European heart journal. Digital health最新文献

{"title":"Multi-instance learning with attention mechanism for coronary artery stenosis detection on coronary computed tomography angiography.","authors":"Vibha Gupta, Petur Petursson, Lukas Hilgendorf, Aidin Rawshani, Jan Borén, Truls Råmunddal, Elmir Omerovic, Antros Louca, Oskar Angerås, Justin Schneiderman, Kristofer Skoglund, Deepak L Bhatt, Magnus Kjellberg, Erik Andersson, Carlo Pirazzi, Araz Rawshani","doi":"10.1093/ehjdh/ztaf029","DOIUrl":"10.1093/ehjdh/ztaf029","url":null,"abstract":"<p><strong>Aims: </strong>Accurate detection of coronary artery stenosis (CAS) on coronary computed tomography angiography is vital for saving lives, as timely diagnosis can prevent severe cardiac events. However, this task remains challenging due to data complexity and variability in imaging protocols. Deep learning offers promising potential to automate detection, but robust methods are essential to address real-world challenges effectively and enhance patient outcomes.</p><p><strong>Methods and results: </strong>A total of 900 cases with curved multiplanar reformations, pre-generated during routine clinical workflows, were used to train a multi-instance learning (MIL) model for detecting significant CAS (≥50% luminal obstruction) in the left anterior descending (LAD), right coronary artery (RCA), and left circumflex (LCX), comprising 776 LAD, 694 RCA, and 600 LCX reconstructions. Patient-level predictions utilized attention scores to quantify each slice's contribution, ensuring a robust and interpretable diagnostic approach. The model achieved the best performance for LAD [area under the curve (AUC): 0.92, 95% confidence interval (CI): 0.87-0.96; Brier score: 0.11], followed by RCA (AUC: 0.91, 95% CI: 0.82-0.999; Brier score: 0.09) and LCX (AUC: 0.92, 95% CI: 0.84-0.99; Brier score: 0.07). Calibration was good for LAD but less precise for RCA and LCX. Attention scores enhanced diagnostic precision by focusing on the most relevant slices.</p><p><strong>Conclusion: </strong>This study highlights the potential of MIL models for CAS detection, with remarkable performance in the LAD. By using attention scores, the model effectively identifies key slices from real-world data, seamlessly integrating with routine clinical workflows. Multi-range pre-processing addresses data complexity, enhancing diagnostic accuracy and supporting clinical decision-making.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"6 3","pages":"382-391"},"PeriodicalIF":3.9,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12088718/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144112898","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":"Evaluating large language models in echocardiography reporting: opportunities and challenges.","authors":"Chieh-Ju Chao, Imon Banerjee, Reza Arsanjani, Chadi Ayoub, Andrew Tseng, Jean-Benoit Delbrouck, Garvan C Kane, Francisco Lopez-Jimenez, Zachi Attia, Jae K Oh, Bradley Erickson, Li Fei-Fei, Ehsan Adeli, Curtis Langlotz","doi":"10.1093/ehjdh/ztae086","DOIUrl":"10.1093/ehjdh/ztae086","url":null,"abstract":"<p><strong>Aims: </strong>The increasing need for diagnostic echocardiography tests presents challenges in preserving the quality and promptness of reports. While Large Language Models (LLMs) have proven effective in summarizing clinical texts, their application in echo remains underexplored.</p><p><strong>Methods and results: </strong>Adult echocardiography studies, conducted at the Mayo Clinic from 1 January 2017 to 31 December 2017, were categorized into two groups: development (all Mayo locations except Arizona) and Arizona validation sets. We adapted open-source LLMs (Llama-2, MedAlpaca, Zephyr, and Flan-T5) using In-Context Learning and Quantized Low-Rank Adaptation fine-tuning (FT) for echo report summarization from 'Findings' to 'Impressions.' Against cardiologist-generated Impressions, the models' performance was assessed both quantitatively with automatic metrics and qualitatively by cardiologists. The development dataset included 97 506 reports from 71 717 unique patients, predominantly male (55.4%), with an average age of 64.3 ± 15.8 years. EchoGPT, a fine-tuned Llama-2 model, outperformed other models with win rates ranging from 87% to 99% in various automatic metrics, and produced reports comparable to cardiologists in qualitative review (significantly preferred in conciseness (<i>P</i> < 0.001), with no significant preference in completeness, correctness, and clinical utility). Correlations between automatic and human metrics were fair to modest, with the best being RadGraph F1 scores vs. clinical utility (<i>r</i> = 0.42) and automatic metrics showed insensitivity (0-5% drop) to changes in measurement numbers.