European heart journal. Digital health最新文献

{"title":"Automated echocardiographic detection of mitral valve prolapse and mitral regurgitation with video-based artificial intelligence algorithms.","authors":"Minhaj U Ansari, Joshua P Barrios, Lionel Tastet, Rohit Jhawar, Luca Cristin, Amy Rich, Dwight Bibby, Qizhi Fang, Farzin Arya, Valentina Crudo, Thuy Nguyen, Dipan J Shah, Francesca N Delling, Geoffrey H Tison","doi":"10.1093/ehjdh/ztag061","DOIUrl":"10.1093/ehjdh/ztag061","url":null,"abstract":"<p><strong>Aims: </strong>We aimed to develop and evaluate fully automated artificial intelligence (AI) system for detection of mitral valve prolapse (MVP) and mitral regurgitation (MR) from echocardiographic studies.</p><p><strong>Methods and results: </strong>We used a dataset of 24 869 echocardiographic studies from the University of California San Francisco (UCSF) to train a multi-view deep neural network (DNN) to detect MVP using apical four-chamber, two-chamber, and parasternal long-axis views. A separate dataset of 27 906 studies from UCSF was used to train a second multi-view DNN model to detect moderate-to-severe or severe MR using colour Doppler in the same views. External validation was performed on echocardiographic MVP videos from Houston Methodist Hospital. The DNN model for MVP detection achieved an area under the receiver operating characteristic curve (AUC) of 0.917 [95% confidence interval (CI): 0.899-0.934], with stronger performance in those with mitral annular disjunction (MAD) or bileaflet MVP. External validation for MVP detection in a geographically and demographically distinct population yielded an AUC of 0.835 (95% CI: 0.803-0.869). The DNN for detection of moderate-to-severe or severe MR in patients with concurrent MVP achieved an AUC of 0.877 (95% CI: 0.805-0.939).</p><p><strong>Conclusion: </strong>Artificial intelligence algorithms can perform automatic detection of MVP and clinically significant MR from echocardiogram studies with high performance. The MVP DNN performed particularly well for more severe MVP phenotypes such as MAD or bileaflet MVP. These algorithms could provide a novel approach for automated, accurate, and rapid diagnosis of MVP and its common clinical sequelae across institutions.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 5","pages":"ztag061"},"PeriodicalIF":4.4,"publicationDate":"2026-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13184616/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147984592","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":"Automated assessment of right ventricular systolic function from coronary angiograms with video-based artificial intelligence algorithms: development, validation, comparison against humans, and prospective deployment.","authors":"Fatima Zahra Fawzi, Istok Menkovic, Nicolas Dostie, Maxime Tremblay-Gravel, Marie-Claude Parent, Gabriel Asslo, Jean-François Tanguay, Guillaume Marquis-Gravel, Minhaj Ansari, Joshua P Barrios, Geoffrey H Tison, Jacques Delfrate, Robert Avram","doi":"10.1093/ehjdh/ztag059","DOIUrl":"10.1093/ehjdh/ztag059","url":null,"abstract":"<p><strong>Aims: </strong>Right ventricular systolic function (RVSF) is a critical determinant of cardiovascular outcomes, yet assessment during coronary angiography remains challenging without prior imaging. We developed and validated DeepRV, a deep learning model predicting RVSF from routine coronary angiograms.</p><p><strong>Methods and results: </strong>DeepRV, a video-based deep neural network, was developed using 8053 coronary angiography studies from 6923 patients at Montreal Heart Institute (2017-23), with RVSF determined by echocardiography. The model was externally validated at the University of California, San Francisco, and prospectively deployed during primary percutaneous coronary intervention (PCI) for ST-segment elevation myocardial infarction (STEMI). In the internal test set (<i>n</i> = 1586; 10.5% reduced RVSF), DeepRV achieved area under the receiver operating characteristic curve (AUROC) 0.80 [95% confidence interval (CI): 0.76-0.84], sensitivity 70.5%, specificity 78.5%, and negative predictive value 95.8%. External validation demonstrated AUROC 0.75 (95% CI: 0.72-0.77) on the UCSF dataset (<i>n</i> = 2247 studies; 30% reduced RVSF). Prospective deployment of DeepRV during STEMI cases at our institution (<i>n</i> = 82) achieved AUROC 0.83 (95% CI: 0.71-0.93) using post-PCI angiogram with a median 5.1 s inference time. In a human performance evaluation (<i>n</i> = 200), artificial intelligence (AI) assistance improved accuracy of identifying RVSF for cardiologists (72.1-77.6%) and medical students (43.5-64.0%). Artificial intelligence alone achieved the highest accuracy (79.5%) and sensitivity (70.0%), while cardiologists with AI achieved the highest specificity (84.6%).