JMIR Cardio最新文献

{"title":"Machine Learning Model for Predicting Coronary Heart Disease Risk: Development and Validation Using Insights From a Japanese Population-Based Study.","authors":"Thien Vu, Yoshihiro Kokubo, Mai Inoue, Masaki Yamamoto, Attayeb Mohsen, Agustin Martin-Morales, Research Dawadi, Takao Inoue, Jie Ting Tay, Mari Yoshizaki, Naoki Watanabe, Yuki Kuriya, Chisa Matsumoto, Ahmed Arafa, Yoko M Nakao, Yuka Kato, Masayuki Teramoto, Michihiro Araki","doi":"10.2196/68066","DOIUrl":"https://doi.org/10.2196/68066","url":null,"abstract":"<p><strong>Background: </strong>Coronary heart disease (CHD) is a major cause of morbidity and mortality worldwide. Identifying key risk factors is essential for effective risk assessment and prevention. A data-driven approach using machine learning (ML) offers advanced techniques to analyze complex, nonlinear, and high-dimensional datasets, uncovering novel predictors of CHD that go beyond the limitations of traditional models, which rely on predefined variables.</p><p><strong>Objective: </strong>This study aims to evaluate the contribution of various risk factors to CHD, focusing on both established and novel markers using ML techniques.</p><p><strong>Methods: </strong>The study recruited 7672 participants aged 30-84 years from Suita City, Japan, between 1989 and 1999. Over an average of 15 years, participants were monitored for cardiovascular events. A total of 7260 participants and 28 variables were included in the analysis after excluding individuals with missing outcome data and eliminating unnecessary variables. Five ML models-logistic regression, random forest (RF), support vector machine, Extreme Gradient Boosting, and Light Gradient-Boosting Machine-were applied for predicting CHD incidence. Model performance was evaluated using accuracy, sensitivity, specificity, precision, area under the curve, F1-score, calibration curves, observed-to-expected ratios, and decision curve analysis. Additionally, Shapley Additive Explanations (SHAPs) were used to interpret the prediction models and understand the contribution of various risk factors to CHD.</p><p><strong>Results: </strong>Among 7260 participants, 305 (4.2%) were diagnosed with CHD. The RF model demonstrated the highest performance, with an accuracy of 0.73 (95% CI 0.64-0.80), sensitivity of 0.74 (95% CI 0.62-0.84), specificity of 0.72 (95% CI 0.61-0.83), and an area under the curve of 0.73 (95% CI 0.65-0.80). RF also showed excellent calibration, with predicted probabilities closely aligning with observed outcomes, and provided substantial net benefit across a range of risk thresholds, as demonstrated by decision curve analysis. SHAP analysis elucidated key predictors of CHD, including the intima-media thickness (IMT_cMax) of the common carotid artery, blood pressure, lipid profiles (non-high-density lipoprotein cholesterol, high-density lipoprotein cholesterol, and triglycerides), and estimated glomerular filtration rate. Novel risk factors identified as significant contributors to CHD risk included lower calcium levels, elevated white blood cell counts, and body fat percentage. Furthermore, a protective effect was observed in women, suggesting the potential necessity for gender-specific risk assessment strategies in future cardiovascular health evaluations.</p><p><strong>Conclusions: </strong>We developed a model to predict CHD using ML and applied SHAP methods for interpretation. This approach highlights the multifactor nature of CHD risk evaluation, aiming to support health care pro","PeriodicalId":14706,"journal":{"name":"JMIR Cardio","volume":"9 ","pages":"e68066"},"PeriodicalIF":0.0,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144063109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Results of a Digital Multimodal Motivational and Educational Program as Follow-Up Care for Former Cardiac Rehabilitation Patients: Randomized Controlled Trial.","authors":"Maxi Pia Bretschneider, Wolfgang Mayer-Berger, Jens Weine, Lena Roth, Peter E H Schwarz, Franz Petermann","doi":"10.2196/73890","DOIUrl":"https://doi.org/10.2196/73890","url":null,"abstract":"","PeriodicalId":14706,"journal":{"name":"JMIR Cardio","volume":"9 ","pages":"e73890"},"PeriodicalIF":0.0,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143988812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Augmenting Engagement in Decentralized Clinical Trials for Atrial Fibrillation: Development and Implementation of a Programmatic Architecture.","authors":"Toluwa Daniel Omole, Andrew Mrkva, Danielle Ferry, Erin Shepherd, Jessica Caratelli, Noah Davis, Richmond Akatue, Timothy Bickmore, Michael K Paasche-Orlow, Jared W