%0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e45130 %T Cloud-Based Machine Learning Platform to Predict Clinical Outcomes at Home for Patients With Cardiovascular Conditions Discharged From Hospital: Clinical Trial %A Yang,Phillip C %A Jha,Alokkumar %A Xu,William %A Song,Zitao %A Jamp,Patrick %A Teuteberg,Jeffrey J %+ Stanford University School of Medicine, 300 Pasteur Dr # H2157 Stanford, Palo Alto, CA, 94305-2200, United States, 1 6508048828, phillip@stanford.edu %K smart sensor %K wearable technology %K moving average %K physical activity %K artificial intelligence %K AI %D 2024 %7 1.3.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Hospitalizations account for almost one-third of the US $4.1 trillion health care cost in the United States. A substantial portion of these hospitalizations are attributed to readmissions, which led to the establishment of the Hospital Readmissions Reduction Program (HRRP) in 2012. The HRRP reduces payments to hospitals with excess readmissions. In 2018, >US $700 million was withheld; this is expected to exceed US $1 billion by 2022. More importantly, there is nothing more physically and emotionally taxing for readmitted patients and demoralizing for hospital physicians, nurses, and administrators. Given this high uncertainty of proper home recovery, intelligent monitoring is needed to predict the outcome of discharged patients to reduce readmissions. Physical activity (PA) is one of the major determinants for overall clinical outcomes in diabetes, hypertension, hyperlipidemia, heart failure, cancer, and mental health issues. These are the exact comorbidities that increase readmission rates, underlining the importance of PA in assessing the recovery of patients by quantitative measurement beyond the questionnaire and survey methods. Objective: This study aims to develop a remote, low-cost, and cloud-based machine learning (ML) platform to enable the precision health monitoring of PA, which may fundamentally alter the delivery of home health care. To validate this technology, we conducted a clinical trial to test the ability of our platform to predict clinical outcomes in discharged patients. Methods: Our platform consists of a wearable device, which includes an accelerometer and a Bluetooth sensor, and an iPhone connected to our cloud-based ML interface to analyze PA remotely and predict clinical outcomes. This system was deployed at a skilled nursing facility where we collected >17,000 person-day data points over 2 years, generating a solid training database. We used these data to train our extreme gradient boosting (XGBoost)–based ML environment to conduct a clinical trial, Activity Assessment of Patients Discharged from Hospital-I, to test the hypothesis that a comprehensive profile of PA would predict clinical outcome. We developed an advanced data-driven analytic platform that predicts the clinical outcome based on accurate measurements of PA. Artificial intelligence or an ML algorithm was used to analyze the data to predict short-term health outcome. Results: We enrolled 52 patients discharged from Stanford Hospital. Our data demonstrated a robust predictive system to forecast health outcome in the enrolled patients based on their PA data. We achieved precise prediction of the patients’ clinical outcomes with a sensitivity of 87%, a specificity of 79%, and an accuracy of 85%. Conclusions: To date, there are no reliable clinical data, using a wearable device, regarding monitoring discharged patients to predict their recovery. We conducted a clinical trial to assess outcome data rigorously to be used reliably for remote home care by patients, health care professionals, and caretakers. %M 38427393 %R 10.2196/45130 %U https://cardio.jmir.org/2024/1/e45130 %U https://doi.org/10.2196/45130 %U http://www.ncbi.nlm.nih.gov/pubmed/38427393 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e56763 %T Association Between Video-Based Telemedicine Visits and Medication Adherence Among Patients With Heart Failure: Retrospective Cross-Sectional Study %A Zheng,Yaguang %A Adhikari,Samrachana %A Li,Xiyue %A Zhao,Yunan %A Mukhopadhyay,Amrita %A Hamo,Carine E %A Stokes,Tyrel %A Blecker,Saul %K telemedicine %K medication adherence %K heart failure %K systolic dysfunction %K medical therapy %K telehealth %K remote monitoring %K self-management %D 2024 %7 5.12.2024 %9 %J JMIR Cardio %G English %X Background: Despite the exponential growth in telemedicine visits in clinical practice due to the COVID-19 pandemic, it remains unknown if telemedicine visits achieved similar adherence to prescribed medications as in-person office visits for patients with heart failure. Objective: Our study examined the association between telemedicine visits (vs in-person visits) and medication adherence in patients with heart failure. Methods: This was a retrospective cross-sectional study of adult patients with a diagnosis of heart failure or an ejection fraction of ≤40% using data between April 1 and October 1, 2020. This period was used because New York University approved telemedicine visits for both established and new patients by April 1, 2020. The time zero window was between April 1 and October 1, 2020, then each identified patient was monitored for up to 180 days. Medication adherence was measured by the mean proportion of days covered (PDC) within 180 days, and categorized as adherent if the PDC was ≥0.8. Patients were included in the telemedicine exposure group or in-person group if all encounters were video visits or in-person office visits, respectively. Poisson regression and logistic regression models were used for the analyses. Results: A total of 9521 individuals were included in this analysis (telemedicine visits only: n=830 in-person office visits only: n=8691). Overall, the mean age was 76.7 (SD 12.4) years. Most of the patients were White (n=6996, 73.5%), followed by Black (n=1060, 11.1%) and Asian (n=290, 3%). Over half of the patients were male (n=5383, 56.5%) and over half were married or living with partners (n=4914, 51.6%). Most patients’ health insurance was covered by Medicare (n=7163, 75.2%), followed by commercial insurance (n=1687, 17.7%) and Medicaid (n=639, 6.7%). Overall, the average PDC was 0.81 (SD 0.286) and 71.3% (6793/9521) of patients had a PDC≥0.8. There was no significant difference in mean PDC between the telemedicine and in-person office groups (mean 0.794, SD 0.294 vs mean 0.812, SD 0.285) with a rate ratio of 0.99 (95% CI 0.96-1.02; P=.09). Similarly, there was no significant difference in adherence rates between the telemedicine and in-person office groups (573/830, 69% vs 6220/8691, 71.6%), with an odds ratio of 0.94 (95% CI 0.81-1.11; P=.12). The conclusion remained the same after adjusting for covariates (eg, age, sex, race, marriage, language, and insurance). Conclusions: We found similar rates of medication adherence among patients with heart failure who were being seen via telemedicine or in-person visits. Our findings are important for clinical practice because we provide real-world evidence that telemedicine can be an approach for outpatient visits for patients with heart failure. As telemedicine is more convenient and avoids transportation issues, it may be an alternative way to maintain the same medication adherence as in-person visits for patients with heart failure. %R 10.2196/56763 %U https://cardio.jmir.org/2024/1/e56763 %U https://doi.org/10.2196/56763 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e57960 %T Results of a Digital Multimodal Motivational and Educational Program as Follow-Up Care for Former Cardiac Rehabilitation Patients: Randomized Controlled Trial %A Bretschneider,Maxi Pia %A Mayer-Berger,Wolfgang %A Weine,Jens %A Roth,Lena %A Schwarz,Peter E H %A Petermann,Franz %K mHealth %K apps %K digital technology %K digital interventions %K coronary heart disease %K lifestyle intervention %K cardiac rehabilitation %K quality of life %K cardiac care %D 2024 %7 11.12.2024 %9 %J JMIR Cardio %G English %X Background: Digital interventions are promising additions for both usual care and rehabilitation. Evidence and studies for the latter, however, are still rare. Objective: The aim of the study was to examine the app/web-based patient education program called “mebix” (previously called “Vision 2 – Gesundes Herz”) regarding its effectiveness in relation to the parameters of disease-specific quality of life (HeartQoL), cardiovascular risk profile (Cardiovascular Risk Management [CARRISMA]), and prognostic estimation of early retirement (Screening instrument work and occupation [SIBAR]) in 190 participants from a cardiological rehabilitation clinic. Methods: To evaluate mebix, 354 patients from the Roderbirken Clinic of the German Pension Insurance Rhineland (Germany) with a coronary heart diesase were recruited and randomized either to the intervention group (using mebix postrehabiliation for up to 12 months) or the control group (receiving standard care). The data collection took place at the end of inpatient rehabilitation (t0), as well as 6 months (t1) and 12 months (t2) after the end of rehabilitation. Analyses of variance are used to assess the overall significance of difference in outcome parameters between groups and over time. Results: The primary endpoint of disease-related quality of life shows a significant improvement of 7.35 points over the course of the intervention that is also more pronounced in the intervention group. Similarly, the 10-year risk of cardiovascular death and myocardial infarction showed significant improvements in the cardiovascular risk profile over time and between groups, indicating better results in the intervention group (ie, a reduction of −1.59 and −5.03, respectively). Secondary outcomes like the body weight and cholesterol levels were significantly reduced in the intervention group, also in comparison with the control group. In addition, the SIBAR was significantly lower/better at the end of the observation period than at the beginning of the observation for both groups. Conclusions: Overall, the digital training program represents an effective follow-up offer after rehabilitation that could be incorporated into standard care to further improve disease-related quality of life and cardiovascular risk profiles. Trial Registration: German Clinical Trials Register DRKS00007569; https://drks.de/search/en/trial/DRKS00007569 %R 10.2196/57960 %U https://cardio.jmir.org/2024/1/e57960 %U https://doi.org/10.2196/57960 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e57328 %T The Development of Heart Failure Electronic-Message Driven Tips to Support Self-Management: Co-Design Case Study %A Ferguson,Caleb %A William,Scott %A Allida,Sabine M %A Fulcher,Jordan %A Jenkins,Alicia J %A Lattimore,Jo-Dee %A Loch,L-J %A Keech,Anthony %K heart failure %K co-design %K smartphone %K app design %K patient education %K e-TIPS %K electronic-message driven tips %D 2024 %7 7.11.2024 %9 %J JMIR Cardio %G English %X Background: Heart failure (HF) is a complex syndrome associated with high morbidity and mortality and increased health care use. Patient education is key to improving health outcomes, achieved by promoting self-management to optimize medical management. Newer digital tools like SMS text messaging and smartphone apps provide novel patient education approaches. Objective: This study aimed to partner with clinicians and people with lived experience of HF to identify the priority educational topic areas to inform the development and delivery of a bank of electronic-message driven tips (e-TIPS) to support HF self-management. Methods: We conducted 3 focus groups with cardiovascular clinicians, people with lived experience of HF, and their caregivers, which consisted of 2 stages: stage 1 (an exploratory qualitative study to identify the unmet educational needs of people living with HF; previously reported) and stage 2 (a co-design feedback session to identify educational topic areas and inform the delivery of e-TIPS). This paper reports the findings of the co-design feedback session. Results: We identified 5 key considerations in delivering e-TIPS and 5 relevant HF educational topics for their content. Key considerations in e-TIP delivery included (1) timing of the e-TIPS; (2) clear and concise e-TIPS; (3) embedding a feedback mechanism; (4) distinguishing actionable and nonactionable e-TIPS; and (5) frequency of e-TIP delivery. Relevant educational topic areas included the following: (1) cardiovascular risk reduction, (2) self-management, (3) food and nutrition, (4) sleep hygiene, and (5) mental health. Conclusions: The findings from this co-design case study have provided a foundation for developing a bank of e-TIPS. These will now be evaluated for usability in the BANDAIDS e-TIPS, a single-group, quasi-experimental study of a 24-week e-TIP program (personalized educational messages) delivered via SMS text messaging (ACTRN12623000644662). %R 10.2196/57328 %U https://cardio.jmir.org/2024/1/e57328 %U https://doi.org/10.2196/57328 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e54994 %T Identifying Predictors of Heart Failure Readmission in Patients From a Statutory Health Insurance Database: Retrospective Machine Learning Study %A Levinson,Rebecca T %A Paul,Cinara %A Meid,Andreas D %A Schultz,Jobst-Hendrik %A Wild,Beate %+ Department of General Internal Medicine and Psychosomatics, Heidelberg University Hospital, Heidelberg University, Im Neuenheimer Feld 410, Heidelberg, 69120, Germany, 49 6221565888, rebeccaterrall.levinson@med.uni-heidelberg.de %K statutory health insurance %K readmission %K machine learning %K heart failure %K heart %K cardiology %K cardiac %K hospitalization %K insurance %K predict %K predictive %K prediction %K predictions %K predictor %K predictors %K all cause %D 2024 %7 23.7.