</p><p><strong>Conclusion: </strong>DeepRV enables automated RVSF assessment from routine coronary angiograms and enhances diagnostic accuracy across experience levels. Real-time inference and open-weight availability support its potential as a point-of-care tool for risk stratification during coronary angiography.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 4","pages":"ztag059"},"PeriodicalIF":4.4,"publicationDate":"2026-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13174274/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147966063","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":"Open science requires trust and rigour: a framework for responsible evaluation of shared AI-ECG tools.","authors":"Lovedeep S Dhingra, Philip M Croon, Evangelos K Oikonomou, Rohan Khera","doi":"10.1093/ehjdh/ztag057","DOIUrl":"10.1093/ehjdh/ztag057","url":null,"abstract":"","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 4","pages":"ztag057"},"PeriodicalIF":4.4,"publicationDate":"2026-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13080934/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147701078","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":"ECG Sex Index in children and adolescents.","authors":"Tolga Hayit, Ibrahim Karabayir, David Herrington, Robert L Davis, Oguz Akbilgic","doi":"10.1093/ehjdh/ztag058","DOIUrl":"10.1093/ehjdh/ztag058","url":null,"abstract":"<p><p>The electrocardiographic sex index (ESI) was developed in adults to capture continuous electrocardiogram (ECG) features associated with biological sex, but its behaviour in children, whose ECG morphology changes substantially through growth and puberty, has not been characterized. We applied the adult-derived ESI model to 61 930 paediatric ECGs from the University of Tennessee Health Science Center clinical population (ages 0-18 years). ESI values were examined by single-year age and stratified by sex and race. Age-related patterns were summarized using mean estimates with 95% confidence intervals, distributional analyses across broader age groups, and the prevalence of extreme sex-typical values (ESI ≥0.8 in males; ≤0.2 in females). In early childhood, ESI values were tightly clustered around 0.5 in both sexes. Beginning in late childhood and becoming more pronounced through adolescence, ESI increased in males and decreased in females, producing a widening separation that plateaued in mid-to-late adolescence, a pattern that was consistent across racial subgroups. Distributional analyses showed parallel shifts in ESI distributions, with older males enriched for higher values and older females enriched for lower values, and threshold-based analyses revealed similar divergence, with the proportions of males with ESI ≥0.8 and females with ESI ≤0.2 both increasing sharply during adolescence. Although derived from adult data, ESI thus exhibits age and sex-dependent patterns in children that align with known developmental trajectories of ECG morphology, indicating that ESI tracks physiological maturation across childhood and adolescence and providing a foundation for evaluating its clinical and biological significance in younger populations.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 4","pages":"ztag058"},"PeriodicalIF":4.4,"publicationDate":"2026-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13131988/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147824353","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":"Artificial intelligence-enhanced electrocardiogram for the detection of rheumatic heart disease.","authors":"Raeesa Bhorat, David M Harmon, Kan Liu, Jennifer Dugan, Christie Ngo, Paul A Friedman, Herman Bagula, Mpiko Ntsekhe, Zachi I Attia","doi":"10.1093/ehjdh/ztag056","DOIUrl":"10.1093/ehjdh/ztag056","url":null,"abstract":"<p><strong>Aims: </strong>Rheumatic heart disease (RHD) remains the most prevalent acquired cardiovascular disease among young adults in developing countries, and there is a critical need for an efficient, affordable, and available screening strategy to detect RHD in these resource-limited areas. The 12-lead electrocardiogram (ECG) is a ubiquitous, inexpensive diagnostic tool, and application of artificial intelligence to the ECG (AI-ECG) has allowed for screening of various cardiovascular pathologies.