Magnani","doi":"10.2196/66436","DOIUrl":"https://doi.org/10.2196/66436","url":null,"abstract":"<p><strong>Background: </strong>Atrial fibrillation (AF) is a chronic cardiovascular condition that requires long-term adherence to medications and self-monitoring. Clinical trials for AF have had limited diversity by sex, race and ethnicity, and rural residence, thereby compromising the integrity and generalizability of trial findings. Digital technology coupled with remote strategies has the potential to increase recruitment of individuals from underrepresented demographic and geographic populations, resulting in increased trial diversity, and improvement in the generalizability of interventions for complex diseases such as AF.</p><p><strong>Objective: </strong>This study aimed to summarize the architecture of a research program using remote methods to enhance geographic and demographic diversity in mobile health trials to improve medication adherence.</p><p><strong>Methods: </strong>We developed a programmatic architecture to conduct remote recruitment and assessments of individuals with AF in 2 complementary randomized clinical trials, funded by the National Institutes of Health, to test the effectiveness of a smartphone-based relational agent on adherence to oral anticoagulation. The study team engaged individuals with either rural or metropolitan residences receiving care for AF at health care settings who then provided consent, and underwent baseline assessments and randomization during a remotely conducted telephone visit. Participants were randomized to receive the relational agent intervention or control and subsequently received a study smartphone with installed apps by mail. Participants received a telephone-based training session on device and app usage accompanied by a booklet with pictures and instructions accessible for any level of health or digital literacy. The program included remote methods by mail and telephone to promote retention at 4-, 8-, and 12-month visits and incentivized return of the smartphone following study participation. The program demonstrated excellent participant engagement and retention throughout the duration of the clinical trials.</p><p><strong>Results: </strong>The trials enrolled 513 participants, surpassing recruitment goals for the rural (n=270; target n=264) and metropolitan (n=243; target n=240) studies. A total of 62% (319/513) were women; 31% (75/243) of participants in the metropolitan study were African American, Asian, American Indian or Alaskan native or other races or ethnicities, in contrast to 5% (12/270) in the rural study. Among all participants, 56% (286/513) had less than an associate's degree and 44% (225/513) were characterized as having limited health literacy. Intervention recipients receiving the relational agent used the agent median of 95-98 (IQR, 56-109) days across both studies. Retention exceeded 89% (457/513) at 12 months with study phones used for median 3.3 (IQR, 1-5) participants.</p><p><strong>Conclusions: </strong>We report here the development and implementation of a p","PeriodicalId":14706,"journal":{"name":"JMIR Cardio","volume":"9 ","pages":"e66436"},"PeriodicalIF":0.0,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144015819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prerequisites for Cost-Effective Home Blood Pressure Telemonitoring: Early Health Economic Analysis.","authors":"Job van Steenkiste, Pim van Dorst, Daan Dohmen, Cornelis Boersma","doi":"10.2196/64386","DOIUrl":"https://doi.org/10.2196/64386","url":null,"abstract":"<p><strong>Background: </strong>Home blood pressure telemonitoring (HBPT) has been proposed to enhance adherence and optimize health care delivery, yet its prerequisites for cost-effective implementation remain unclear.</p><p><strong>Objective: </strong>This study aims to quantify the potential cost-effectiveness of HBPT and identify prerequisites for cost-effective implementation of HBPT in comparison to standard hypertension management, using an early health economic analysis from a societal perspective.</p><p><strong>Methods: </strong>A decision-analytic Markov model with a lifetime horizon (30 years) and a willingness-to-pay threshold of €20,000 (€1=US $1.09) per quality-adjusted life year (QALY) was developed to assess the cost-effectiveness of HBPT compared to standard of care (SOC). The HBPT intervention was based on an existing HBPT program applied by the Maasstad Hospital, Rotterdam, the Netherlands. The model incorporated 12 health states: 7 blood pressure states, 1 cardiovascular (CV) event, 1 recurrent CV event, 1 postrecurrent CV event, 1 all-cause death, and 1 CV disease-related death. A hypothetical cohort of 1000 patients (average age 65.3 years) was modeled, and results were reported in costs, QALYs, and the incremental cost-effectiveness ratio (ICER). The model assumed 3 in-person outpatient department (OPD) consultations in the SOC group and 1.5 in the HBPT group. Extensive sensitivity analyses were performed to identify important variables for the cost-effective implementation of HBPT.