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Patients with heart failure (HF) are the most commonly readmitted group of adult patients in Germany. Most patients with HF are readmitted for noncardiovascular reasons. Understanding the relevance of HF management outside the hospital setting is critical to understanding HF and factors that lead to readmission. Application of machine learning (ML) on data from statutory health insurance (SHI) allows the evaluation of large longitudinal data sets representative of the general population to support clinical decision-making. Objective: This study aims to evaluate the ability of ML methods to predict 1-year all-cause and HF-specific readmission after initial HF-related admission of patients with HF in outpatient SHI data and identify important predictors. Methods: We identified individuals with HF using outpatient data from 2012 to 2018 from the AOK Baden-Württemberg SHI in Germany. We then trained and applied regression and ML algorithms to predict the first all-cause and HF-specific readmission in the year after the first admission for HF. We fitted a random forest, an elastic net, a stepwise regression, and a logistic regression to predict readmission by using diagnosis codes, drug exposures, demographics (age, sex, nationality, and type of coverage within SHI), degree of rurality for residence, and participation in disease management programs for common chronic conditions (diabetes mellitus type 1 and 2, breast cancer, chronic obstructive pulmonary disease, and coronary heart disease). We then evaluated the predictors of HF readmission according to their importance and direction to predict readmission. Results: Our final data set consisted of 97,529 individuals with HF, and 78,044 (80%) were readmitted within the observation period. Of the tested modeling approaches, the random forest approach best predicted 1-year all-cause and HF-specific readmission with a C-statistic of 0.68 and 0.69, respectively. Important predictors for 1-year all-cause readmission included prescription of pantoprazole, chronic obstructive pulmonary disease, atherosclerosis, sex, rurality, and participation in disease management programs for type 2 diabetes mellitus and coronary heart disease. Relevant features for HF-specific readmission included a large number of canonical HF comorbidities. Conclusions: While many of the predictors we identified were known to be relevant comorbidities for HF, we also uncovered several novel associations. Disease management programs have widely been shown to be effective at managing chronic disease; however, our results indicate that in the short term they may be useful for targeting patients with HF with comorbidity at increased risk of readmission. Our results also show that living in a more rural location increases the risk of readmission. Overall, factors beyond comorbid disease were relevant for risk of HF readmission. This finding may impact how outpatient physicians identify and monitor patients at risk of HF readmission. %R 10.2196/54994 %U https://cardio.jmir.org/2024/1/e54994 %U https://doi.org/10.2196/54994 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e59948 %T Feasibility, Acceptability, and Preliminary Effectiveness of a Combined Digital Platform and Community Health Worker Intervention for Patients With Heart Failure: Pilot Randomized Controlled Trial %A Carter,Jocelyn A Carter %A Swack,Natalia %A Isselbacher,Eric %A Donelan,Karen %A Thorndike,Anne %+ Division of General Internal Medicine, Massachusetts General Hospital, Harvard Medical School, 55 Fruit street, Blake 15, Boston, MA, 02114, United States, 1 1 617 726 2000, jcarter0@partners.org %K heart failure %K heart %K cardiology %K failure %K clinical pilot trial %K digital platform %K home %K digital health %K remote monitoring %K monitoring %K home-based care %K community health workers %K social needs care %K randomized controlled trial %K controlled trials %K feasibility %K usability %K acceptability %K social needs %D 2024 %7 8.8.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Heart failure (HF) is a burdensome condition and a leading cause of 30-day hospital readmissions in the United States. Clinical and social factors are key drivers of hospitalization. These 2 strategies, digital platforms and home-based social needs care, have shown preliminary effectiveness in improving adherence to clinical care plans and reducing acute care use in HF. Few studies, if any, have tested combining these 2 strategies in a single intervention. Objective: This study aims to perform a pilot randomized controlled trial assessing the acceptability, feasibility, and preliminary effectiveness of a 30-day digitally-enabled community health worker (CHW) intervention in HF. Methods: Adults hospitalized with a diagnosis of HF at an academic hospital were randomly assigned to receive digitally-enabled CHW care (intervention; digital platform +CHW) or CHW-enhanced usual care (control; CHW only) for 30 days after hospital discharge. Primary outcomes were feasibility (use of the platform) and acceptability (willingness to use the platform in the future). Secondary outcomes assessed preliminary effectiveness (30-day readmissions, emergency department visits, and missed clinic appointments). Results: A total of 56 participants were randomized (control: n=31; intervention: n=25) and 47 participants (control: n=28; intervention: n=19) completed all trial activities. Intervention participants who completed trial activities wore the digital sensor on 78% of study days with mean use of 11.4 (SD 4.6) hours/day, completed symptom questionnaires on 75% of study days, used the blood pressure monitor 1.1 (SD 0.19) times/day, and used the digital weight scale 1 (SD 0.13) time/day. Of intervention participants, 100% responded very or somewhat true to the statement “If I have access to the [platform] moving forward, I will use it.” Some (n=9, 47%) intervention participants indicated they required support to use the digital platform. A total of 19 (100%) intervention participants and 25 (89%) control participants had ≥5 CHW interactions during the 30-day study period. All intervention (n=19, 100%) and control (n=26, 93%) participants who completed trial activities indicated their CHW interactions were “very satisfying.” In the full sample (N=56), fewer participants in the intervention group were readmitted 30 days after hospital discharge compared to the control group (n=3, 12% vs n=8, 26%; P=.12). Both arms had similar rates of missed clinic appointments and emergency department visits. Conclusions: This pilot trial of a digitally-enabled CHW intervention for HF demonstrated feasibility, acceptability, and a clinically relevant reduction in 30-day readmissions among participants who received the intervention. Additional investigation is needed in a larger trial to determine the effect of this intervention on HF home management and clinical outcomes. Trial Registration: Clinicaltrials.gov NCT05130008; https://clinicaltrials.gov/study/NCT05130008 International Registered Report Identifier (IRRID): RR2-10.2196/55687 %M 38959294 %R 10.2196/59948 %U https://cardio.jmir.org/2024/1/e59948 %U https://doi.org/10.2196/59948 %U http://www.ncbi.nlm.nih.gov/pubmed/38959294 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e42402 %T Effects of a Web-based Weight Management Education Program on Various Factors for Overweight and Obese Women: Randomized Controlled Trial %A Han,Yunmin %A Sung,Hoyong %A Kim,Geonhui %A Ryu,Yeun %A Yoon,Jiyeon %A Kim,Yeon Soo %+ Department of Physical Education, Seoul National University, Seoul, Gawnak Gu, Gawankro 1, 71-1, 408, Seoul, 08826, Republic of Korea, 82 2 880 7894, kys0101@snu.ac.kr %K weight loss %K obesity %K health education %K self-management %K health promotion %K tailored feedback %K web-based intervention %K behavior change %D 2024 %7 18.4.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Mediated diet and exercise methods yield effective short-term weight loss but are costly and hard to manage. However, web-based programs can serve many participants, offering ease of access and cost-efficiency. Objective: This study aimed to compare the effectiveness of a web-based weight management program through web-based education alone (MINE) or combined with tailored video feedback (MINE Plus) with a control (CO) group. Methods: This intervention included 60 Korean women with overweight and obesity (BMI≥23 kg/m2) aged 19 years to 39 years old. We randomly allocated 60 participants to each of 3 groups: (1) MINE group (web-based education video and self-monitoring app), (2) MINE Plus group (web-based education video, self-monitoring app, and 1:1 tailored video feedback), and (3) CO group (only self-monitoring app). Web-based education included nutrition, physical activity, psychological factors, medical knowledge for weight loss, goal setting, and cognitive and behavioral strategies. Tailored feedback aimed to motivate and provide solutions via weekly 10-minute real-time video sessions. The intervention lasted 6 weeks, followed by a 6-week observation period to assess the education's lasting effects, with evaluations at baseline, 6 weeks, and 12 weeks. A generalized linear mixed model was used to evaluate time and group interactions. Results: In the intention-to-treat analysis including all 60 participants, there were significant differences in weight change at 6 weeks in the MINE and MINE Plus groups, with mean weight changes of –0.74 (SD 1.96) kg (P=.03) and –1.87 (SD 1.8) kg (P<.001), respectively, while no significant change was observed in the CO group, who had a mean weight increase of 0.03 (SD 1.68) kg (P=.91). After 12 weeks, changes in body weight were –1.65 (SD 2.64) kg in the MINE group, –1.59 (SD 2.79) kg in the MINE Plus group, and 0.43 (SD 1.42) kg in the CO group. There was a significant difference between the MINE and MINE Plus groups (P<.001). Significant group × time effects were found for body weight in the MINE and CO groups (P<.001) and in the MINE Plus and CO groups (P<.001), comparing baseline and 12 weeks. Regarding physical activity and psychological factors, only body shape satisfaction and health self-efficacy were associated with improvements in the MINE and MINE Plus groups (P<.001). Conclusions: This study found that the group receiving education and tailored feedback showed significant weight loss and improvements in several psychological factors, though there were differences in the sustainability of the effects. Trial Registration: Korea Disease Control and Prevention Agency (KDCA) KCT0007780: https://cris.nih.go.kr/cris/search/detailSearch.do/22861 %M 38635975 %R 10.2196/42402 %U https://cardio.jmir.org/2024/1/e42402 %U https://doi.org/10.2196/42402 %U http://www.ncbi.nlm.nih.gov/pubmed/38635975 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e48971 %T Formative Perceptions of a Digital Pill System to Measure Adherence to Heart Failure Pharmacotherapy: Mixed Methods Study %A Chai,Peter R %A Kaithamattam,Jenson J %A Chung,Michelle %A Tom,Jeremiah J %A Goodman,Georgia R %A Hasdianda,Mohammad Adrian %A Carnes,Tony Christopher %A Vaduganathan,Muthiah %A Scirica,Benjamin M %A Schnipper,Jeffrey L %+ Department of Emergency Medicine, Brigham and Women’s Hospital, 75 Francis Street, Boston, MA, 02115, United States, 1 617 732 5640, pchai@bwh.harvard.edu %K behavioral interventions %K cardiac treatment %K digital pill system %K heart failure medication %K heart failure %K ingestible sensors %K medication adherence %D 2024 %7 15.2.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Heart failure (HF) affects 6.2 million Americans and is a leading cause of hospitalization. The mainstay of the management of HF is adherence to pharmacotherapy. Despite the effectiveness of HF pharmacotherapy, effectiveness is closely linked to adherence. Measuring adherence to HF pharmacotherapy is difficult; most clinical measures use indirect strategies such as calculating pharmacy refill data or using self-report. While helpful in guiding treatment adjustments, indirect measures of adherence may miss the detection of suboptimal adherence and co-occurring structural barriers associated with nonadherence. Digital pill systems (DPSs), which use an ingestible radiofrequency emitter to directly measure medication ingestions in real-time, represent a strategy for measuring and responding to nonadherence in the context of HF pharmacotherapy. Previous work has demonstrated the feasibility of using DPSs to measure adherence in other chronic diseases, but this strategy has yet to be leveraged for individuals with HF. Objective: We aim to explore through qualitative interviews the facilitators and barriers to using DPS technology to monitor pharmacotherapy adherence among patients with HF. Methods: We conducted individual, semistructured qualitative interviews and quantitative assessments between April and August 2022. A total of 20 patients with HF who were admitted to the general medical or cardiology service at an urban quaternary care hospital participated in this study. Participants completed a qualitative interview exploring the overall acceptability of and willingness to use DPS technology for adherence monitoring and perceived barriers to DPS use. Quantitative assessments evaluated HF history, existing medication adherence strategies, and attitudes toward technology. We analyzed qualitative data using applied thematic analysis and NVivo software (QSR International). Results: Most participants (12/20, 60%) in qualitative interviews reported a willingness to use the DPS to measure HF medication adherence. Overall, the DPS was viewed as useful for increasing accountability and reinforcing adherence behaviors. Perceived barriers included technological issues, a lack of need, additional costs, and privacy concerns. Most were open to sharing adherence data with providers to bolster clinical care and decision-making. Reminder messages following detected nonadherence were perceived as a key feature, and customization was desired. Suggested improvements are primarily related to the design and usability of the Reader (a wearable device). Conclusions: Overall, individuals with HF perceived the DPS to be an acceptable and useful tool for measuring medication adherence. Accurate, real-time ingestion data can guide adherence counseling to optimize adherence management and inform tailored behavioral interventions to support adherence among patients with HF. %M 38358783 %R 10.2196/48971 %U https://cardio.jmir.org/2024/1/e48971 %U https://doi.org/10.2196/48971 %U http://www.ncbi.nlm.nih.gov/pubmed/38358783 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e54801 %T Association of Arterial Stiffness With Mid- to Long-Term Home Blood Pressure Variability in the Electronic Framingham Heart Study: Cohort Study %A Wang,Xuzhi %A Zhang,Yuankai %A Pathiravasan,Chathurangi H %A Ukonu,Nene C %A Rong,Jian %A Benjamin,Emelia J %A McManus,David D %A Larson,Martin G %A Vasan,Ramachandran S %A Hamburg,Naomi M %A Murabito,Joanne M %A Liu,Chunyu %A Mitchell,Gary F %+ Department of Biostatistics, Boston University School of Public Health, 715 Albany Street, Boston, MA, 02118, United States, 1 6176385104, liuc@bu.edu %K arterial stiffness %K mobile health %K mHealth %K blood pressure %K blood pressure variability %K risk factors %D 2024 %7 8.4.