KW - clinical deterioration KW - visual analytics KW - artificial intelligence KW - monitoring KW - risk KW - prediction KW - impact KW - cardiology KW - acute care N2 - 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 UR - https://www.researchprotocols.org/2021/7/e29631 UR - http://dx.doi.org/10.2196/29631 UR - http://www.ncbi.nlm.nih.gov/pubmed/34043525 ID - info:doi/10.2196/29631 ER - TY - JOUR AU - Tran, Linh AU - Chi, Lianhua AU - Bonti, Alessio AU - Abdelrazek, Mohamed AU - Chen, Phoebe Yi-Ping PY - 2021/4/1 TI - Mortality Prediction of Patients With Cardiovascular Disease Using Medical Claims Data Under Artificial Intelligence Architectures: Validation Study JO - JMIR Med Inform SP - e25000 VL - 9 IS - 4 KW - mortality KW - cardiovascular KW - medical claims data KW - imbalanced data KW - machine learning KW - deep learning N2 - 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. UR - https://medinform.jmir.org/2021/4/e25000 UR - http://dx.doi.org/10.2196/25000 UR - http://www.ncbi.nlm.nih.gov/pubmed/33792549 ID - info:doi/10.2196/25000 ER - TY - JOUR AU - Andy, U. Anietie AU - Guntuku, C. Sharath AU - Adusumalli, Srinath AU - Asch, A. David AU - Groeneveld, W. Peter AU - Ungar, H. Lyle AU - Merchant, M. Raina PY - 2021/2/19 TI - Predicting Cardiovascular Risk Using Social Media Data: Performance Evaluation of Machine-Learning Models JO - JMIR Cardio SP - e24473 VL - 5 IS - 1 KW - ASCVD KW - machine learning KW - natural language processing KW - atherosclerotic KW - cardiovascular disease KW - social media language KW - social media N2 - 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. UR - http://cardio.jmir.org/2021/1/e24473/ UR - http://dx.doi.org/10.2196/24473 UR - http://www.ncbi.nlm.nih.gov/pubmed/33605888 ID - info:doi/10.2196/24473 ER - TY - JOUR AU - Stengl, Helena AU - Ganeshan, Ramanan AU - Hellwig, Simon AU - Blaszczyk, Edyta AU - Fiebach, B. Jochen AU - Nolte, H. Christian AU - Bauer, Axel AU - Schulz-Menger, Jeanette AU - Endres, Matthias AU - Scheitz, F. Jan PY - 2021/2/5 TI - Cardiomyocyte Injury Following Acute Ischemic Stroke: Protocol for a Prospective Observational Cohort Study JO - JMIR Res Protoc SP - e24186 VL - 10 IS - 2 KW - ischemic stroke KW - troponin T KW - myocardial ischemia KW - myocardial injury KW - stroke-heart syndrome KW - cardiac imaging techniques KW - magnetic resonance imaging KW - Takotsubo syndrome KW - autonomic nervous system N2 - 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 UR - http://www.researchprotocols.org/2021/2/e24186/ UR - http://dx.doi.org/10.2196/24186 UR - http://www.ncbi.nlm.nih.gov/pubmed/33544087 ID - info:doi/10.2196/24186 ER - TY - JOUR AU - Likosky, Donald AU - Yule, J. Steven AU - Mathis, R. Michael AU - Dias, D. Roger AU - Corso, J. Jason AU - Zhang, Min AU - Krein, L. Sarah AU - Caldwell, D. Matthew AU - Louis, Nathan AU - Janda, M. Allison AU - Shah, J. Nirav AU - Pagani, D. Francis AU - Stakich-Alpirez, Korana AU - Manojlovich, M. Milisa PY - 2021/1/8 TI - Novel Assessments of Technical and Nontechnical Cardiac Surgery Quality: Protocol for a Mixed Methods Study JO - JMIR Res Protoc SP - e22536 VL - 10 IS - 1 KW - cardiac surgery KW - quality KW - protocol KW - study KW - coronary artery bypass grafting surgery KW - complications KW - patient risk KW - variation KW - intraoperative KW - improvement N2 - 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 UR - https://www.researchprotocols.org/2021/1/e22536 UR - http://dx.doi.org/10.2196/22536 UR - http://www.ncbi.nlm.nih.gov/pubmed/33416505 ID - info:doi/10.2196/22536 ER - TY - JOUR AU - Bennasar, Mohamed AU - Banks, Duncan AU - Price, A. Blaine AU - Kardos, Attila PY - 2020/5/29 TI - Minimal Patient Clinical Variables to Accurately Predict Stress Echocardiography Outcome: Validation Study Using Machine Learning Techniques JO - JMIR Cardio SP - e16975 VL - 4 IS - 1 KW - stress echocardiography KW - coronary heart disease KW - risk factors KW - machine learning KW - feature selection KW - risk prediction N2 - 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. UR - http://cardio.jmir.org/2020/1/e16975/ UR - http://dx.doi.org/10.2196/16975 UR - http://www.ncbi.nlm.nih.gov/pubmed/32469316 ID - info:doi/10.2196/16975 ER - TY - JOUR AU - Lee, Jen-Kuang AU - Hung, Chi-Sheng AU - Huang, Ching-Chang AU - Chen, Ying-Hsien AU - Chuang, Pao-Yu AU - Yu, Jiun-Yu AU - Ho, Yi-Lwun PY - 2019/01/31 TI - 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 JO - J Med Internet Res SP - e12790 VL - 21 IS - 1 KW - CHA2DS2-VASc score KW - fourth-generation synchronous telehealth program KW - hospitalization KW - cardiovascular disease N2 - 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. UR - https://www.jmir.org/2019/1/e12790/ UR - http://dx.doi.org/10.2196/12790 UR - http://www.ncbi.nlm.nih.gov/pubmed/30702437 ID - info:doi/10.2196/12790 ER - TY - JOUR AU - Sisa, Ivan PY - 2018/03/05 TI - Comment on: Clinical Validity, Understandability, and Actionability of Online Cardiovascular Disease Risk Calculators: Systematic Review JO - J Med Internet Res SP - e10093 VL - 20 IS - 3 KW - cardiovascular disease KW - risk assessment KW - risk model UR - http://www.jmir.org/2018/3/e10093/ UR - http://dx.doi.org/10.2196/10093 UR - http://www.ncbi.nlm.nih.gov/pubmed/29506971 ID - info:doi/10.2196/10093 ER - TY - JOUR AU - Bonner, Carissa AU - Fajardo, Anthony Michael AU - Hui, Samuel AU - Stubbs, Renee AU - Trevena, Lyndal PY - 2018/02/01 TI - Clinical Validity, Understandability, and Actionability of Online Cardiovascular Disease Risk Calculators: Systematic Review JO - J Med Internet Res SP - e29 VL - 20 IS - 2 KW - cardiovascular disease KW - risk assessment KW - risk communication KW - risk formats N2 - 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. UR - http://www.jmir.org/2018/2/e29/ UR - http://dx.doi.org/10.2196/jmir.8538 UR - http://www.ncbi.nlm.nih.gov/pubmed/29391344 ID - info:doi/10.2196/jmir.8538 ER -