</p><p><strong>Conclusion: </strong>EchoGPT can generate draft reports for human review and approval, helping to streamline the workflow. However, scalable evaluation approaches dedicated to echo reports remains necessary.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"6 3","pages":"326-339"},"PeriodicalIF":3.9,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12088711/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144112611","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":"The Role of Cardiovascular Disease Journals in Reporting Sex and Gender in Research.","authors":"C Noel Bairey Merz, Robert O Bonow, Mercedes Carnethon, Filippo Crea, Joseph A Hill, Harlan M Krumholz, Roxana Mehran, Erica S Spatz","doi":"10.1093/ehjdh/ztaf022","DOIUrl":"10.1093/ehjdh/ztaf022","url":null,"abstract":"","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"6 3","pages":"315-316"},"PeriodicalIF":3.9,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12088709/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144112822","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 six-lead portable electrocardiogram device for detecting left ventricular systolic dysfunction: a prospective single-centre cohort study.","authors":"Jaehyun Lim, Hak Seung Lee, Ga In Han, Sora Kang, Jong-Hwan Jang, Yong-Yeon Jo, Jeong Min Son, Min Sung Lee, Joon-Myoung Kwon, Seung-Pyo Lee","doi":"10.1093/ehjdh/ztaf025","DOIUrl":"10.1093/ehjdh/ztaf025","url":null,"abstract":"<p><strong>Aims: </strong>The real-world effectiveness of the artificial intelligence model based on electrocardiogram (AI-ECG) signals from portable devices for detection of left ventricular systolic dysfunction (LVSD) requires further exploration.</p><p><strong>Methods and results: </strong>In this prospective, single-centre study, we assessed the diagnostic performance of AI-ECG for detecting LVSD using a six-lead hand-held portable device (AliveCor KardiaMobile 6L). We retrained the AI-ECG model, previously validated with 12-lead ECG, to interpret the 6-lead ECG inputs. Patients aged 19 years or older underwent six-lead ECG recording during transthoracic echocardiography. The primary outcome was the area under the receiver operating characteristic curve (AUROC) for detecting LVSD, defined as an ejection fraction below 40%. Of the 1716 patients recruited prospectively, 1635 were included for the final analysis (mean age 60.6 years, 50% male), among whom 163 had LVSD on echocardiography. The AI-ECG model based on the six-lead portable device demonstrated an AUROC of 0.924 [95% confidence interval (CI) 0.903-0.944], with 83.4% sensitivity (95% CI 77.8-89.0%) and 88.7% specificity (95% CI 87.1-90.4%). Of the 1079 patients evaluated using the AI-ECG model based on the conventional 12-lead ECG, the AUROC was 0.962 (95% CI 0.947-0.977), with 90.1% sensitivity (95% CI 85.0-95.2%) and 91.1% specificity (95% CI 89.3-92.9%).</p><p><strong>Conclusion: </strong>The AI-ECG model constructed with the six-lead hand-held portable ECG device effectively identifies LVSD, demonstrating comparable accuracy to that of the conventional 12-lead ECG. This highlights the potential of hand-held portable ECG devices leveraged with AI as efficient tools for early LVSD screening.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"6 3","pages":"476-485"},"PeriodicalIF":3.9,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12088721/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144112682","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":"Virtual reality for pre-procedural planning of valve-in-valve transcatheter aortic valve implantation.","authors":"Dominika Kanschik, Jafer Haschemi, Kathrin Klein, Oliver Maier, Stephan Binneboessel, Ursala Tokhi, Shazia Afzal, Patrick W Serruys, Tsung-Ying Tsai, Gerald Antoch, Artur Lichtenberg, Christina Ballázs, Dmytro Stadnik, Maximilian Scherner, Malte Kelm, Tobias Zeus, Christian Jung","doi":"10.1093/ehjdh/ztaf024","DOIUrl":"10.1093/ehjdh/ztaf024","url":null,"abstract":"<p><strong>Aims: </strong>Valve-in-valve transcatheter aortic valve implantation (ViV-TAVI) has proven to be an effective treatment option for high-risk patients with degenerated surgical bioprosthetic aortic valves. Multislice computed tomography (MSCT) analysis, the current gold standard for procedural planning, has certain limitations. Virtual reality (VR) could optimize pre-procedural planning by delivering three-dimensional (3D) patient-specific information. This study aimed to investigate the feasibility of visualizing the bioprosthesis and adjacent structures with VR, as well as the accuracy and reproducibility of VR measurements and their advantages and limitations in planning ViV-TAVI.