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Short-term blood pressure variability (BPV) is associated with arterial stiffness in patients with hypertension. Few studies have examined associations between arterial stiffness and digital home BPV over a mid- to long-term time span, irrespective of underlying hypertension. Objective: This study aims to investigate if arterial stiffness traits were associated with subsequent mid- to long-term home BPV in the electronic Framingham Heart Study (eFHS). We hypothesized that higher arterial stiffness was associated with higher home BPV over up to 1-year follow-up. Methods: At a Framingham Heart Study research examination (2016-2019), participants underwent arterial tonometry to acquire measures of arterial stiffness (carotid-femoral pulse wave velocity [CFPWV]; forward pressure wave amplitude [FWA]) and wave reflection (reflection coefficient [RC]). Participants who agreed to enroll in eFHS were provided with a digital blood pressure (BP) cuff to measure home BP weekly over up to 1-year follow-up. Participants with less than 3 weeks of BP readings were excluded. Linear regression models were used to examine associations of arterial measures with average real variability (ARV) of week-to-week home systolic (SBP) and diastolic (DBP) BP adjusting for important covariates. We obtained ARV as an average of the absolute differences of consecutive home BP measurements. ARV considers not only the dispersion of the BP readings around the mean but also the order of BP readings. In addition, ARV is more sensitive to measurement-to-measurement BPV compared with traditional BPV measures. Results: Among 857 eFHS participants (mean age 54, SD 9 years; 508/857, 59% women; mean SBP/DBP 119/76 mm Hg; 405/857, 47% hypertension), 1 SD increment in FWA was associated with 0.16 (95% CI 0.09-0.23) SD increments in ARV of home SBP and 0.08 (95% CI 0.01-0.15) SD increments in ARV of home DBP; 1 SD increment in RC was associated with 0.14 (95% CI 0.07-0.22) SD increments in ARV of home SBP and 0.11 (95% CI 0.04-0.19) SD increments in ARV of home DBP. After adjusting for important covariates, there was no significant association between CFPWV and ARV of home SBP, and similarly, no significant association existed between CFPWV and ARV of home DBP (P>.05). Conclusions: In eFHS, higher FWA and RC were associated with higher mid- to long-term ARV of week-to-week home SBP and DBP over 1-year follow-up in individuals across the BP spectrum. Our findings suggest that higher aortic stiffness and wave reflection are associated with higher week-to-week variation of BP in a home-based setting over a mid- to long-term time span. %M 38587880 %R 10.2196/54801 %U https://cardio.jmir.org/2024/1/e54801 %U https://doi.org/10.2196/54801 %U http://www.ncbi.nlm.nih.gov/pubmed/38587880 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e57111 %T Accurate Modeling of Ejection Fraction and Stroke Volume With Mobile Phone Auscultation: Prospective Case-Control Study %A Huecker,Martin %A Schutzman,Craig %A French,Joshua %A El-Kersh,Karim %A Ghafghazi,Shahab %A Desai,Ravi %A Frick,Daniel %A Thomas,Jarred Jeremy %+ Department of Emergency Medicine, University of Louisville, 530 South Jackson St., Louisville, KY, 40202, United States, 1 5028525689, martin.huecker@louisville.edu %K ejection fraction %K stroke volume %K auscultation %K digital health %K telehealth %K acoustic recording %K acoustic recordings %K acoustic %K mHealth %K mobile health %K mobile phone %K mobile phones %K heart failure %K heart %K cardiac %K cardiology %K health care costs %K audio %K echocardiographic %K echocardiogram %K ultrasonography %K echocardiography %K accuracy %K monitoring %K telemonitoring %K recording %K recordings %K ejection %K machine learning %K algorithm %K algorithms %D 2024 %7 26.6.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Heart failure (HF) contributes greatly to morbidity, mortality, and health care costs worldwide. Hospital readmission rates are tracked closely and determine federal reimbursement dollars. No current modality or technology allows for accurate measurement of relevant HF parameters in ambulatory, rural, or underserved settings. This limits the use of telehealth to diagnose or monitor HF in ambulatory patients. Objective: This study describes a novel HF diagnostic technology using audio recordings from a standard mobile phone. Methods: This prospective study of acoustic microphone recordings enrolled convenience samples of patients from 2 different clinical sites in 2 separate areas of the United States. Recordings were obtained at the aortic (second intercostal) site with the patient sitting upright. The team used recordings to create predictive algorithms using physics-based (not neural networks) models. The analysis matched mobile phone acoustic data to ejection fraction (EF) and stroke volume (SV) as evaluated by echocardiograms. Using the physics-based approach to determine features eliminates the need for neural networks and overfitting strategies entirely, potentially offering advantages in data efficiency, model stability, regulatory visibility, and physical insightfulness. Results: Recordings were obtained from 113 participants. No recordings were excluded due to background noise or for any other reason. Participants had diverse racial backgrounds and body surface areas. Reliable echocardiogram data were available for EF from 113 patients and for SV from 65 patients. The mean age of the EF cohort was 66.3 (SD 13.3) years, with female patients comprising 38.3% (43/113) of the group. Using an EF cutoff of ≤40% versus >40%, the model (using 4 features) had an area under the receiver operating curve (AUROC) of 0.955, sensitivity of 0.952, specificity of 0.958, and accuracy of 0.956. The mean age of the SV cohort was 65.5 (SD 12.7) years, with female patients comprising 34% (38/65) of the group. Using a clinically relevant SV cutoff of <50 mL versus >50 mL, the model (using 3 features) had an AUROC of 0.922, sensitivity of 1.000, specificity of 0.844, and accuracy of 0.923. Acoustics frequencies associated with SV were observed to be higher than those associated with EF and, therefore, were less likely to pass through the tissue without distortion. Conclusions: This work describes the use of mobile phone auscultation recordings obtained with unaltered cellular microphones. The analysis reproduced the estimates of EF and SV with impressive accuracy. This technology will be further developed into a mobile app that could bring screening and monitoring of HF to several clinical settings, such as home or telehealth, rural, remote, and underserved areas across the globe. This would bring high-quality diagnostic methods to patients with HF using equipment they already own and in situations where no other diagnostic and monitoring options exist. %M 38924781 %R 10.2196/57111 %U https://cardio.jmir.org/2024/1/e57111 %U https://doi.org/10.2196/57111 %U http://www.ncbi.nlm.nih.gov/pubmed/38924781 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e52648 %T Evaluation of a New Telemedicine System for Early Detection of Cardiac Instability in Patients With Chronic Heart Failure: Real-Life Out-of-Hospital Study %A Urien,Jean Marie %A Berthelot,Emmanuelle %A Raphael,Pierre %A Moine,Thomas %A Lopes,Marie Emilie %A Assayag,Patrick %A Jourdain,Patrick %+ CHU Bicêtre, 78 rue du general Leclerc, Le Kremlin Bicêtre, 94270, France, 33 145213735, emmanuelle.berthelot@aphp.fr %K telemedicine system %K follow-up %K detection %K heart failure %K chronic heart failure %K CHF %K heart disease %K ambulatory patient %K ambulatory patients %K home-based %K TwoCan Pulse %K telecardiology %K cardiology %K e-device %K mHealth %K mobile health %K app %K apps %K application %K applications %K effectiveness %K real-life setting %K remote monitoring %K virtual monitoring %K France %K men %K gerontology %K geriatric %K geriatrics %K older adult %K older adults %K elder %K elderly %K older man %K ageing %K aging %D 2024 %7 13.8.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: For a decade, despite results from many studies, telemedicine systems have suffered from a lack of recommendations for chronic heart failure (CHF) care because of variable study results. Another limitation is the hospital-based architecture of most telemedicine systems. Some systems use an algorithm based on daily weight, transcutaneous oxygen measurement, and heart rate to detect and treat acute heart failure (AHF) in patients with CHF as early on as possible. Objective: The aim of this study is to determine the efficacy of a telemonitoring system in detecting clinical destabilization in real-life settings (out-of-hospital management) without generating too many false positive alerts. Methods: All patients self-monitoring at home using the system after a congestive AHF event treated at a cardiology clinic in France between March 2020 and March 2021 with at least 75% compliance on daily measurements were included retrospectively. New-onset AHF was defined by the presence of at least 1 of the following criteria: transcutaneous oxygen saturation loss, defined as a transcutaneous oxygen measurement under 90%; rise of cardiac frequency above 110 beats per minute; weight gain of at least 2 kg; and symptoms of congestive AHF, described over the phone. An AHF alert was generated when the criteria reached our definition of new-onset acute congestive heart failure (HF). Results: A total of 111 consecutive patients (n=70 men) with a median age of 76.60 (IQR 69.5-83.4) years receiving the telemonitoring system were included. Thirty-nine patients (35.1%) reached the HF warning level, and 28 patients (25%) had confirmed HF destabilization during follow-up. No patient had AHF without being detected by the telemonitoring system. Among incorrect AHF alerts (n=11), 5 patients (45%) had taken inaccurate measurements, 3 patients (27%) had supraventricular arrhythmia, 1 patient (9%) had a pulmonary bacterial infection, and 1 patient (9%) contracted COVID-19. A weight gain of at least 2 kg within 4 days was significantly associated with a correct AHF alert (P=.004), and a heart rate of more than 110 beats per minute was more significantly associated with an incorrect AHF alert (P=.007). Conclusions: This single-center study highlighted the efficacy of the telemedicine system in detecting and quickly treating cardiac instability complicating the course of CHF by detecting new-onset AHF as well as supraventricular arrhythmia, thus helping cardiologists provide better follow-up to ambulatory patients. %M 39137030 %R 10.2196/52648 %U https://cardio.jmir.org/2024/1/e52648 %U https://doi.org/10.2196/52648 %U http://www.ncbi.nlm.nih.gov/pubmed/39137030 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e49895 %T Evaluation of the Effectiveness of Advanced Technology Clinical Simulation Manikins in Improving the Capability of Australian Paramedics to Deliver High-Quality Cardiopulmonary Resuscitation: Pre- and Postintervention Study %A Zucca,Alison %A Bryant,Jamie %A Purse,Jeffrey %A Szwec,Stuart %A Sanson-Fisher,Robert %A Leigh,Lucy %A Richer,Mike %A Morrison,Alan %K paramedicine %K cardiopulmonary resuscitation %K clinical simulation %K professional development %K manikins %K effectiveness %K technology %K paramedics %K patient care %K simulation-based training %K deployment %D 2024 %7 24.12.2024 %9 %J JMIR Cardio %G English %X Background: Emergency medical services attend out-of-hospital cardiac arrests all across Australia. Resuscitation by emergency medical services is attempted in nearly half of all cases. However, resuscitation skills can degrade over time without adequate exposure, which negatively impacts patient survival. Consequently, for paramedics working in areas with low out-of-hospital cardiac arrest case volumes, ambulance services and professional bodies recognize the importance of alternative ways to maintain resuscitation skills. Simulation-based training via resuscitation manikins offers a potential solution for maintaining paramedic clinical practice skills. Objective: The aim of the study is to examine the effectiveness of advanced technology clinical simulation manikins and accompanying simulation resources (targeted clinical scenarios and debriefing tools) in improving the demonstrable capability of paramedics to deliver high-quality patient care, as measured by external cardiac compression (ECC) performance. Methods: A pre- and postintervention study design without a control group was used. Data were collected at the start of the manikin training forum (baseline), immediately following the training forum (time 2), and 6 to 11 months after the training forum (time 3). The study was conducted with paramedics from 95 NSW Ambulance locations (75 regional locations and 20 metropolitan locations). Eligible participants were paramedics who were employed by NSW Ambulance (N=106; 100% consent rate). As part of the intervention, paramedics attended a training session on the use of advanced technology simulation manikins. Manikins were then deployed to locations for further use. The main outcome measure was an overall compression score that was automatically recorded and calculated by the simulator manikin in 2-minute cycles. This score was derived from compressions that were fully released and with the correct hand position, adequate depth, and adequate rate. Results: A total of 106 (100% consent rate) paramedics participated, primarily representing regional ambulance locations (n= 75, 78.9%). ECC compression scores were on average 95% or above at all time points, suggesting high performance. No significant differences over time (P>.05) were identified for the overall ECC performance score, compressions fully released, compressions with adequate depth, or compressions with the correct hand position. However, paramedics had significantly lower odds (odds ratio 0.30, 95% CI 0.12-0.78) of achieving compressions with adequate rate at time 3 compared to time 2 (P=.01). Compressions were of a slower rate, with an average difference of 2.1 fewer compressions every minute. Conclusions: Despite this difference in compression rate over time, this did not cause significant detriment to overall ECC performance. Training and deployment of simulator manikins did not significantly change paramedics’ overall ECC performance. The high baseline performance (ceiling effect) of paramedics in this sample may have prevented the potential increase in skills and performance. %R 10.2196/49895 %U https://cardio.jmir.org/2024/1/e49895 %U https://doi.org/10.2196/49895 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e54823 %T Cardiac Rehabilitation During the COVID-19 Pandemic and the Potential for Digital Technology to Support Physical Activity Maintenance: Qualitative Study %A Park,Linda G %A Chi,Serena %A Pitsenbarger,Susan %A Johnson,Julene K %A Shah,Amit J %A Elnaggar,Abdelaziz %A von Oppenfeld,Julia %A Cho,Evan %A Harzand,Arash %A Whooley,Mary A %+ Department of Community Health Systems, University of California San Francisco, 2 Koret Way, Room 531A, San Francisco, CA, 94143-0610, United States, 1 415 502 6616, linda.park@ucsf.edu %K cardiac rehabilitation %K cardiac rehab %K COVID-19 %K digital health %K digital technology %K physical activity %K physical activity maintenance %K social media %K older adults %K pandemic %K social distancing %K technology %K wearables %K CR %K exercise %K cardiovascular disease %K gerontology %K geriatric %K geriatrics %K hospital %K medical facility %K California %K interview %K thematic analysis %K anxiety %D 2024 %7 14.3.