</p><p><strong>Results: </strong>Following the base-case analysis, HBPT was not cost-effective with an ICER of €20,386 per QALY. Sensitivity analyses indicated that reducing the number of in-person OPD consultations resulted in a more favorable ICER. Specifically, reducing the number of in-person OPD consultations to 1.48 annually resulted in an ICER below the willingness-to-pay threshold. Reducing the in-person OPD consultations to an average of 1.18 per year would make HBPT cost-saving. Scenario analyses revealed that extending the duration of HBPT's clinical effect to 2 or 3 years substantially improved the ICER. Additionally, targeting HBPT toward patients aged 64 years or below further improved the ICER.</p><p><strong>Conclusions: </strong>HBPT could result in cost-effective or cost-saving outcomes with only minor reductions in in-person OPD consultations. These findings highlight the potential of HBPT to transform hypertension management by replacing traditional hypertension management with more efficient care using remote patient monitoring.</p>","PeriodicalId":14706,"journal":{"name":"JMIR Cardio","volume":"9 ","pages":"e64386"},"PeriodicalIF":0.0,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144018233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The rs243865 Polymorphism in Matrix Metalloproteinase-2 and its Association With Target Organ Damage in Patients With Resistant Hypertension: Cross-Sectional Study.","authors":"An Tuan Huynh, Hoang Anh Vu, Ho Quoc Chuong, Tien Hoang Anh, An Viet Tran","doi":"10.2196/71016","DOIUrl":"https://doi.org/10.2196/71016","url":null,"abstract":"<p><strong>Background: </strong>Resistant hypertension (RH) presents significant clinical challenges, often precipitating a spectrum of cardiovascular complications. Particular attention recently has focused on the role of matrix metalloproteinase-2 (MMP-2) gene polymorphisms, implicated in hypertensive target organ damage (TOD). Despite growing interest, the specific contribution of MMP-2 polymorphisms to such damage in RH remains inadequately defined.</p><p><strong>Objective: </strong>This study is the first to examine the rs243865 (-1306C>T) polymorphism in the MMP-2 gene in the Vietnamese population and patients with RH, underscoring its critical role as a genetic determinant of TOD.</p><p><strong>Methods: </strong>A cross-sectional study with both descriptive and analytical components was conducted with 78 patients with RH at the Can Tho Central General Hospital and Can Tho University of Medicine and Pharmacy Hospital from July 2023 to February 2024.</p><p><strong>Results: </strong>More than three-quarters of patients with RH had carotid-femoral pulse wave velocity (PWV) >10 m/s and microalbuminuria at a prevalence of 79% (62/78) and 76% (59/78), respectively, and more than half of patients with RH had left ventricular mass index, relative wall thickness, and carotid artery stenosis with a prevalence of 56% (45/78), 55% (43/78), and 53% (41/78), respectively. Of the 78 studied patients with RH, the presence of genotype CC was 77% (60/78), genotype CT accounted for 21% (16/78), and genotype TT for 3% (2/78). The presence of single nucleotide polymorphism rs243865 (-1306C>T) with allele T was 23% (18/78). The MMP-2 gene polymorphism 1306C/T (rs243865) was significantly associated with ejection fraction and carotid artery stenosis with odds ratios (ORs) 8.1 (95% CI 1.3-51.4; P=.03) and 4.5 (95% CI 1.1-20.1; P=.048), respectively. The allele T was found to be significantly associated with arterial stiffness including brachial-ankle PWV and carotid-femoral PWV with the correlation coefficient of OR 2.2 (95% CI 0.6-3.8) and OR 1.8 (95% CI 0.5-3.2), respectively.</p><p><strong>Conclusions: </strong>The MMP-2 gene polymorphism rs243865 (-1306C>T) may have an association with measurable TOD in RH.</p>","PeriodicalId":14706,"journal":{"name":"JMIR Cardio","volume":"9 ","pages":"e71016"},"PeriodicalIF":0.