</p><p><strong>Methods and results: </strong>The visualizations and measurements were performed using 3mensio software and VR software by analysts blinded to the results of the other software based on MSCT data from 20 patients who underwent ViV-TAVI interventions. Moreover, eight physicians graded numerous aspects of pre-procedural ViV-TAVI planning with and without VR visualizations. The analysis showed no significant differences between the measurements and strong correlations with correlation coefficients between 0.874 and 0.994, <i>P</i> < 0.001. Moreover, good-to-excellent intra- and interobserver reliability with intraclass correlation coefficient values between 0.897 and 0.986 was documented. The qualitative analysis showed that 3D visualization using VR facilitates assessing the spatial relationships between the structures. Furthermore, VR enabled a superior visual understanding of the bioprosthesis and the distances between the virtual prosthesis and the coronaries as well as the sinotubular junction.</p><p><strong>Conclusion: </strong>Virtual reality can be a valuable addition to the pre-procedural planning of ViV-TAVI interventions, thanks to detailed 3D visualization and precise measurements. Further studies are needed to assess the impact on patient outcomes.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"6 3","pages":"372-381"},"PeriodicalIF":3.9,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12088716/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144112902","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":"Explainable artificial intelligence for stroke risk stratification in atrial fibrillation.","authors":"Raquel Mae Zimmerman, Edgar J Hernandez, Martin Tristani-Firouzi, Mark Yandell, Benjamin A Steinberg","doi":"10.1093/ehjdh/ztaf019","DOIUrl":"10.1093/ehjdh/ztaf019","url":null,"abstract":"<p><p>Current risk stratification tools can limit the optimal implementation of new and emerging therapies for patients with heart rhythm disorders. For example, stroke prevention treatments have outpaced means for stroke risk stratification for patients with atrial fibrillation (AF). Artificial intelligence (AI) techniques have shown promise for improving various tasks in cardiovascular medicine. Here, we explain key concepts in AI that are central to using these technologies for better risk stratification, highlighting one approach particularly well suited to the task of portable, personalized risk stratification-probabilistic graphical models (PGMs). Probabilistic graphical models can empower physicians to ask and answer a variety of clinical questions, which we demonstrate using a preliminary model of AF-related stroke risk among 1.6 million patients within the University of Utah Health System. This example also highlights the ability of PGMs to combine social determinants of health and other non-traditional variables with standard clinical and demographic ones to improve personalized risk predictions and address risk factor interactions. When combined with electronic health data, these computational technologies hold great promise to empower personalized, explainable, and equitable risk assessment.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"6 3","pages":"317-325"},"PeriodicalIF":3.9,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12088725/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144112775","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 hybrid algorithm-based ECG risk prediction model for cardiovascular disease.","authors":"Pan Zhou, Zhao Yang, Yiming Hao, Fangfang Fan, Wenlang Zhao, Ziyu Wang, Qiuju Deng, Yongchen Hao, Na Yang, Lizhen Han, Pingping Jia, Yue Qi, Yan Zhang, Jing Liu","doi":"10.1093/ehjdh/ztaf023","DOIUrl":"10.1093/ehjdh/ztaf023","url":null,"abstract":"<p><strong>Aims: </strong>Little is known about the role of electrocardiography (ECG) in the community population independent of physical and laboratory examinations. Thus, this study developed and validated several ECG-based models for cardiovascular disease (CVD) risk assessment, with or without simple questionnaire-based variables.