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Social distancing from the COVID-19 pandemic may have decreased engagement in cardiac rehabilitation (CR) and may have had possible consequences on post-CR exercise maintenance. The increased use of technology as an adaptation may benefit post-CR participants via wearables and social media. Thus, we sought to explore the possible relationships of both the pandemic and technology on post-CR exercise maintenance. Objective: This study aimed to (1) understand CR participation during the COVID-19 pandemic, (2) identify perceived barriers and facilitators to physical activity after CR completion, and (3) assess willingness to use technology and social media to support physical activity needs among older adults with cardiovascular disease. Methods: We recruited participants aged 55 years and older in 3 different CR programs offered at both public and private hospitals in Northern California. We conducted individual interviews on CR experiences, physical activity, and potential for using technology. We used thematic analysis to synthesize the data. Results: In total, 22 participants (n=9, 41% female participants; mean age 73, SD 8 years) completed in-depth interviews. Themes from participants’ feedback included the following: (1) anxiety and frustration about the wait for CR caused by COVID-19 conditions, (2) positive and safe participant experience once in CR during the pandemic, (3) greater attention needed to patients after completion of CR, (4) notable demand for technology during the pandemic and after completion of CR, and (5) social media networking during the CR program considered valuable if training is provided. Conclusions: Individuals who completed CR identified shared concerns about continuing physical activity despite having positive experiences during the CR program. There were significant challenges during the pandemic and heightened concerns for safety and health. The idea of providing support by leveraging digital technology (wearable devices and social media for social support) resonated as a potential solution to help bridge the gap from CR to more independent physical activity. More attention is needed to help individuals experience a tailored and safe transition to home to maintain physical activity among those who complete CR. %M 38483450 %R 10.2196/54823 %U https://cardio.jmir.org/2024/1/e54823 %U https://doi.org/10.2196/54823 %U http://www.ncbi.nlm.nih.gov/pubmed/38483450 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e47730 %T Targeting Key Risk Factors for Cardiovascular Disease in At-Risk Individuals: Developing a Digital, Personalized, and Real-Time Intervention to Facilitate Smoking Cessation and Physical Activity %A Versluis,Anke %A Penfornis,Kristell M %A van der Burg,Sven A %A Scheltinga,Bouke L %A van Vliet,Milon H M %A Albers,Nele %A Meijer,Eline %+ Department of Public Health and Primary Care, Leiden University Medical Center, Albinusdreef 2, Leiden, 2333 ZA, Netherlands, 31 712568433, E.Meijer@lumc.nl %K smoking %K physical activity %K virtual coach %K eHealth %K development %K collaboration %K conversational agent %K risk factor %K cardiovascular disease %K CVD %K digital %K smoking cessation %K intervention %D 2024 %7 20.12.2024 %9 Viewpoint %J JMIR Cardio %G English %X Health care is under pressure due to an aging population with an increasing prevalence of chronic diseases, including cardiovascular disease. Smoking and physical inactivity are 2 key preventable risk factors for cardiovascular disease. Yet, as with most health behaviors, they are difficult to change. In the interdisciplinary Perfect Fit project, scientists from different fields join forces to develop an evidence-based virtual coach (VC) that supports smokers in quitting smoking and increasing their physical activity. In this Viewpoint paper, intervention content, design, and implementation, as well as lessons learned, are presented to support other research groups working on similar projects. A total of 6 different approaches were used and combined to support the development of the Perfect Fit VC. The approaches used are (1) literature reviews, (2) empirical studies, (3) collaboration with end users, (4) content and technical development sprints, (5) interdisciplinary collaboration, and (6) iterative proof-of-concept implementation. The Perfect Fit intervention integrates evidence-based behavior change techniques with new techniques focused on identity change, big data science, sensor technology, and personalized real-time coaching. Intervention content of the virtual coaching matches the individual needs of the end users. Lessons learned include ways to optimally implement and tailor interactions with the VC (eg, clearly explain why the user is asked for input and tailor the timing and frequency of the intervention components). Concerning the development process, lessons learned include strategies for effective interdisciplinary collaboration and technical development (eg, finding a good balance between end users’ wishes and legal possibilities). The Perfect Fit development process was collaborative, iterative, and challenging at times. Our experiences and lessons learned can inspire and benefit others. Advanced, evidence-based digital interventions, such as Perfect Fit, can contribute to a healthy society while alleviating health care burden. %M 39705698 %R 10.2196/47730 %U https://cardio.jmir.org/2024/1/e47730 %U https://doi.org/10.2196/47730 %U http://www.ncbi.nlm.nih.gov/pubmed/39705698 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e49515 %T Persuasive Systems Design Trends in Coronary Heart Disease Management: Scoping Review of Randomized Controlled Trials %A Agyei,Eunice Eno Yaa Frimponmaa %A Ekpezu,Akon %A Oinas-Kukkonen,Harri %+ Oulu Advanced Research on Service and Information Systems, Faculty of Information Technology and Electrical Engineering, University of Oulu, Pentti Kaiteran katu 1, Oulu, 90570, Finland, 358 0449511559, eunice.agyei@oulu.fi %K coronary heart disease %K persuasive systems design %K behavior change %K randomized controlled trial %K RCT %K controlled trials %K heart %K CHD %K cardiovascular %D 2024 %7 19.6.2024 %9 Review %J JMIR Cardio %G English %X Background: Behavior change support systems (BCSSs) have the potential to help people maintain healthy lifestyles and aid in the self-management of coronary heart disease (CHD). The Persuasive Systems Design (PSD) model is a framework for designing and evaluating systems designed to support lifestyle modifications and health behavior change using information and communication technology. However, evidence for the underlying design principles behind BCSSs for CHD has not been extensively reported in the literature. Objective: This scoping review aims to identify existing health BCSSs for CHD, report the characteristics of these systems, and describe the persuasion context and persuasive design principles of these systems based on the PSD framework. Methods: Using the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines, 3 digital databases (Scopus, Web of Science, and MEDLINE) were searched between 2010 to 2022. The major inclusion criteria for studies were in accordance with the PICO (Population, Intervention, Comparison, and Outcome) approach. Results: Searches conducted in the databases identified 1195 papers, among which 30 were identified as eligible for the review. The most interesting characteristics of the BCSSs were the predominant use of primary task support principles, followed by dialogue support and credibility support and the sparing use of social support principles. Theories of behavior change such as the Social Cognitive Theory and Self-Efficacy Theory were used often to underpin these systems. However, significant trends in the use of persuasive system features on par with behavior change theories could not be established from the reviewed studies. This points to the fact that there is still no theoretical consensus on how best to design interventions to promote behavior change in patients with CHD. Conclusions: Our results highlight key software features for designing BCSSs for the prevention and management of CHD. We encourage designers of behavior change interventions to evaluate the techniques that contributed to the success of the intervention. Future research should focus on evaluating the effectiveness of the interventions, persuasive design principles, and behavior change theories using research methodologies such as meta-analysis. %M 38896840 %R 10.2196/49515 %U https://cardio.jmir.org/2024/1/e49515 %U https://doi.org/10.2196/49515 %U http://www.ncbi.nlm.nih.gov/pubmed/38896840 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e60697 %T The Role of Machine Learning in the Detection of Cardiac Fibrosis in Electrocardiograms: Scoping Review %A Handra,Julia %A James,Hannah %A Mbilinyi,Ashery %A Moller-Hansen,Ashley %A O'Riley,Callum %A Andrade,Jason %A Deyell,Marc %A Hague,Cameron %A Hawkins,Nathaniel %A Ho,Kendall %A Hu,Ricky %A Leipsic,Jonathon %A Tam,Roger %+ Faculty of Medicine, University of British Columbia, 2194 Health Sciences Mall, Vancouver, BC, V6T 1Z3, Canada, 1 (604) 822 2421, jhandra@student.ubc.ca %K machine learning %K cardiac fibrosis %K electrocardiogram %K ECG %K detection %K ML %K cardiovascular disease %K review %D 2024 %7 30.12.2024 %9 Review %J JMIR Cardio %G English %X Background: Cardiovascular disease remains the leading cause of mortality worldwide. Cardiac fibrosis impacts the underlying pathophysiology of many cardiovascular diseases by altering structural integrity and impairing electrical conduction. Identifying cardiac fibrosis is essential for the prognosis and management of cardiovascular disease; however, current diagnostic methods face challenges due to invasiveness, cost, and inaccessibility. Electrocardiograms (ECGs) are widely available and cost-effective for monitoring cardiac electrical activity. While ECG-based methods for inferring fibrosis exist, they are not commonly used due to accuracy limitations and the need for cardiac expertise. However, the ECG shows promise as a target for machine learning (ML) applications in fibrosis detection. Objective: This study aims to synthesize and critically evaluate the current state of ECG-based ML approaches for cardiac fibrosis detection. Methods: We conducted a scoping review of research in ECG-based ML applications to identify cardiac fibrosis. Comprehensive searches were performed in PubMed, IEEE Xplore, Scopus, Web of Science, and DBLP databases, including publications up to October 2024. Studies were included if they applied ML techniques to detect cardiac fibrosis using ECG or vectorcardiogram data and provided sufficient methodological details and outcome metrics. Two reviewers independently assessed eligibility and extracted data on the ML models used, their performance metrics, study designs, and limitations. Results: We identified 11 studies evaluating ML approaches for detecting cardiac fibrosis using ECG data. These studies used various ML techniques, including classical (8/11, 73%), ensemble (3/11, 27%), and deep learning models (4/11, 36%). Support vector machines were the most used classical model (6/11, 55%), with the best-performing models of each study achieving accuracies of 77% to 93%. Among deep learning approaches, convolutional neural networks showed promising results, with one study reporting an area under the receiver operating characteristic curve (AUC) of 0.89 when combined with clinical features. Notably, a large-scale convolutional neural network study (n=14,052) achieved an AUC of 0.84 for detecting cardiac fibrosis, outperforming cardiologists (AUC 0.63-0.66). However, many studies had limited sample sizes and lacked external validation, potentially impacting the generalizability of the findings. Variability in reporting methods may affect the reproducibility and applicability of these ML-based approaches. Conclusions: ML-augmented ECG analysis shows promise for accessible and cost-effective detection of cardiac fibrosis. However, there are common limitations with respect to study design and insufficient external validation, raising concerns about the generalizability and clinical applicability of the findings. Inconsistencies in methodologies and incomplete reporting further impede cross-study comparisons. Future work may benefit from using prospective study designs, larger and more clinically and demographically diverse datasets, advanced ML models, and rigorous external validation. Addressing these challenges could pave the way for the clinical implementation of ML-based ECG detection of cardiac fibrosis to improve patient outcomes and health care resource allocation. %M 39753213 %R 10.2196/60697 %U https://cardio.jmir.org/2024/1/e60697 %U https://doi.org/10.2196/60697 %U http://www.ncbi.nlm.nih.gov/pubmed/39753213 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e55958 %T The Role of Clinician-Developed Applications in Promoting Adherence to Evidence-Based Guidelines: Pilot Study %A Prakash,Madhu Prita %A Thiagalingam,Aravinda %K computerized clinical decision support systems %K acute coronary syndrome %K clinical guidelines %K chest pain pathway %K decision support %K coronary %K heart %K cardiac %K cardiology %K chest %K pain %K web-based %K app %K applications %K computerized %K guideline %K emergency %K usability %D 2024 %7 31.12.2024 %9 %J JMIR Cardio %G English %X Background: Computerized clinical decision support systems (CDSS) are increasingly being used in clinical practice to improve health care delivery. Mobile apps are a type of CDSS that are currently being increasingly used, particularly in lifestyle interventions and disease prevention. However, the use of such apps in acute patient care, diagnosis, and management has not been studied to a great extent. The Pathway for Acute Coronary Syndrome Assessment (PACSA) is a set of guidelines developed to standardize the management of suspected acute coronary syndrome across emergency departments in New South Wales, Australia. These guidelines, which risk stratify patients and provide an appropriate management plan, are currently available as PDF documents or physical paper-based PACSA documents. The routine use of these documents and their acceptability among clinicians is uncertain. Presenting the PACSA guidelines on a mobile app in a sequential format may be a more acceptable alternative to the current paper-based PACSA documents. Objective: This study aimed to assess the utility and acceptability of a