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12061201/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144002988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Co-Occurring Diseases and Mortality in Patients With Chronic Heart Disease, Modeling Their Dynamically Expanding Disease Portfolios: Nationwide Register Study.","authors":"Nikolaj Normann Holm, Anne Frølich, Helena Dominguez, Kim Peder Dalhoff, Helle Gybel Juul-Larsen, Ove Andersen, Anders Stockmarr","doi":"10.2196/57749","DOIUrl":"https://doi.org/10.2196/57749","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Medical advances in managing patients with chronic heart disease (HD) permit the co-occurrence of other chronic diseases due to increased longevity, causing them to become multimorbid. Previous research on the effect of co-occurring diseases on mortality among patients with HD often considers disease counts or clusters at HD diagnosis, overlooking the dynamics of patients' disease portfolios over time, where new chronic diseases are diagnosed before death. Furthermore, these studies do not consider interactions among diseases and between diseases, biological and socioeconomic variables, which are essential for addressing health disparities among patients with HD. Therefore, a mapping of the effect of combinations of these co-occurring diseases on mortality among patients with HD considering such interactions in a dynamic setting is warranted.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to examine the effect of the co-occurring diseases of patients with HD on mortality, modeling their dynamically expanding chronic disease portfolios while identifying interactions between the co-occurring diseases, socioeconomic and biological variables.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This study used data from the national Danish registries and algorithmic diagnoses of 15 chronic diseases to obtain a study population of all 766,596 adult patients with HD in Denmark from January 1, 1995, to December 31, 2015. The time from HD diagnosis until death was modeled using an extended Cox model involving chronic diseases and their interactions as time-varying covariates. We identified interactions between co-occurring diseases, socioeconomic and biological variables in a data-driven manner using a hierarchical forward-backward selection procedure and stability selection. We mapped the impact on mortality of (1) the most common disease portfolios, (2) the disease portfolios subject to the highest level of interaction, and (3) the most severe disease portfolios. Estimates from interaction-based models were compared to an additive model.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Cancer had the highest impact on mortality (hazard ratio=6.72 for male individuals and 7.59 for female individuals). Excluding cancer revealed schizophrenia and dementia as those with the highest mortality impact (top 5 hazard ratios in the 11.72-13.37 range for male individuals and 13.86-16.65 for female individuals for combinations of 4 diseases). The additive model underestimated the effects up to a factor of 1.4 compared to the interaction model. Stroke, osteoporosis, chronic obstructive pulmonary disease, dementia, and depression were identified as chronic diseases involved in the most complex interactions, which were of the fifth order.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The findings of this study emphasize the importance of identifying and modeling disease interactions to gain a comprehensive understanding of mortality risk in patients with HD. This study illustrat","PeriodicalId":14706,"journal":{"name":"JMIR Cardio","volume":"9 ","pages":"e57749"},"PeriodicalIF":0.0,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12064962/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144019803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Telehealth Support From Cardiologists to Primary Care Physicians in Heart Failure Treatment: Mixed Methods Feasibility Study of the Brazilian Heart Insufficiency With Telemedicine Trial.","authors":"Leonardo Graever, Priscila Cordeiro Mafra, Vinicius Klein Figueira, Vanessa Navega Miler, Júlia Dos Santos Lima Sobreiro, Gabriel Pesce de Castro da Silva, Aurora Felice Castro Issa, Leonardo Cançado Monteiro Savassi, Mariana Borges Dias, Marcelo Machado Melo, Viviane Belidio Pinheiro da Fonseca, Isabel Cristina Pacheco da Nóbrega, Maria Kátia Gomes, Laís Pimenta Ribeiro Dos Santos, José Roberto Lapa E Silva, Anne Froelich, Helena Dominguez","doi":"10.2196/64438","DOIUrl":"https://doi.org/10.2196/64438","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Heart failure is a prevalent condition ideally managed through collaboration between health care sectors. Telehealth between cardiologists and primary care physicians is a strategy to improve the quality of care for patients with heart failure. Still, the effectiveness of this approach on patient-relevant outcomes needs to be determined.