</p><p><strong>Methods and results: </strong>Patients aged >18 years with severe RHD with at least one transthoracic echocardiogram and one standard 12-lead ECG performed at Groote Schuur Hospital, Cape Town, within 180 days of each other were eligible. A total of 920 RHD patients were identified, with 2199 corresponding controls from the same medical centre. Patients were allocated to derivation (80%), validation (10%), and testing (10%) groups, respectively. The AI-ECG to detect RHD from a standard 12-lead ECG was built using the Keras framework under Tensorflow backend. In the test group, the AI-ECG for RHD exhibited strong algorithm performance with an AUC of 0.890 (95% Confidence Interval 0.848-0.940) and an accuracy of 83.8%. The algorithm remained robust between RHD presentation: mitral valve alone (AUC 0.913) and mixed mitral and aortic valve disease (AUC 0.858). There were minor performance differences in the subgroup analysis of patient sex, age, and ECG characteristics.</p><p><strong>Conclusion: </strong>In this study, an AI-ECG algorithm was successfully developed to screen for advanced RHD from a standard 12-lead ECG, and the AI-ECG performance remained acceptable across most subgroups, including RHD manifestation, patient sex, age <70 years, and ECG characteristics.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 4","pages":"ztag056"},"PeriodicalIF":4.4,"publicationDate":"2026-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13131984/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147824166","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":"Prediction of vasovagal syncope using artificial intelligence-enabled smartwatch photoplethysmography-derived heart rate variability.","authors":"Hak Seung Lee, Junho Song, Moonki Jung, Yong-Yeon Jo, Joon-Myoung Kwon, Jun Hwan Cho","doi":"10.1093/ehjdh/ztag053","DOIUrl":"10.1093/ehjdh/ztag053","url":null,"abstract":"<p><strong>Aims: </strong>Vasovagal syncope (VVS) can cause injury and impaired quality of life, and effective prevention requires timely warning before loss of consciousness. To evaluate whether smartwatch photoplethysmography (PPG)-derived heart rate variability (HRV) can predict VVS before symptom onset, and to identify an optimal observation window and lead time.</p><p><strong>Methods and results: </strong>We prospectively enrolled 132 patients with suspected neurally mediated syncope who underwent head-up tilt (HUT) testing while wearing a wrist-worn Samsung Galaxy Watch 6 for continuous multiwavelength PPG acquisition (25 Hz). The HRV features (<i>n</i> = 107) were extracted. An Extra Trees classifier (600 trees) was trained using an 80/20 subject-level split and evaluated on a hold-out test set. Model performance was assessed using AUROC and threshold metrics, including specificity, at a fixed sensitivity of 0.90. Sixty-three participants were HUT-positive, and 69 were HUT-negative. The 5-min presyncope window achieved the highest discrimination (AUROC, 0.91; 95% CI 0.77-1.00). At 90% sensitivity, specificity was 0.64 (95% CI 0.40-0.85). Using a fixed 5-min window, early prediction remained robust at a 5-min lead time (AUROC 0.91; 95% CI 0.76-1.00; accuracy 84.6%; 95% CI 0.65-0.92). The most informative predictors included nonlinear complexity metrics (approximate entropy and composite multiscale entropy) and autonomic balance indices (normalized low-frequency, log-transformed high-frequency, and the cardiac vagal index).</p><p><strong>Conclusion: </strong>Artificial intelligence-enabled analysis of smartwatch PPG-derived HRV can prospectively predict VVS during HUT using a short 5-min observation window while maintaining clinically meaningful performance at a 5-min lead time, supporting the feasibility of wearable, real-time warning systems.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 4","pages":"ztag053"},"PeriodicalIF":4.4,"publicationDate":"2026-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13131986/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147824346","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":"AI-driven voltage map analysis for optimizing catheter ablation strategy in atrial fibrillation: a proof-of-concept study.","authors":"Takeshi Tohyama, Kazuo Sakamoto, Tomomi Nagayama, Hirotake Yokoyama, Tsukasa Watanabe, Yasushi Mukai, Shunsuke Kawai, Daisuke Yakabe, Hiroshi Mannoji, Kazuhiro Nagaoka, Atsushi Tanaka, Mitsutaka Yamamoto, Kiyohiro Ogawa, Takeshi Mikami, Shujiro Inoue, Susumu Takase, Kei Inoue, Kazuya Hosokawa, Koji Todaka, Hiroyuki Tsutsui, Kohtaro Abe","doi":"10.1093/ehjdh/ztag054","DOIUrl":"10.1093/ehjdh/ztag054","url":null,"abstract":"<p><strong>Aims: </strong>Pulmonary vein isolation (PVI) has been established as the standard catheter ablation (CA) strategy for atrial fibrillation (AF). However, approximately 20-40% of patients experience recurrence after CA. Although three-dimensional (3D) maps generated during CA provide valuable electrophysiological information, they may not be fully utilized in clinical decision-making. To develop an artificial intelligence (AI) model that analyses 3D voltage maps and long-term AF recurrence to guide best practices in CA for AF.