clinician-developed app modeling the PACSA guidelines as an alternative to the existing paper-based PACSA documents in assessing chest pain presentations to the emergency department. Methods: An app modeling the PACSA guidelines was created using the Research Electronic Data Capture (REDCap) platform by a cardiologist, with a total development time of <3 hours. The app utilizes a sequential design, requiring participants to input patient data in a step-wise fashion to reach the final patient risk stratification. Emergency department doctors were asked to use the app and apply it to two hypothetical patient scenarios. Participants then completed a survey to assess if the PACSA app offered any advantages over the current paper-based PACSA documents Results: Participants (n=31) ranged from junior doctors to senior physicians. Current clinician adherence to the paper-based PACSA documents was low with 55% (N=17) never using it in their daily practice. Totally, 42% of participants found the PACSA app easier to use compared to the paper-based PACSA documents and 58% reported that the PACSA app was also faster to use. The perceived usefulness of the PACSA app was similar to the perceived usefulness of the paper-based PACSA documents. Conclusions: The PACSA app offers a more efficient and user-friendly alternative to the current paper-based PACSA documents and may promote clinician adherence to evidence-based guidelines. Additional studies with a larger number of participants are required to assess the transferability of the PACSA app to everyday practice. Furthermore, apps are relatively easy to develop using existing online platforms, with the scope for clinicians to develop such apps for other evidence-based guidelines and across different specialties. %R 10.2196/55958 %U https://cardio.jmir.org/2024/1/e55958 %U https://doi.org/10.2196/55958 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e52266 %T Impact of an mHealth App (Kencom) on Patients With Untreated Hypertension Initiating Antihypertensive Medications: Real-World Cohort Study %A Matsumura,Koichiro %A Nakagomi,Atsushi %A Yagi,Eijiro %A Yamada,Nobuhiro %A Funauchi,Yohei %A Kakehi,Kazuyoshi %A Yoshida,Ayano %A Kawamura,Takayuki %A Ueno,Masafumi %A Nakazawa,Gaku %A Tabuchi,Takahiro %K untreated hypertension %K mobile health app %K antihypertensive medication %K cardiovascular disease %K mHealth %D 2024 %7 26.11.2024 %9 %J JMIR Cardio %G English %X Background: To prevent the further development of cardiovascular diseases, it is a growing global priority to detect untreated hypertension in patients and ensure adequate blood pressure control via drug therapy. However, few effective tools that facilitate the initiation of antihypertensive medications among such patients have been identified. Objective: We aimed to determine whether a mobile health (mHealth) app facilitates the initiation of antihypertensive medications among patients with untreated hypertension. Methods: We analyzed a large longitudinal integrated database mainly comprised of data from middle-aged, employed people and their families. The database contained data from health checkups, health insurance claims, and the mHealth app kencom. kencom is used to manage daily life logs (eg, weight, number of steps) and to provide health information tailored to customers. Patients with untreated hypertension were identified using the baseline health checkup data, and follow-up health checkups were conducted to identify the rate of initiation of antihypertensive medications between mHealth app users and nonusers. Antihypertensive medication status was confirmed via a questionnaire administered during the medical checkup as well as a review of the health insurance claims database. We conducted a modified Poisson regression analysis, weighted by inverse probability of treatment weighting, to examine the effect of mHealth app usage on the initiation of antihypertensive medications. Additionally, data from four lifestyle questionnaires from the baseline and follow-up health checkups were collected to evaluate lifestyle modifications that could be attributed to the mHealth app. Results: Data were collected from 50,803 eligible patients (mean age 49, SD 9 years; men n=39,412, 77.6%; women n=11,391, 22.4%) with a median follow-up period of 3.0 (IQR 2.3‐3.1) years. The rate of initiation of antihypertensive medications was significantly higher in the mHealth app user group than in the nonuser group: 23.4% (3482/14,879) versus 18.5% (6646/35,924; P<.001), respectively. The risk ratio of mHealth app usage for initiated antihypertensive medications was 1.28 (95% CI 1.23‐1.33). Among those who did not intend to improve their lifestyle habits such as exercise and diet at baseline, the rate of lifestyle improvement at follow-up was compared between mHealth app users and nonusers, using data from the questionnaires; mHealth app users demonstrated a significantly higher rate of lifestyle changes than nonusers. Conclusions: For patients with untreated hypertension, the use of the mHealth app kencom, which was not dedicated to hypertension treatment, was associated with a higher initiation of antihypertensive medications. %R 10.2196/52266 %U https://cardio.jmir.org/2024/1/e52266 %U https://doi.org/10.2196/52266 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e54530 %T Feasibility of Using Text Messaging to Identify and Assist Patients With Hypertension With Health-Related Social Needs: Cross-Sectional Study %A Kormanis,Aryn %A Quinones,Selina %A Obermiller,Corey %A Denizard-Thompson,Nancy %A Palakshappa,Deepak %+ Department of Internal Medicine, Wake Forest University School of Medicine, Medical Center Blvd, Winston Salem, NC, 27157, United States, 1 3367161795, dpalaksh@wakehealth.edu %K social determinants of health %K health-related social needs %K mobile health %K health information technology %K feasibility %K mobile phone %K SMS text messaging %K message %K pilot study %K patients %K patient %K hypertension %K screening %D 2024 %7 13.2.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Health-related social needs are associated with poor health outcomes, increased acute health care use, and impaired chronic disease management. Given these negative outcomes, an increasing number of national health care organizations have recommended that the health system screen and address unmet health-related social needs as a routine part of clinical care, but there are limited data on how to implement social needs screening in clinical settings to improve the management of chronic diseases such as hypertension. SMS text messaging could be an effective and efficient approach to screen patients; however, there are limited data on the feasibility of using it. Objective: We conducted a cross-sectional study of patients with hypertension to determine the feasibility of using SMS text messaging to screen patients for unmet health-related social needs. Methods: We randomly selected 200 patients (≥18 years) from 1 academic health system. Patients were included if they were seen at one of 17 primary care clinics that were part of the academic health system and located in Forsyth County, North Carolina. We limited the sample to patients seen in one of these clinics to provide tailored information about local community-based resources. To ensure that the participants were still patients within the clinic, we only included those who had a visit in the previous 3 months. The SMS text message included a link to 6 questions regarding food, housing, and transportation. Patients who screened positive and were interested received a subsequent message with information about local resources. We assessed the proportion of patients who completed the questions. We also evaluated for the differences in the demographics between patients who completed the questions and those who did not using bivariate analyses. Results: Of the 200 patients, the majority were female (n=109, 54.5%), non-Hispanic White (n=114, 57.0%), and received commercial insurance (n=105, 52.5%). There were no significant differences in demographics between the 4446 patients who were eligible and the 200 randomly selected patients. Of the 200 patients included, the SMS text message was unable to be delivered to 9 (4.5%) patients and 17 (8.5%) completed the social needs questionnaire. We did not observe a significant difference in the demographic characteristics of patients who did versus did not complete the questionnaire. Of the 17, a total of 5 (29.4%) reported at least 1 unmet need, but only 2 chose to receive resource information. Conclusions: We found that only 8.5% (n=17) of patients completed a SMS text message–based health-related social needs questionnaire. SMS text messaging may not be feasible as a single modality to screen patients in this population. Future research should evaluate if SMS text message–based social needs screening is feasible in other populations or effective when paired with other screening modalities. %M 38349714 %R 10.2196/54530 %U https://cardio.jmir.org/2024/1/e54530 %U https://doi.org/10.2196/54530 %U http://www.ncbi.nlm.nih.gov/pubmed/38349714 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e53696 %T Metaphor Diffusion in Online Health Communities: Infodemiology Study in a Stroke Online Health Community %A Khoshnaw,Sara %A Panzarasa,Pietro %A De Simoni,Anna %K online health community %K social capital %K metaphor %K stroke %K OHC %K novelty %K passive analysis %K stroke survivor %K self-promotion %K post-stroke %K information diffusion %D 2024 %7 17.12.2024 %9 %J JMIR Cardio %G English %X Background: Online health communities (OHCs) enable patients to create social ties with people with similar health conditions outside their existing social networks. Harnessing mechanisms of information diffusion in OHCs has attracted attention for its ability to improve illness self-management without the use of health care resources. Objective: We aimed to analyze the novelty of a metaphor used for the first time in an OHC, assess how it can facilitate self-management of post-stroke symptoms, describe its appearance over time, and classify its diffusion mechanisms. Methods: We conducted a passive analysis of posts written by UK stroke survivors and their family members in an online stroke community between 2004 and 2011. Posts including the term “legacy of stroke” were identified. Information diffusion was classified according to self-promotion or viral spread mechanisms and diffusion depth (the number of users the information spreads out to). Linguistic analysis was performed through the British National Corpus and the Google search engine. Results: Post-stroke symptoms were referred to as “legacy of stroke.” This metaphor was novel and appeared for the first time in the OHC in the second out of a total of 3459 threads. The metaphor was written by user A, who attributed it to a stroke consultant explaining post-stroke fatigue. This user was a “superuser” (ie, a user with high posting activity) and self-promoted the metaphor throughout the years in response to posts written by other users, in 51 separate threads. In total, 7 users subsequently used the metaphor, contributing to its viral diffusion, of which 3 were superusers themselves. Superusers achieved the higher diffusion depths (maximum of 3). Of the 7 users, 3 had been part of threads where user A mentioned the metaphor, while 2 users had been part of discussion threads in unrelated conversations. In total, 2 users had not been part of threads with any of the other users, suggesting that the metaphor was acquired through prior lurking activity. Conclusions: Metaphors that are considered helpful by patients with stroke to come to terms with their symptoms can diffuse in OHCs through both self-promotion and social (or viral) spreading, with the main driver of diffusion being the superuser trait. Lurking activity (the most common behavior in OHCs) contributed to the diffusion of information. As an increasing number of patients with long-term conditions join OHCs to find others with similar health-related concerns, improving clinicians’ and researchers’ awareness of the diffusion of metaphors that facilitate self-management in health social media may be beneficial beyond the individual patient. %R 10.2196/53696 %U https://cardio.jmir.org/2024/1/e53696 %U https://doi.org/10.2196/53696 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e49590 %T Comparing the Efficacy of Targeted and Blast Portal Messaging in Message Opening Rate and Anticoagulation Initiation in Patients With Atrial Fibrillation in the Preventing Preventable Strokes Study II: Prospective Cohort Study %A Kapoor,Alok %A Patel,Parth %A Chennupati,Soumya %A Mbusa,Daniel %A Sadiq,Hammad %A Rampam,Sanjeev %A Leung,Robert %A Miller,Megan %A Vargas,Kevin Rivera %A Fry,Patrick %A Lowe,Mary Martin %A Catalano,Christina %A Harrison,Charles %A Catanzaro,John Nicholas %A Crawford,Sybil %A Smith,Anne Marie %+ University of Massachusetts Chan Medical School, 55 N Lake Ave, Worcester, MA, 01655, United States, 1 9178564538, alok.kapoor@umassmemorial.org %K anticoagulants %K atrial fibrillation %K humans %K outpatients %K patient education as topic %K patient portals %D 2024 %7 24.1.