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to assess the feasibility of telehealth support provided by cardiologists for treating patients with heart failure to primary care physicians from public primary care practices in Rio de Janeiro, Brazil.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We used mixed methods to assess the feasibility of telehealth support. From 2020 to 2022, we tested 2 telehealth approaches: synchronous videoconferences (phase A) and interaction through an asynchronous web platform (phase B). The primary outcome was feasibility. Exploratory outcomes were telehealth acceptability of patients, primary care physicians, and cardiologists; the patients' clinical status; and prescription practices. Qualitative methods comprised content analysis of 3 focus groups and 15 individual interviews with patients, primary care physicians, and cardiologists. Quantitative methods included the baseline assessment of 83 patients; a single-arm, before-and-after assessment of clinical status in 58 patients; and an assessment of guideline-directed medical therapy in 28 patients with reduced ejection fraction measured within 1 year of follow-up. We integrated qualitative and quantitative data using a joint display table and used the A Process for Decision-Making After Pilot and Feasibility Trials framework for feasibility assessment.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Telehealth support from cardiologists to primary care physicians was generally well accepted. As barriers, patients expressed concern about reduced direct access to cardiologists, primary care physicians reported work overload and a lack of relative advantage, and cardiologists expressed concern about the sustainability of the intervention. Quantitative analysis revealed an overall poor baseline clinical status of patients with heart failure, with 53% (44/83) decompensated, as expected. Compliance with guideline-directed medical therapy for the treatment of heart failure with reduced ejection fraction after telehealth showed a modest improvement for β-blockers (17/20, 85% to 18/19, 95%) and renin-angiotensin-aldosterone system inhibitors (14/20, 70% to 15/19, 79%) but a drop in the prescription of spironolactone (16/20, 80% to 15/20, 75%). Neprilysin and sodium-glucose cotransporter 2 inhibitors were introduced in 4 and 1 patient, respectively. Missing record data precluded a more precise analysis. The feasibility assessment was positive, favoring the asynchronous modality. Potential modifications include more effective patient and professional recruitment strategies and educational activities to raise awareness of collaborati","PeriodicalId":14706,"journal":{"name":"JMIR Cardio","volume":"9 ","pages":"e64438"},"PeriodicalIF":0.0,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12046267/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144024968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Web-Based Tool to Perform a Values Clarification for Stroke Prevention in Patients With Atrial Fibrillation: Design and Preliminary Testing Study.","authors":"Michael P Dorsch, Allen J Flynn, Kaitlyn M Greer, Sabah Ganai, Geoffrey D Barnes, Brian Zikmund-Fisher","doi":"10.2196/67956","DOIUrl":"https://doi.org/10.2196/67956","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Atrial fibrillation (AF) is associated with an increased risk of stroke. Oral anticoagulation (OAC) is used for stroke prevention in AF, but it also increases bleeding risk. Clinical guidelines do not definitively recommend for or against OAC for patients with borderline stroke risk. Decision-making may benefit from values clarification exercises to communicate risk trade-offs.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to evaluate if a visual with a values clarification alters the understanding of the trade-offs of anticoagulation in AF.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;Participants aged 45-64 years were recruited across the United States via an online survey. While answering the survey, they were asked to imagine they were newly diagnosed with AF with a CHA2DS2-VASc (congestive heart failure; hypertension; age ≥75 years [doubled]; type 2 diabetes; previous stroke, transient ischemic attack, or thromboembolism [doubled]; vascular disease; age 65 to 75 years; and sex category) score of 1 for men and 2 for women. Eligibility criteria included no diagnosis of AF and no prior OAC use. Participants were randomized to one of three conditions: (1) standard text-based information only (n=255), (2) visual aids showing stroke-risk probabilities (n=218), or (3) visual aids plus a values clarification exercise (visual+VC; n=200). Participants were subrandomized within the 2 visual-based groups to view either a gauge display or an icon array representing stroke risk. All participants read a hypothetical scenario of being newly diagnosed with AF and hypertension. The primary outcome was decision confidence as measured by the SURE (Sure of Myself; Understand Information; Risk-Benefit Ratio; Encouragement) test. Secondary measures included participants' perceived stroke risk reduction, worry about stroke or bleeding, and likelihood to choose OAC.