</p><p><strong>Methods and results: </strong>A dedicated multicentre registry recording detailed CA data for AF and recurrence was used to develop the AI model. The model was designed to evaluate the completion of PVI and ablation beyond-PVI (be-PVI), considering future AF recurrence with the need for additional PVI and be-PVI interventions. The AI model was trained and validated via fivefold cross-validation with 1268 maps. It effectively stratified cases for predicting 1-year AF recurrence after CA (<i>P</i> < 0.001) and identified those likely to benefit from additional ablations (PVI: <i>P</i> = 0.032, be-PVI: <i>P</i> < 0.001, and a combination of PVI and be-PVI: <i>P</i> < 0.001).</p><p><strong>Conclusion: </strong>The developed AI model predicts AF recurrence based on the completion of PVI and be-PVI and accurately identifies patients who may require further intervention. AI analysis of intraoperative 3D maps could guide optimal CA strategy planning, considering long-term AF recurrence.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 4","pages":"ztag054"},"PeriodicalIF":4.4,"publicationDate":"2026-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13131983/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147824119","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":"Development and validation of clinical prediction models for personalized renal function monitoring in people with heart failure in primary care: the RENAL-HF study protocol.","authors":"Alexandar Vincent-Paulraj, Matthew J Carr, David A Jenkins, Bertram Muller-Myhsok, Mark Devonald, Jay Wright, Nefyn Williams, Niels Peek, Munir Pirmohamed, Darren M Ashcroft","doi":"10.1093/ehjdh/ztag055","DOIUrl":"10.1093/ehjdh/ztag055","url":null,"abstract":"<p><strong>Aims: </strong>Heart failure (HF) is a growing problem in society with an ageing population and many patients with heart failure are affected by renal dysfunction. The RENAL-HF project aims to develop predictive risk models to support personalized renal function monitoring and treatment in patients with HF in primary care.</p><p><strong>Methods and results: </strong>This study will use electronic health records from the Clinical Practice Research Datalink (CPRD) database for patients who were diagnosed with HF. We will develop three prediction models-Mixed-effects model, Growth mixture model, and recurrent neural network-long short-term memory model to predict future worsening renal function, including events that lead to hospitalization, and death. Using an internal-external validation approach based on geographic region, we will choose the top-performing model using various metrics to evaluate the predictive performance.</p><p><strong>Conclusion: </strong>This protocol provides a detailed description of the methods used for developing and validating prognostic models for personalized renal function monitoring in people with HF in primary care.</p><p><strong>Protocol registration: </strong>The study and use of CPRD data were approved by the Independent Scientific Advisory Committee for Clinical Practice Research Datalink research (<b>Protocol Number: 22_001794).</b></p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 4","pages":"ztag055"},"PeriodicalIF":4.4,"publicationDate":"2026-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13131987/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147824258","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 pilot study on AI-based voice analysis for monitoring patients hospitalized with acute decompensated heart failure.","authors":"Leonhard Riehle, Mariam Fouad, Marcus Hott, Emanuel Heil, Chong Bin Lee, Felix Schoenrath, Soumya Vungarala, Bruce Johnson, Lyle Olson, Aurele Goetz, Filipe Barata, Nicholas Cummins, Gerhard Hindricks, Felix Hohendanner","doi":"10.1093/ehjdh/ztag052","DOIUrl":"10.1093/ehjdh/ztag052","url":null,"abstract":"<p><strong>Aims: </strong>Monitoring pulmonary congestion in chronic heart failure (HF) reduces decompensation and hospitalization, but conventional methods such as weight and symptom tracking are often unreliable. As fluid accumulation affects the lungs and vocal tract, subtle voice alterations may serve as a non-invasive signal for early detection of worsening HF.