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: The gap in anticoagulation use among patients with atrial fibrillation (AF) is a major public health threat. Inadequate patient education contributes to this gap. Patient portal–based messaging linked to educational materials may help bridge this gap, but the most effective messaging approach is unknown. Objective: This study aims to compare the responsiveness of patients with AF to an AF or anticoagulation educational message between 2 portal messaging approaches: sending messages targeted at patients with upcoming outpatient appointments 1 week before their scheduled appointment (targeted) versus sending messages to all eligible patients in 1 blast, regardless of appointment scheduling status (blast), at 2 different health systems: the University of Massachusetts Chan Medical School (UMass) and the University of Florida College of Medicine-Jacksonville (UFL). Methods: Using the 2 approaches, we sent patient portal messages to patients with AF and grouped patients by high-risk patients on anticoagulation (group 1), high-risk patients off anticoagulation (group 2), and low-risk patients who may become eligible for anticoagulation in the future (group 3). Risk was classified based on the congestive heart failure, hypertension, age ≥75 years, diabetes mellitus, stroke, vascular disease, age between 65 and 74 years, and sex category (CHA2DS2-VASc) score. The messages contained a link to the Upbeat website of the Heart Rhythm Society, which displays print and video materials about AF and anticoagulation. We then tracked message opening, review of the website, anticoagulation use, and administered patient surveys across messaging approaches and sites using Epic Systems (Epic Systems Corporation) electronic health record data and Google website traffic analytics. We then conducted chi-square tests to compare potential differences in the proportion of patients opening messages and other evaluation metrics, adjusting for potential confounders. All statistical analyses were performed in SAS (version 9.4; SAS Institute). Results: We sent 1686 targeted messages and 1450 blast messages. Message opening was significantly higher with the targeted approach for patients on anticoagulation (723/1156, 62.5% vs 382/668, 57.2%; P=.005) and trended the same in patients off anticoagulation; subsequent website reviews did not differ by messaging approach. More patients off anticoagulation at baseline started anticoagulation with the targeted approach than the blast approach (adjusted percentage 9.3% vs 2.1%; P<.001). Conclusions: Patients were more responsive in terms of message opening and subsequent anticoagulation initiation with the targeted approach. %M 38265849 %R 10.2196/49590 %U https://cardio.jmir.org/2024/1/e49590 %U https://doi.org/10.2196/49590 %U http://www.ncbi.nlm.nih.gov/pubmed/38265849 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e57058 %T Analysis of Demographic and Socioeconomic Factors Influencing Adherence to a Web-Based Intervention Among Patients After Acute Coronary Syndrome: Prospective Observational Cohort Study %A Sassone,Biagio %A Fuca',Giuseppe %A Pedaci,Mario %A Lugli,Roberta %A Bertagnin,Enrico %A Virzi',Santo %A Bovina,Manuela %A Pasanisi,Giovanni %A Mandini,Simona %A Myers,Jonathan %A Tolomeo,Paolo %+ Division of Provincial Cardiology, Department of Translational Medicine, University of Ferrara, Via Savonarola, 9, Ferrara, 44121, Italy, 39 0516838219, biagio.sassone@unife.it %K telemedicine %K digital literacy %K digital health %K acute coronary syndrome %K older age %K caregiver %K socioeconomic %K educational %K mobile phone %D 2024 %7 2.8.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Although telemedicine has been proven to have significant potential for improving care for patients with cardiac problems, there remains a substantial risk of introducing disparities linked to the use of digital technology, especially for older or socially vulnerable subgroups. Objective: We investigated factors influencing adherence to a telemedicine-delivered health education intervention in patients with ischemia, emphasizing demographic and socioeconomic considerations. Methods: We conducted a descriptive, observational, prospective cohort study in consecutive patients referred to our cardiology center for acute coronary syndrome, from February 2022 to January 2023. Patients were invited to join a web-based health educational meeting (WHEM) after hospital discharge, as part of a secondary prevention program. The WHEM sessions were scheduled monthly and used a teleconference software program for remote synchronous videoconferencing, accessible through a standard computer, tablet, or smartphone based on patient preference or availability. Results: Out of the 252 patients (median age 70, IQR 61.0-77.3 years; n=189, 75% male), 98 (38.8%) declined the invitation to participate in the WHEM. The reasons for nonacceptance were mainly challenges in handling digital technology (70/98, 71.4%), followed by a lack of confidence in telemedicine as an integrative tool for managing their medical condition (45/98, 45.9%), and a lack of internet-connected devices (43/98, 43.8%). Out of the 154 patients who agreed to participate in the WHEM, 40 (25.9%) were unable to attend. Univariable logistic regression analysis showed that the presence of a caregiver with digital proficiency and a higher education level was associated with an increased likelihood of attendance to the WHEM, while the converse was true for increasing age and female sex. After multivariable adjustment, higher education level (odds ratio [OR] 2.26, 95% CI 1.53-3.32; P<.001) and caregiver with digital proficiency (OR 12.83, 95% CI 5.93-27.75; P<.001) remained independently associated with the outcome. The model discrimination was good even when corrected for optimism (optimism-corrected C-index=0.812), as was the agreement between observed and predicted probability of participation (optimism-corrected calibration intercept=0.010 and slope=0.948). Conclusions: This study identifies a notable lack of suitability for a specific cohort of patients with ischemia to participate in our telemedicine intervention, emphasizing the risk of digital marginalization for a significant portion of the population. Addressing low digital literacy rates among patients or their informal caregivers and overcoming cultural bias against remote care were identified as critical issues in our study findings to facilitate the broader adoption of telemedicine as an inclusive tool in health care. %M 38912920 %R 10.2196/57058 %U https://cardio.jmir.org/2024/1/e57058 %U https://doi.org/10.2196/57058 %U http://www.ncbi.nlm.nih.gov/pubmed/38912920 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e51399 %T Physical Activity, Heart Rate Variability, and Ventricular Arrhythmia During the COVID-19 Lockdown: Retrospective Cohort Study %A Texiwala,Sikander Z %A de Souza,Russell J %A Turner,Suzette %A Singh,Sheldon M %+ Schulich Heart Center, Sunnybrook Health Sciences, Room A222, 2075 Bayview Ave, Toronto, ON, M4N 3M5, Canada, 1 416 480 6100 ext 86359, sheldon.singh@sunnybrook.ca %K implantable cardioverter defibrillator %K heart rate variability %K physical activity %K lockdown %K ICD %K ventricular arrhythmias %K defibrillator %K implementation %D 2024 %7 5.2.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Ventricular arrhythmias (VAs) increase with stress and national disasters. Prior research has reported that VA did not increase during the onset of the COVID-19 lockdown in March 2020, and the mechanism for this is unknown. Objective: This study aimed to report the presence of VA and changes in 2 factors associated with VA (physical activity and heart rate variability [HRV]) at the onset of COVID-19 lockdown measures in Ontario, Canada. Methods: Patients with implantable cardioverter defibrillator (ICD) followed at a regional cardiac center in Ontario, Canada with data available for both HRV and physical activity between March 1 and 31, 2020, were included. HRV, physical activity, and the presence of VA were determined during the pre- (March 1-10, 2020) and immediate postlockdown (March 11-31) period. When available, these data were determined for the same period in 2019. Results: In total, 68 patients had complete data for 2020, and 40 patients had complete data for 2019. Three (7.5%) patients had VA in March 2019, whereas none had VA in March 2020 (P=.048). Physical activity was reduced during the postlockdown period (mean 2.3, SD 1.6 hours vs mean 2.1, SD 1.6 hours; P=.003). HRV was unchanged during the pre- and postlockdown period (mean 91, SD 30 ms vs mean 92, SD 28 ms; P=.84). Conclusions: VA was infrequent during the COVID-19 pandemic. A reduction in physical activity with lockdown maneuvers may explain this observation. %M 38315512 %R 10.2196/51399 %U https://cardio.jmir.org/2024/1/e51399 %U https://doi.org/10.2196/51399 %U http://www.ncbi.nlm.nih.gov/pubmed/38315512 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e52576 %T User Engagement, Acceptability, and Clinical Markers in a Digital Health Program for Nonalcoholic Fatty Liver Disease: Prospective, Single-Arm Feasibility Study %A Björnsdottir,Sigridur %A Ulfsdottir,Hildigunnur %A Gudmundsson,Elias Freyr %A Sveinsdottir,Kolbrun %A Isberg,Ari Pall %A Dobies,Bartosz %A Akerlie Magnusdottir,Gudlaug Erla %A Gunnarsdottir,Thrudur %A Karlsdottir,Tekla %A Bjornsdottir,Gudlaug %A Sigurdsson,Sigurdur %A Oddsson,Saemundur %A Gudnason,Vilmundur %+ Department of Endocrinology, Metabolism and Diabetes, Karolinska Institutet, Solnavägen 1, Stockholm, 171 77, Sweden, 46 8 524 800 00, sigridur.bjornsdottir@ki.se %K digital health program %K nonalcoholic fatty liver disease %K NAFLD %K cardiometabolic health %K digital therapeutics %K liver %K chronic %K hepatic %K cardiometabolic %K cardiovascular %K cardiology %K weight %K acceptability %K digital health %K metabolic syndrome %K diabetic %K diabetes %K diabetics %K type 2 %K BMI %K lifestyle %K exercise %K physical activity %K coaching %K diet %K dietary %K nutrition %K nutritional %K patient education %K coach %K feasibility %K fat %K body composition %D 2024 %7 15.2.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Nonalcoholic fatty liver disease (NAFLD) has become the most common chronic liver disease in the world. Common comorbidities are central obesity, type 2 diabetes mellitus, dyslipidemia, and metabolic syndrome. Cardiovascular disease is the most common cause of death among people with NAFLD, and lifestyle changes can improve health outcomes. Objective: This study aims to explore the acceptability of a digital health program in terms of engagement, retention, and user satisfaction in addition to exploring changes in clinical outcomes, such as weight, cardiometabolic risk factors, and health-related quality of life. Methods: We conducted a prospective, open-label, single-arm, 12-week study including 38 individuals with either a BMI >30, metabolic syndrome, or type 2 diabetes mellitus and NAFLD screened by FibroScan. An NAFLD-specific digital health program focused on disease education, lowering carbohydrates in the diet, food logging, increasing activity level, reducing stress, and healthy lifestyle coaching was offered to participants. The coach provided weekly feedback on food logs and other in-app activities and opportunities for participants to ask questions. The coaching was active throughout the 12-week intervention period. The primary outcome was feasibility and acceptability of the 12-week program, assessed through patient engagement, retention, and satisfaction with the program. Secondary outcomes included changes in weight, liver fat, body composition, and other cardiometabolic clinical parameters at baseline and 12 weeks. Results: In total, 38 individuals were included in the study (median age 59.5, IQR 46.3-68.8 years; n=23, 61% female). Overall, 34 (89%) participants completed the program and 29 (76%) were active during the 12-week program period. The median satisfaction score was 6.3 (IQR 5.8-6.7) of 7. Mean weight loss was 3.5 (SD 3.7) kg (P<.001) or 3.2% (SD 3.4%), with a 2.2 (SD 2.7) kg reduction in fat mass (P<.001). Relative liver fat reduction was 19.4% (SD 23.9%). Systolic blood pressure was reduced by 6.0 (SD 13.5) mmHg (P=.009). The median reduction was 0.14 (IQR 0-0.47) mmol/L for triglyceride levels (P=.003), 3.2 (IQR 0.0-5.4) µU/ml for serum insulin (s-insulin) levels (P=.003), and 0.5 (IQR –0.7 to 3.8) mmol/mol for hemoglobin A1c (HbA1c) levels (P=.03). Participants who were highly engaged (ie, who used the app at least 5 days per week) had greater weight loss and liver fat reduction. Conclusions: The 12-week-long digital health program was feasible for individuals with NAFLD, receiving high user engagement, retention, and satisfaction. Improved liver-specific and cardiometabolic health was observed, and more engaged participants showed greater improvements. This digital health program could provide a new tool to improve health outcomes in people with NAFLD. Trial Registration: Clinicaltrials.gov NCT05426382; https://clinicaltrials.gov/study/NCT05426382 %M 38152892 %R 10.2196/52576 %U https://cardio.jmir.org/2024/1/e52576 %U https://doi.org/10.2196/52576 %U http://www.ncbi.nlm.nih.gov/pubmed/38152892 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e57241 %T Contactless and Calibration-Free Blood Pressure and Pulse Rate Monitor for Screening and Monitoring of Hypertension: Cross-Sectional Validation Study %A Kapoor,Melissa %A Holman,Blair %A Cohen,Carolyn %+ Mind over Matter Medtech Ltd, Kemp House, 160 City Road, London, EC1V 2NX, United Kingdom, 44 07881 927063, melissa@mind-medtech.com %K remote photoplethysmography %K vital signs %K calibration-free blood pressure monitor %K medical device %K hypertension screening %K home blood pressure monitoring %K vital %K vitals %K device %K devices %K hypertension %K hypertensive %K cardiovascular %K cardiology %K heart %K blood pressure %K monitoring %K monitor %K mHealth %K mobile health %K validation %D 2024 %7 5.8.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: The key to reducing the immense morbidity and mortality burdens of cardiovascular diseases is to help people keep their blood pressure (BP) at safe levels. This requires that more people with hypertension be identified, diagnosed, and given tools to lower their BP. BP monitors are critical to hypertension diagnosis and management. However, there are characteristics of conventional BP monitors (oscillometric cuff sphygmomanometers) that hinder rapid and effective hypertension diagnosis and management. Calibration-free, software-only BP monitors that operate on ubiquitous mobile devices can enable on-demand BP monitoring, overcoming the hardware barriers of conventional BP monitors. Objective: This study aims to investigate the accuracy of a contactless BP monitor software app for classifying the full range of clinically relevant BPs as hypertensive or nonhypertensive and to evaluate its accuracy for measuring the pulse rate (PR) and BP of people with BPs relevant to stage-1 hypertension. Methods: The software app, known commercially as Lifelight, was investigated following the data collection and data analysis methodology outlined in International Organization for Standardization (ISO) 81060-2:2018/AMD 1:2020 “Non-invasive Sphygmomanometers—Part 2: Clinical investigation of automated measurement type.” This validation study was conducted by the independent laboratory Element Materials Technology Boulder (formerly Clinimark). The study generated data from 85 people aged 18-85 years with a wide-ranging distribution of BPs specified in ISO 81060-2:2018/AMD 1:2020. At least 20% were required to have Fitzpatrick scale skin tones of 5 or 6 (ie, dark skin tones). The accuracy of the app’s BP measurements was assessed by comparing its BP measurements with measurements made by dual-observer manual auscultation using the same-arm sequential method specified in ISO 81060-2:2018/AMD 1:2020. The accuracy of the app’s PR measurements was assessed by comparing its measurements with concurrent electroencephalography-derived heart rate values. Results: The app measured PR with an accuracy root-mean-square of 1.3 beats per minute and mean absolute error of 1.1 (SD 0.8) beats per minute. The sensitivity and specificity with which it determined that BPs exceeded the in-clinic systolic threshold