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;A total of 673 participants completed the survey. The overall SURE test was 61.2% (156/255) for the standard, 66.5% (145/218) for the visual, and 67% (134/200) for the visual+VC group (visual vs standard P=.23; visual+VC vs standard P=.20). Participants were less likely to choose OAC in the visual groups (standard: mean 58.3, SD 30; visual: mean 51.4, SD 32; visual+VC: 51.9, SD 28; P=.03). Participants felt the reduction in stroke risk from an OAC was less in the visual groups (standard: mean 63.8, SD 22; visual: mean 54.2, SD 28; visual+VC: mean 58.6, SD 25; P&lt;.001). Visualization methods (gauge vs icon array) showed no significant differences in overall SURE test results. Participants were less likely to choose OAC and perceived a smaller stroke risk reduction with gauge than icon array (OAC choice: gauge 48.8, icon array 55.4; P=.03; stroke risk reduction: gauge 52.1, icon array 60.4; P=.001).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Visual aids can modestly affect decision confidence and perceptions regarding the benefits of OAC but do not significan","PeriodicalId":14706,"journal":{"name":"JMIR Cardio","volume":"9 ","pages":"e67956"},"PeriodicalIF":0.0,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12007723/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143990894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MARIA (Medical Assistance and Rehabilitation Intelligent Agent) for Medication Adherence in Patients With Heart Failure: Empirical Results From a Wizard of Oz Systematic Conversational Agent Design Clinical Protocol.","authors":"Nik Nailah Abdullah, Jia Tang, Hemad Fetrati, Nor Fadhilah Binti Kaukiah, Sahrin Bin Saharudin, Vee Sim Yong, Chia How Yen","doi":"10.2196/55846","DOIUrl":"https://doi.org/10.2196/55846","url":null,"abstract":"<p><strong>Background: </strong>Nonadherence to medication is a key factor contributing to high heart failure (HF) rehospitalization rates. A conversational agent (CA) or chatbot is a technology that can enhance medication adherence by helping patients self-manage their medication routines at home.</p><p><strong>Objective: </strong>This study outlines the conception of a design method for developing a CA to support patients in medication adherence, utilizing design thinking as the primary process for gathering requirements, prototyping, and testing. We apply this design method to the ongoing development of Medical Assistance and Rehabilitation Intelligent Agent (MARIA), a rule-based CA.</p><p><strong>Methods: </strong>Following the design thinking process, at the ideation stage, we engaged a multidisciplinary group of stakeholders (patients and pharmacists) to elicit requirements for the early conception of MARIA. In collaboration with pharmacists, we structured MARIA's dialogue into a workflow based on Adlerian therapy, a psychoeducational theory. At the testing stage, we conducted an observational study using the Wizard of Oz (WoZ) research method to simulate the MARIA prototype with 20 patient participants. This approach validated and refined our application of Adlerian therapy in the CA's dialogue. We incorporated human-likeness and trust scoring into user satisfaction assessments after each WoZ session to evaluate MARIA's feasibility and acceptance of medication adherence. Dialogue data collected through WoZ simulations were analyzed using a coding analysis technique.</p><p><strong>Results: </strong>Our design method for the CA revealed gaps in MARIA's conception, including (1) handling negative responses, (2) appropriate use of emoticons to enhance human-likeness, (3) system feedback mechanisms during turn-taking delays, and (4) defining the extent to which a CA can communicate on behalf of a health care provider regarding medication adherence.