</p><p><strong>Methods and results: </strong>Using a derivation cohort of 3734 Chinese participants aged ≥40 years, we developed the ECG-based models to predict the risk of developing CVD (comprising fatal and non-fatal coronary heart disease, unstable angina, stroke, and heart failure). Candidate predictors associated with CVD were screened from hundreds of ECG characteristics using a hybrid algorithm. By incorporating the questionnaire-based predictors, we constructed the ECG-questionnaire model. All models were tested in an external validation cohort (<i>n</i> = 1224) to determine their discrimination and calibration. Over a maximum follow-up of 7 years, 433 CVD events occurred in the derivation cohort. The ECG model with 37 selected features achieved comparable performance concerning the clinical model using traditional cardiovascular risk factors (<i>C</i>-statistic: 0.690, 95% confidence interval [CI]: 0.638-0.743) in the external validation cohort. Such performance significantly improved when the questionnaire-based predictors were added (<i>C</i>-statistic: 0.734, 95% CI: 0.685-0.784; calibration χ²: 3.334, <i>P</i> = 0.950). Compared with the clinical model, 17.4% of the participants were correctly assigned to the corresponding risk groups, with an absolute integrated discrimination index of 0.048 (95% CI: 0.016-0.080).</p><p><strong>Conclusion: </strong>The ECG model with/without questionnaire-based variables can accurately predict future CVD risk independent of physical and laboratory examinations, suggesting its great potential in routine clinical practice.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"6 3","pages":"466-475"},"PeriodicalIF":3.9,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12088724/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144112587","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":"Racial and ethnic disparities in aortic stenosis within a universal healthcare system characterized by natural language processing for targeted intervention.","authors":"Dhruva Biswas, Jack Wu, Sam Brown, Apurva Bharucha, Natalie Fairhurst, George Kaye, Kate Jones, Freya Parker Copeland, Bethan O'Donnell, Daniel Kyle, Tom Searle, Nilesh Pareek, Rafal Dworakowski, Alexandros Papachristidis, Narbeh Melikian, Olaf Wendler, Ranjit Deshpande, Max Baghai, James Galloway, James T Teo, Richard Dobson, Jonathan Byrne, Philip MacCarthy, Ajay M Shah, Mehdi Eskandari, Kevin O'Gallagher","doi":"10.1093/ehjdh/ztaf018","DOIUrl":"10.1093/ehjdh/ztaf018","url":null,"abstract":"<p><strong>Aims: </strong>Aortic stenosis (AS) is a condition marked by high morbidity and mortality in severe, symptomatic cases without intervention via transcatheter aortic valve implantation (TAVI) or surgical aortic valve replacement (SAVR). Racial and ethnic disparities in access to these treatments have been documented, particularly in North America, where socioeconomic factors such as health insurance confound analyses. This study evaluates disparities in AS management across racial and ethnic groups, accounting for socioeconomic deprivation, using an artificial intelligence (AI) framework.</p><p><strong>Methods and results: </strong>We conducted a retrospective cohort study using a natural language processing pipeline to analyse both structured and unstructured data from > 1 million patients at a London hospital. Key variables included age, sex, self-reported race and ethnicity, AS severity, and socioeconomic status. The primary outcomes were rates of valvular intervention and all-cause mortality. Among 6967 patients with AS, Black patients were younger, more symptomatic, and more comorbid than White patients. Black patients with objective evidence of AS on echocardiography were less likely to receive a clinical diagnosis than White patients. In severe AS, TAVI and SAVR procedures were performed at lower rates among Black patients than among White patients, with a longer time to SAVR. In multivariate analysis of severe AS, controlling for socioeconomic status, Black patients experienced higher mortality (hazard ratio = 1.42, 95% confidence interval = 1.05-1.92, <i>P</i> = 0.02).</p><p><strong>Conclusion: </strong>An AI framework characterizes racial and ethnic disparities in AS management, which persist in a universal healthcare system, highlighting targets for future healthcare interventions.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"6 3","pages":"392-403"},"PeriodicalIF":3.9,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12088714/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144112868","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":"Deep learning on electrocardiogram waveforms to stratify risk of obstructive stable coronary artery disease.","authors":"Rishi K Trivedi, I Min Chiu, John Weston Hughes, Albert J Rogers, David Ouyang","doi":"10.1093/ehjdh/ztaf020","DOIUrl":"10.1093/ehjdh/ztaf020","url":null,"abstract":"<p><strong>Aims: </strong>Coronary artery disease (CAD) incidence continues to rise with an increasing burden of chronic coronary disease (CCD). Current probability-based risk assessment for obstructive CAD (oCAD) lacks sufficient diagnostic accuracy. We aimed to develop and validate a deep learning (DL) algorithm utilizing electrocardiogram (ECG) waveforms and clinical features to predict oCAD in patients with suspected CCD.