for hypertension diagnosis were 70.1% and 71.7%, respectively. These rates are consistent with those reported for conventional BP monitors in a literature review by The National Institute for Health and Care Excellence. The app’s mean error for measuring BP in the range of normotension and stage-1 hypertension (ie, 65/85, 76% of participants) was 6.5 (SD 12.9) mm Hg for systolic BP and 0.4 (SD 10.6) mm Hg for diastolic BP. Mean absolute error was 11.3 (SD 10.0) mm Hg and 8.6 (SD 6.8) mm Hg, respectively. Conclusions: A calibration-free, software-only medical device was independently tested against ISO 81060-2:2018/AMD 1:2020. The safety and performance demonstrated in this study suggest that this technique could be a potential solution for rapid and scalable screening and management of hypertension. %M 39102277 %R 10.2196/57241 %U https://cardio.jmir.org/2024/1/e57241 %U https://doi.org/10.2196/57241 %U http://www.ncbi.nlm.nih.gov/pubmed/39102277 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e68825 %T Correction: Cloud-Based Machine Learning Platform to Predict Clinical Outcomes at Home for Patients With Cardiovascular Conditions Discharged From Hospital: Clinical Trial %A Yang,Phillip C %A Jha,Alokkumar %A Xu,William %A Song,Zitao %A Jamp,Patrick %A Teuteberg,Jeffrey J %+ Stanford University School of Medicine, 300 Pasteur Dr # H2157 Stanford, Palo Alto, CA, 94305-2200, United States, 1 6508048828, phillip@stanford.edu %D 2024 %7 10.12.2024 %9 Corrigenda and Addenda %J JMIR Cardio %G English %X %M 39658002 %R 10.2196/68825 %U https://cardio.jmir.org/2024/1/e68825 %U https://doi.org/10.2196/68825 %U http://www.ncbi.nlm.nih.gov/pubmed/39658002 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e53815 %T Cognitive Behavioral Therapy for Symptom Preoccupation Among Patients With Premature Ventricular Contractions: Nonrandomized Pretest-Posttest Study %A Liliequist,Björn E %A Särnholm,Josefin %A Skúladóttir,Helga %A Ólafsdóttir,Eva %A Ljótsson,Brjánn %A Braunschweig,Frieder %+ Department of Clinical Neuroscience, Division of Psychology, Karolinska Institutet, Nobels väg 9, Stockholm, 171 65, Sweden, 46 08 524 800 00, bjorn.liliequist@ki.se %K premature ventricular contractions %K quality of life %K symptom preoccupation %K cognitive behavioral therapy: CBT %D 2024 %7 7.5.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Premature ventricular contractions (PVCs) are a common cardiac condition often associated with disabling symptoms and impaired quality of life (QoL). Current treatment strategies have limited effectiveness in reducing symptoms and restoring QoL for patients with PVCs. Symptom preoccupation, involving cardiac-related fear, hypervigilance, and avoidance behavior, is associated with disability in other cardiac conditions and can be effectively targeted by cognitive behavioral therapy (CBT). Objective: The aim of this study was to evaluate the effect of a PVC-specific CBT protocol targeting symptom preoccupation in patients with symptomatic idiopathic PVCs. Methods: Nineteen patients diagnosed with symptomatic idiopathic PVCs and symptom preoccupation underwent PVC-specific CBT over 10 weeks. The treatment was delivered by a licensed psychologist via videoconference in conjunction with online text-based information and homework assignments. The main components of the treatment were exposure to cardiac-related symptoms and reducing cardiac-related avoidance and control behavior. Self-rated measures were collected at baseline, post treatment, and at 3- and 6-month follow-ups. The primary outcome was PVC-specific QoL at posttreatment assessment measured with a PVC-adapted version of the Atrial Fibrillation Effects on Quality of Life questionnaire. Secondary measures included symptom preoccupation measured with the Cardiac Anxiety Questionnaire. PVC burden was evaluated with 5-day continuous electrocardiogram recordings at baseline, post treatment, and 6-month follow-up. Results: We observed large improvements in PVC-specific QoL (Cohen d=1.62, P<.001) and symptom preoccupation (Cohen d=1.73, P<.001) post treatment. These results were sustained at the 3- and 6-month follow-ups. PVC burden, as measured with 5-day continuous electrocardiogram, remained unchanged throughout follow-up. However, self-reported PVC symptoms were significantly lower at posttreatment assessment and at both the 3- and 6-month follow-ups. Reduction in symptom preoccupation had a statistically significant mediating effect of the intervention on PVC-specific QoL in an explorative mediation analysis. Conclusions: This uncontrolled pilot study shows preliminary promising results for PVC-specific CBT as a potentially effective treatment approach for patients with symptomatic idiopathic PVCs and symptom preoccupation. The substantial improvements in PVC-specific QoL and symptom preoccupation, along with the decreased self-reported PVC-related symptoms warrant further investigation in a larger randomized controlled trial. Trial Registration: ClinicalTrials.gov NCT05087238; https://clinicaltrials.gov/study/NCT05087238 %M 38713500 %R 10.2196/53815 %U https://cardio.jmir.org/2024/1/e53815 %U https://doi.org/10.2196/53815 %U http://www.ncbi.nlm.nih.gov/pubmed/38713500 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e56848 %T The Effect of Inhaled Beta-2 Agonists on Heart Rate in Patients With Asthma: Sensor-Based Observational Study %A Khusial,Rishi Jayant %A Sont,Jacob K %A Usmani,Omar S %A Bonini,Matteo %A Chung,Kian Fan %A Fowler,Stephen James %A Honkoop,Persijn J %+ Department of Biomedical Data Sciences, Leiden University Medical Center, Albinusdreef 2, Leiden, 2333 ZA, Netherlands, 31 715261319, r.j.khusial@lumc.nl %K asthma %K mHealth %K side effects %K beta-2 agonists %K inhaler medication %K heart rate %K sensor %K observational study %K asthma management %K cardiac cells %K monitoring %K Fitbit %K inhaler %D 2024 %7 11.12.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Beta-2 agonists play an important role in the management of asthma. Inhaled long-acting beta-2 agonists (LABAs) and short-acting beta-2 agonists (SABAs) cause bronchodilation by stimulating adrenoceptors. These receptors are also present in cardiac cells and, as a side effect, could also be stimulated by inhaled beta-2 agonists. Objective: This study aims to assess the effect of beta-2 agonists on heart rate (HR). Methods: The data were retrieved from an observational study, the myAirCoach Quantification Campaign. Beta-2 agonist use was registered by self-reported monthly questionnaires and by smart inhalers. HR was monitored continuously with the Fitbit Charge HR tracker (Fitbit Inc). Patients (aged 18 years and older) were recruited if they had uncontrolled asthma and used inhalation medication. Our primary outcome was the difference in HR between LABA and non-LABA users. Secondary outcomes were the difference in HR on days SABAs were used compared to days SABAs were not used and an assessment of the timing of inhaler use during the day. Results: Patients using LABA did not have a clinically relevant higher HR (average 0.8 beats per minute difference) during the day. Around the moment of SABA inhalation itself, the HR does increase steeply, and it takes 138 minutes before it returns to the normal range. Conclusions: This study indicates that LABAs do not have a clinically relevant effect on HR. SABAs are instead associated with a short-term HR increase. Trial Registration: ClinicalTrials.gov NCT02774772; https://clinicaltrials.gov/study/NCT02774772 %M 39661964 %R 10.2196/56848 %U https://cardio.jmir.org/2024/1/e56848 %U https://doi.org/10.2196/56848 %U http://www.ncbi.nlm.nih.gov/pubmed/39661964 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e51439 %T Factors That Influence Patient Satisfaction With the Service Quality of Home-Based Teleconsultation During the COVID-19 Pandemic: Cross-Sectional Survey Study %A Meng,Guangxia %A McAiney,Carrie %A McKillop,Ian %A Perlman,Christopher M %A Tsao,Shu-Feng %A Chen,Helen %+ School of Public Health Sciences, University of Walterloo, 200 University Ave W, Waterloo, ON, N2L 3G1, Canada, 1 519 888 4567 ext 42131, helen.chen@uwaterloo.ca %K teleconsultation %K secondary stroke prevention %K telemedicine %K service quality %K patient satisfaction %D 2024 %7 16.2.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Ontario stroke prevention clinics primarily held in-person visits before the COVID-19 pandemic and then had to shift to a home-based teleconsultation delivery model using telephone or video to provide services during the pandemic. This change may have affected service quality and patient experiences. Objective: This study seeks to understand patient satisfaction with Ontario stroke prevention clinics’ rapid shift to a home-based teleconsultation delivery model used during the COVID-19 pandemic. The research question explores explanatory factors affecting patient satisfaction. Methods: Using a cross-sectional service performance model, we surveyed patients who received telephone or video consultations at 2 Ontario stroke prevention clinics in 2021. This survey included closed- and open-ended questions. We used logistic regression and qualitative content analysis to understand factors affecting patient satisfaction with the quality of home-based teleconsultation services. Results: The overall response rate to the web survey was 37.2% (128/344). The quantitative analysis was based on 110 responses, whereas the qualitative analysis included 97 responses. Logistic regression results revealed that responsiveness (adjusted odds ratio [AOR] 0.034, 95% CI 0.006-0.188; P<.001) and empathy (AOR 0.116, 95% CI 0.017-0.800; P=.03) were significant factors negatively associated with low satisfaction (scores of 1, 2, or 3 out of 5). The only characteristic positively associated with low satisfaction was when survey consent was provided by the substitute decision maker (AOR 6.592, 95% CI 1.452-29.927; P=.02). In the qualitative content analysis, patients with both low and high global satisfaction scores shared the same factors of service dissatisfaction (assurance, reliability, and empathy). The main subcategories associated with dissatisfaction were missing clinical activities, inadequate communication, administrative process issues, and absence of personal connection. Conversely, the high-satisfaction group offered more positive feedback on assurance, reliability, and empathy, as well as on having a competent clinician, appropriate patient selection, and excellent communication and empathy skills. Conclusions: The insights gained from this study can be considered when designing home-based teleconsultation services to enhance patient experiences in stroke prevention care. %M 38363590 %R 10.2196/51439 %U https://cardio.jmir.org/2024/1/e51439 %U https://doi.org/10.2196/51439 %U http://www.ncbi.nlm.nih.gov/pubmed/38363590 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e53421 %T A Multidisciplinary Assessment of ChatGPT’s Knowledge of Amyloidosis: Observational Study %A King,Ryan C %A Samaan,Jamil S %A Yeo,Yee Hui %A Peng,Yuxin %A Kunkel,David C %A Habib,Ali A %A Ghashghaei,Roxana %+ Division of Cardiology, Department of Medicine, University of California, Irvine Medical Center, 101 The City Drive South, Orange, CA, 92868, United States, 1 714 456 7890, kingrc@hs.uci.edu %K amyloidosis %K ChatGPT %K large language models %K cardiology %K gastroenterology %K neurology %K artificial intelligence %K multidisciplinary care %K assessment %K patient education %K large language model %K accuracy %K reliability %K accessibility %K educational resources %K dissemination %K gastroenterologist %K cardiologist %K medical society %K institution %K institutions %K Facebook %K neurologist %K reproducibility %K amyloidosis-related %D 2024 %7 19.4.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Amyloidosis, a rare multisystem condition, often requires complex, multidisciplinary care. Its low prevalence underscores the importance of efforts to ensure the availability of high-quality patient education materials for better outcomes. ChatGPT (OpenAI) is a large language model powered by artificial intelligence that offers a potential avenue for disseminating accurate, reliable, and accessible educational resources for both patients and providers. Its user-friendly interface, engaging conversational responses, and the capability for users to ask follow-up questions make it a promising future tool in delivering accurate and tailored information to patients. Objective: We performed a multidisciplinary assessment of the accuracy, reproducibility, and readability of ChatGPT in answering questions related to amyloidosis. Methods: In total, 98 amyloidosis questions related to cardiology, gastroenterology, and neurology were curated from medical societies, institutions, and amyloidosis Facebook support groups and inputted into ChatGPT-3.5 and ChatGPT-4. Cardiology- and gastroenterology-related responses were independently graded by a board-certified cardiologist and gastroenterologist, respectively, who specialize in amyloidosis. These 2 reviewers (RG and DCK) also graded general questions for which disagreements were resolved with discussion. Neurology-related responses were graded by a board-certified neurologist (AAH) who specializes in amyloidosis. Reviewers used the following grading scale: (1) comprehensive, (2) correct but inadequate, (3) some correct and some incorrect, and (4) completely incorrect. Questions were stratified by categories for further analysis. Reproducibility was assessed by inputting each question twice into each model. The readability of ChatGPT-4 responses was also evaluated using the Textstat library in Python (Python Software Foundation) and the Textstat readability package in R software (R Foundation for Statistical Computing). Results: ChatGPT-4 (n=98) provided 93 (95%) responses with accurate information, and 82 (84%) were comprehensive. ChatGPT-3.5 (n=83) provided 74 (89%) responses with accurate information, and 66 (79%) were comprehensive. When examined by question category, ChatGTP-4 and ChatGPT-3.5 provided 53 (95%) and 48 (86%) comprehensive responses, respectively, to “general questions” (n=56). When examined by subject, ChatGPT-4 and ChatGPT-3.5 performed best in response to cardiology questions (n=12) with both models producing 10 (83%) comprehensive responses. For gastroenterology (n=15), ChatGPT-4 received comprehensive grades for 9 (60%) responses, and ChatGPT-3.5 provided 8 (53%) responses. Overall, 96 of 98 (98%) responses for ChatGPT-4 and 73 of 83 (88%) for ChatGPT-3.5 were reproducible. The readability of ChatGPT-4’s responses ranged from 10th to beyond graduate US grade levels with an average of 15.5 (SD 1.9). Conclusions: Large language models are a promising tool for accurate and reliable health information for patients living with amyloidosis. However, ChatGPT’s responses exceeded the American Medical Association’s recommended fifth- to sixth-grade reading level. Future studies focusing on improving response accuracy and readability are warranted. Prior to widespread implementation, the technology’s limitations and ethical implications must be further explored to ensure patient safety and equitable implementation. %M 38640472 %R 10.2196/53421 %U https://cardio.jmir.org/2024/1/e53421 %U https://doi.org/10.2196/53421 %U http://www.ncbi.nlm.nih.gov/pubmed/38640472 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e53091 %T Use of Machine Learning for Early Detection of Maternal Cardiovascular Conditions: Retrospective Study Using Electronic Health Record Data %A Shara,Nawar %A Mirabal-Beltran,Roxanne %A Talmadge,Bethany %A Falah,Noor %A Ahmad,Maryam %A Dempers,Ramon %A Crovatt,Samantha %A Eisenberg,Steven %A Anderson,Kelley %+ School of Nursing, Georgetown University, 3700 Reservoir Road, NW, Washington, DC, 20057, United States, 1 2026873496, rm1910@georgetown.edu %K machine learning %K preeclampsia %K cardiovascular %K maternal %K obstetrics %K health disparities %K woman %K women %K pregnancy %K pregnant %K cardiovascular %K cardiovascular condition %K retrospective study %K electronic health record %K EHR %K technology %K decision-making %K health disparity %K virtual server %K thromboembolism %K kidney failure %K HOPE-CAT %D 2024 %7 22.4.