</p><p><strong>Methods and results: </strong>The Voice Analysis for Monitoring Patients with HF trial (VAMP-HF, NCT06566911) prospectively enrolled 104 patients hospitalized with acute decompensated HF (ADHF) across two academic centres in the USA and Germany. Daily voice recordings were collected from admission to discharge, with breathing features extracted from speech and acoustic features from sustained vowels. A machine-learning model was trained to classify recordings as admission-phase vs. discharge-phase using leave-one-patient-out. Patients with clinical deterioration, insufficient audio quality, or short length of stay were excluded. Seventy-nine patients were included in the final dataset. The model classified admission and discharge with an <i>F</i> ₁-score of 0.83 (95% CI: 0.77-0.90; AUC = 0.90). In patients with higher audio volume (<i>N</i> = 54), performance reached 0.89 (95% CI: 0.82-0.94; AUC = 0.91). When applied to intermediate hospitalization days, model-predicted scores showed progressive increases from admission towards discharge. Performance remained robust irrespective of significant weight loss during hospitalization.</p><p><strong>Conclusion: </strong>In this pilot study, structured voice and breathing analysis discriminated hospitalization phase from admission through discharge in patients with ADHF. This non-invasive approach captured progressive changes during the hospital course and warrants further investigation with concurrent objective congestion markers to establish physiological specificity.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 6","pages":"ztag052"},"PeriodicalIF":4.4,"publicationDate":"2026-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13326637/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148378194","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":"Study design of the InTakeCare trial: a digital health solution to monitor and improve medication adherence in hypertensive patients.","authors":"Emanuele Tauro, Alessandra Gorini, Martina Vigorè, Lucia Zanotti, Alessandro Croce, Martino F Pengo, Davide Soranna, Antonella Zambon, Gianfranco Parati, Enrico Gianluca Caiani, Grzegorz Bilo","doi":"10.1093/ehjdh/ztag051","DOIUrl":"10.1093/ehjdh/ztag051","url":null,"abstract":"<p><strong>Aims: </strong>The InTakeCare Trial aims to develop, implement, and clinically validate a novel digital health solution (DHS) to improve medication adherence (MA) in patients with arterial hypertension. This initiative responds to the global issue of poor MA to long-term pharmacological treatments, compromising patient outcomes and increasing healthcare costs.</p><p><strong>Methods and results: </strong>This study is structured as a multidisciplinary, single-centre, randomized, open, blinded-endpoint clinical trial. In the preliminary phase, focus groups and a survey are conducted to develop patient personas and fictional archetypes that represent real people in the development of interventions, informing the personalization of a mobile application for patients and a web dashboard for physicians. The developed DHS is designed to deliver tailored reminders, health messages, and real-time monitoring of MA. After a pilot usability phase, 206 hypertensive patients will be randomized to standard care or active intervention for a 3-month period, followed by a 2-month observational phase to assess the persistence of intervention effects on adherence. MA is measured via direct (e.g. plasma drug levels) and indirect (e.g. self-reports) methods, alongside ambulatory blood pressure monitoring and behavioural engagement scales.</p><p><strong>Conclusion: </strong>This study offers a novel, theory-informed framework for the design of personalized DHS in chronic disease management. Leveraging user-centred design and machine learning-driven persona classification, InTakeCare introduces a scalable, evidence-based solution that addresses individual variability in adherence behaviours. The trial's findings are expected to generate insights into the efficacy, usability, and acceptability of personalized DHS in routine clinical practice, providing a replicable model for future DHS in other chronic conditions.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 4","pages":"ztag051"},"PeriodicalIF":4.4,"publicationDate":"2026-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13131980/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147824411","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}