</p><p><strong>Methods and results: </strong>The study includes subjects undergoing invasive angiography for evaluation of CCD over a 4-year period at a quaternary care centre. oCAD was defined as performance of percutaneous coronary intervention (PCI) based on assessment by interventional cardiologists during elective angiography. DL models were developed for ECG waveforms alone (DL-ECG), clinical features from standard risk scores (DL-Clinical), and the combination of ECG waveforms and clinical features (DL-MM); a commonly used pre-test probability estimation tool from the CAD Consortium study was used for comparison (CAD2) [3]. The CAD2 model [AUC 0.733 (0.717-0.750)] had similar performance as the DL-Clinical model [AUC 0.762 (0.746-0.778)]. The DL-ECG model [AUC 0.741 (0.726-0.758)] had similar performance as both the clinical feature models. The DL-MM model [AUC 0.807 (0.793-0.822)] had a superior performance. Validation in an external cohort demonstrated similar performance in the DL-MM [AUC 0.716 (0.707-0.726)] and CAD2 risk score [AUC 0.715 (0.705-0.724)].</p><p><strong>Conclusion: </strong>A multi-modality DL model utilizing ECG waveforms and clinical risk factors can improve prediction of oCAD in CCD compared with risk-factor based models. Prospective research is warranted to determine whether incorporating DL methods in ECG analysis improves diagnosis of oCAD and outcomes in CCD.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"6 3","pages":"456-465"},"PeriodicalIF":3.9,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12088713/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144112700","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":"Unsupervised clustering of single-lead electrocardiograms associates with prevalent and incident heart failure in coronary artery disease.","authors":"Josseline Madrid, William J Young, Stefan van Duijvenboden, Michele Orini, Patricia B Munroe, Julia Ramírez, Ana Mincholé","doi":"10.1093/ehjdh/ztaf013","DOIUrl":"10.1093/ehjdh/ztaf013","url":null,"abstract":"<p><strong>Aims: </strong>Clinical consequences of coronary artery disease (CAD) are varied [e.g. atrial fibrillation (AF) and heart failure (HF)], and current risk stratification tools are ineffective. We aimed to identify clusters of individuals with CAD exhibiting unique patterns on the electrocardiogram (ECG) in an unsupervised manner and assess their association with cardiovascular risk.</p><p><strong>Methods and results: </strong>Twenty-one ECG markers were derived from single-lead median-beat ECGs of 1928 individuals with CAD without a previous diagnosis of AF, HF, or ventricular arrhythmia (VA) from the imaging study in UK Biobank (CAD-IMG-UKB). An unsupervised clustering algorithm was used to group these markers into distinct clusters. We characterized each cluster according to their demographic and ECG characteristics, as well as their prevalent and incident risk of AF, HF, and VA (4-year median follow-up). Validation and association with prevalent diagnoses were performed in an independent cohort of 1644 individuals. The model identified two clusters within the CAD-IMG-UKB cohort. Cluster 1 (<i>n</i> = 359) exhibited prolonged QRS duration and QT intervals, along with greater morphological variations in QRS and T-waves, compared with Cluster 2 (<i>n</i> = 1569). Cluster 1, relative to Cluster 2, had a significantly higher risk of incident HF [hazard ratio (HR): 2.40, 95% confidence interval (CI): 1.51-3.83], confirmed by independent validation (HR: 1.77, CI: 1.31-2.41). It also showed a higher association with prevalent HF (odds ratio: 4.10, CI: 2.02-8.29), independent of clinical risk factors.</p><p><strong>Conclusion: </strong>Our approach identified a cluster of individuals with CAD sharing ECG characteristics indicating HF risk, holding significant implications for targeted treatment and prevention enabling accessible large-scale screening.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"6 3","pages":"435-446"},"PeriodicalIF":3.9,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12088720/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144112826","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}