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Cardiovascular conditions (eg, cardiac and coronary conditions, hypertensive disorders of pregnancy, and cardiomyopathies) were the leading cause of maternal mortality between 2017 and 2019. The United States has the highest maternal mortality rate of any high-income nation, disproportionately impacting those who identify as non-Hispanic Black or Hispanic. Novel clinical approaches to the detection and diagnosis of cardiovascular conditions are therefore imperative. Emerging research is demonstrating that machine learning (ML) is a promising tool for detecting patients at increased risk for hypertensive disorders during pregnancy. However, additional studies are required to determine how integrating ML and big data, such as electronic health records (EHRs), can improve the identification of obstetric patients at higher risk of cardiovascular conditions. Objective: This study aimed to evaluate the capability and timing of a proprietary ML algorithm, Healthy Outcomes for all Pregnancy Experiences-Cardiovascular-Risk Assessment Technology (HOPE-CAT), to detect maternal-related cardiovascular conditions and outcomes. Methods: Retrospective data from the EHRs of a large health care system were investigated by HOPE-CAT in a virtual server environment. Deidentification of EHR data and standardization enabled HOPE-CAT to analyze data without pre-existing biases. The ML algorithm assessed risk factors selected by clinical experts in cardio-obstetrics, and the algorithm was iteratively trained using relevant literature and current standards of risk identification. After refinement of the algorithm’s learned risk factors, risk profiles were generated for every patient including a designation of standard versus high risk. The profiles were individually paired with clinical outcomes pertaining to cardiovascular pregnancy conditions and complications, wherein a delta was calculated between the date of the risk profile and the actual diagnosis or intervention in the EHR. Results: In total, 604 pregnancies resulting in birth had records or diagnoses that could be compared against the risk profile; the majority of patients identified as Black (n=482, 79.8%) and aged between 21 and 34 years (n=509, 84.4%). Preeclampsia (n=547, 90.6%) was the most common condition, followed by thromboembolism (n=16, 2.7%) and acute kidney disease or failure (n=13, 2.2%). The average delta was 56.8 (SD 69.7) days between the identification of risk factors by HOPE-CAT and the first date of diagnosis or intervention of a related condition reported in the EHR. HOPE-CAT showed the strongest performance in early risk detection of myocardial infarction at a delta of 65.7 (SD 81.4) days. Conclusions: This study provides additional evidence to support ML in obstetrical patients to enhance the early detection of cardiovascular conditions during pregnancy. ML can synthesize multiday patient presentations to enhance provider decision-making and potentially reduce maternal health disparities. %M 38648629 %R 10.2196/53091 %U https://cardio.jmir.org/2024/1/e53091 %U https://doi.org/10.2196/53091 %U http://www.ncbi.nlm.nih.gov/pubmed/38648629 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e51916 %T The Effect of an AI-Based, Autonomous, Digital Health Intervention Using Precise Lifestyle Guidance on Blood Pressure in Adults With Hypertension: Single-Arm Nonrandomized Trial %A Leitner,Jared %A Chiang,Po-Han %A Agnihotri,Parag %A Dey,Sujit %+ Electrical and Computer Engineering Department, University of California, San Diego, 9500 Gilman Dr, La Jolla, CA, 92093, United States, 1 8587220467, jjleitne@ucsd.edu %K blood pressure %K hypertension %K digital health %K lifestyle change %K lifestyle medicine %K wearables %K remote patient monitoring %K artificial intelligence %K AI %K mobile phone %D 2024 %7 28.5.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Home blood pressure (BP) monitoring with lifestyle coaching is effective in managing hypertension and reducing cardiovascular risk. However, traditional manual lifestyle coaching models significantly limit availability due to high operating costs and personnel requirements. Furthermore, the lack of patient lifestyle monitoring and clinician time constraints can prevent personalized coaching on lifestyle modifications. Objective: This study assesses the effectiveness of a fully digital, autonomous, and artificial intelligence (AI)–based lifestyle coaching program on achieving BP control among adults with hypertension. Methods: Participants were enrolled in a single-arm nonrandomized trial in which they received a BP monitor and wearable activity tracker. Data were collected from these devices and a questionnaire mobile app, which were used to train personalized machine learning models that enabled precision lifestyle coaching delivered to participants via SMS text messaging and a mobile app. The primary outcomes included (1) the changes in systolic and diastolic BP from baseline to 12 and 24 weeks and (2) the percentage change of participants in the controlled, stage-1, and stage-2 hypertension categories from baseline to 12 and 24 weeks. Secondary outcomes included (1) the participant engagement rate as measured by data collection consistency and (2) the number of manual clinician outreaches. Results: In total, 141 participants were monitored over 24 weeks. At 12 weeks, systolic and diastolic BP decreased by 5.6 mm Hg (95% CI −7.1 to −4.2; P<.001) and 3.8 mm Hg (95% CI −4.7 to −2.8; P<.001), respectively. Particularly, for participants starting with stage-2 hypertension, systolic and diastolic BP decreased by 9.6 mm Hg (95% CI −12.2 to −6.9; P<.001) and 5.7 mm Hg (95% CI −7.6 to −3.9; P<.001), respectively. At 24 weeks, systolic and diastolic BP decreased by 8.1 mm Hg (95% CI −10.1 to −6.1; P<.001) and 5.1 mm Hg (95% CI −6.2 to −3.9; P<.001), respectively. For participants starting with stage-2 hypertension, systolic and diastolic BP decreased by 14.2 mm Hg (95% CI −17.7 to −10.7; P<.001) and 8.1 mm Hg (95% CI −10.4 to −5.7; P<.001), respectively, at 24 weeks. The percentage of participants with controlled BP increased by 17.2% (22/128; P<.001) and 26.5% (27/102; P<.001) from baseline to 12 and 24 weeks, respectively. The percentage of participants with stage-2 hypertension decreased by 25% (32/128; P<.001) and 26.5% (27/102; P<.001) from baseline to 12 and 24 weeks, respectively. The average weekly participant engagement rate was 92% (SD 3.9%), and only 5.9% (6/102) of the participants required manual outreach over 24 weeks. Conclusions: The study demonstrates the potential of fully digital, autonomous, and AI-based lifestyle coaching to achieve meaningful BP improvements and high engagement for patients with hypertension while substantially reducing clinician workloads. Trial Registration: ClinicalTrials.gov NCT06337734; https://clinicaltrials.gov/study/NCT06337734 %M 38805253 %R 10.2196/51916 %U https://cardio.jmir.org/2024/1/e51916 %U https://doi.org/10.2196/51916 %U http://www.ncbi.nlm.nih.gov/pubmed/38805253 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e59243 %T Smart Device Ownership and Use of Social Media, Wearable Trackers, and Health Apps Among Black Women With Hypertension in the United States: National Survey Study %A Kalinowski,Jolaade %A Bhusal,Sandesh %A Pagoto,Sherry L %A Newton Jr,Robert %A Waring,Molly E %+ Department of Human Development and Family Sciences, University of Connecticut, 348 Mansfield Rd Unit 1058, Storrs, CT, 06269, United States, 1 203 251 8421, jolaade.kalinowski@uconn.edu %K Black women %K Black %K women %K tracker %K trackers %K wearable %K wearables %K hypertension %K hypertensive %K cardiology %K cardiovascular %K blood pressure %K social media %K technology %K usage %K digital health %K eHealth %K tablet %K mHealth %K mobile health %K app %K apps %K applications %K survey %K surveys %K questionnaire %K questionnaires %K Health Information National Trends Survey %K HINTS %D 2024 %7 9.9.2024 %9 Research Letter %J JMIR Cardio %G English %X The majority of Black women with hypertension in the United States have smartphones or tablets and use social media, and many use wearable activity trackers and health or wellness apps, digital tools that can be used to support lifestyle changes and medication adherence. %M 39250778 %R 10.2196/59243 %U https://cardio.jmir.org/2024/1/e59243 %U https://doi.org/10.2196/59243 %U http://www.ncbi.nlm.nih.gov/pubmed/39250778 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e54746 %T Comparison of Auscultation Quality Using Contemporary Digital Stethoscopes %A Saraya,Norah %A McBride,Jonathon %A Singh,Karandeep %A Sohail,Omar %A Das,Porag Jeet %+ Department of Learning Health Sciences, University of Michigan, North Ingalls Building, 300 N Ingalls St, Ann Arbor, MI, 48109, United States, 1 734 936 1649, karandeep@health.ucsd.edu %K auscultation %K digital stethoscopes %K valvular heart disease %D 2024 %7 8.11.2024 %9 Research Letter %J JMIR Cardio %G English %X %M 39514245 %R 10.2196/54746 %U https://cardio.jmir.org/2024/1/e54746 %U https://doi.org/10.2196/54746 %U http://www.ncbi.nlm.nih.gov/pubmed/39514245 %0 Journal Article %@ 2561-1011 %I JMIR Publications %V 8 %N %P e60503 %T Identifying the Severity of Heart Valve Stenosis and Regurgitation Among a Diverse Population Within an Integrated Health Care System: Natural Language Processing Approach %A Xie,Fagen %A Lee,Ming-sum %A Allahwerdy,Salam %A Getahun,Darios %A Wessler,Benjamin %A Chen,Wansu %+ Department of Research and Evaluation, Kaiser Permanente Southern California, 100 S Los Robles Ave, 2nd Floor, Pasadena, CA, 91101, United States, 1 6265643294, fagen.xie@kp.org %K echocardiography report %K heart valve %K stenosis %K regurgitation %K natural language processing %K algorithm %D 2024 %7 30.9.2024 %9 Original Paper %J JMIR Cardio %G English %X Background: Valvular heart disease (VHD) is a leading cause of cardiovascular morbidity and mortality that poses a substantial health care and economic burden on health care systems. Administrative diagnostic codes for ascertaining VHD diagnosis are incomplete. Objective: This study aimed to develop a natural language processing (NLP) algorithm to identify patients with aortic, mitral, tricuspid, and pulmonic valve stenosis and regurgitation from transthoracic echocardiography (TTE) reports within a large integrated health care system. Methods: We used reports from echocardiograms performed in the Kaiser Permanente Southern California (KPSC) health care system between January 1, 2011, and December 31, 2022. Related terms/phrases of aortic, mitral, tricuspid, and pulmonic stenosis and regurgitation and their severities were compiled from the literature and enriched with input from clinicians. An NLP algorithm was iteratively developed and fine-trained via multiple rounds of chart review, followed by adjudication. The developed algorithm was applied to 200 annotated echocardiography reports to assess its performance and then the study echocardiography reports. Results: A total of 1,225,270 TTE reports were extracted from KPSC electronic health records during the study period. In these reports, valve lesions identified included 111,300 (9.08%) aortic stenosis, 20,246 (1.65%) mitral stenosis, 397 (0.03%) tricuspid stenosis, 2585 (0.21%) pulmonic stenosis, 345,115 (28.17%) aortic regurgitation, 802,103 (65.46%) mitral regurgitation, 903,965 (73.78%) tricuspid regurgitation, and 286,903 (23.42%) pulmonic regurgitation. Among the valves, 50,507 (4.12%), 22,656 (1.85%), 1685 (0.14%), and 1767 (0.14%) were identified as prosthetic aortic valves, mitral valves, tricuspid valves, and pulmonic valves, respectively. Mild and moderate were the most common severity levels of heart valve stenosis, while trace and mild were the most common severity levels of regurgitation. Males had a higher frequency of aortic stenosis and all 4 valvular regurgitations, while females had more mitral, tricuspid, and pulmonic stenosis. Non-Hispanic Whites had the highest frequency of all 4 valvular stenosis and regurgitations. The distribution of valvular stenosis and regurgitation severity was similar across race/ethnicity groups. Frequencies of aortic stenosis, mitral stenosis, and regurgitation of all 4 heart valves increased with age. In TTE reports with stenosis detected, younger patients were more likely to have mild aortic stenosis, while older patients were more likely to have severe aortic stenosis. However, mitral stenosis was opposite (milder in older patients and more severe in younger patients). In TTE reports with regurgitation detected, younger patients had a higher frequency of severe/very severe aortic regurgitation. In comparison, older patients had higher frequencies of mild aortic regurgitation and severe mitral/tricuspid regurgitation. Validation of the NLP algorithm against the 200 annotated TTE reports showed excellent precision, recall, and F1-scores. Conclusions: The proposed computerized algorithm could effectively identify heart valve stenosis and regurgitation, as well as the severity of valvular involvement, with significant implications for pharmacoepidemiological studies and outcomes research. %M 39348175 %R 10.2196/60503 %U https://cardio.jmir.org/2024/1/e60503 %U https://doi.org/10.2196/60503 %U http://www.ncbi.nlm.nih.gov/pubmed/39348175