</p><p><strong>Conclusions: </strong>The design thinking process provided interactive steps to involve users early in the development of a CA. Notably, the use of WoZ in an observational clinical protocol highlighted the following: (1) coding analysis offered guidelines for modeling CA dialogue with patient safety in mind; (2) incorporating human-likeness and trust in user satisfaction assessments provided insights into attributes that foster patient trust in a CA; and (3) the application of Adlerian therapy demonstrated its effectiveness in motivating patients with HF to adhere to medication within a CA framework. In conclusion, our method is valuable for modeling and validating CA interactions with patients, assessing system reliability, user expectations, and constraints. It can guide designers in leveraging existing CA technologies, such as ChatGPT or AWS Lex, for adaptation in health care settings.</p>","PeriodicalId":14706,"journal":{"name":"JMIR Cardio","volume":"9 ","pages":"e55846"},"PeriodicalIF":0.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12022519/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143983803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Patient and Clinician Perspectives on Alert-Based Remote Monitoring-First Care for Cardiovascular Implantable Electronic Devices: Semistructured Interview Study Within the Veterans Health Administration.","authors":"Allison Kratka, Thomas L Rotering, Scott Munson, Merritt H Raitt, Mary A Whooley, Sanket Dhruva","doi":"10.2196/66215","DOIUrl":"10.2196/66215","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Patients with cardiovascular implantable electronic devices (CIEDs) typically attend in-person CIED clinic visits at least annually, paired with remote monitoring (RM). As the CIED data available through in-person CIED clinic visits and RM are nearly identical, the 2023 Heart Rhythm Society expert consensus statement introduced \"alert-based RM,\" an RM-first approach where patients with CIEDs that are consistently and continuously connected to RM, in the absence of recent alerts and other cardiac comorbidities, could attend in-person CIED clinic visits every 24 months or ultimately only as clinically prompted by actionable events identified on RM. However, there is no published information about patient and clinician perspectives on barriers and facilitators to such an RM-first care model.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;We aimed to understand patient and clinician perspectives about an RM-first care model for CIED care.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We interviewed 40 rural veteran patients who were experienced with RM with CIEDs and 22 CIED clinicians who were experienced in using RM regarding barriers and facilitators to an RM-first care model. We conducted a reflexive thematic analysis of interviews. Two authors familiarized themselves with the dataset and generated separate codebooks based on the interview guides and inductively coded notes. These 2 authors met and reviewed each other's codes, sought additional author input, and resolved differences before 1 author coded the remaining interviews and developed candidate themes. These themes were refined, named, and supported with quotations.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Patients expressed interest in an RM-first approach, to reduce the burden of long travel times, sometimes in inclement weather, and to enable clinicians to provide care for other patients. However, many preferred routine in-person visits; reasons included a skepticism of the capabilities of RM, a sense that in-person visits provided superior care, and enjoyment of in-person patient-clinician relationships. Clinicians were interested in RM-first care, especially for stable, RM-adherent patients who were not device-dependent. Clinicians most frequently cited the benefit of reducing patient travel burden as well as optimizing clinic space and time to focus on other care such as reviewing routine RM transmissions, but also noted barriers including lack of in-person assessment, patient-perceived diminution of the patient-clinician relationship, possible loss to follow-up, and technological difficulties. Clinicians felt that an RM-first care model should be evaluated for success based on patient satisfaction and assessment of timely addressing of rhythm issues to prevent adverse outcomes. Most clinicians believed that RM-first care represented the future of CIED care.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Both patients and CIED clinicians interviewed who were experienced in using RM were open to an","PeriodicalId":14706,"journal":{"name":"JMIR Cardio","volume":"9 ","pages":"e66215"},"PeriodicalIF":0.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11990655/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143784505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}