European heart journal. Digital health最新文献

{"title":"From wrist to heart: clinical validation and real-world translation of wearable and portable AI-enhanced electrocardiography.","authors":"Ahmed El-Medany, Aidan René Birdi, Aron Abraham, Tanush Pandey, Arunashis Sau, Sadia Khan, Fu Siong Ng","doi":"10.1093/ehjdh/ztag155","DOIUrl":"https://doi.org/10.1093/ehjdh/ztag155","url":null,"abstract":"<p><p>Wearable and portable electrocardiogram (ECG) devices are shifting cardiovascular monitoring beyond clinician-directed testing, driven by consumer-led self-monitoring, remote care, and preventive cardiology. Artificial intelligence (AI) may enhance the value of these devices by supporting automated interpretation, but clinical translation remains uneven. This narrative review synthesises current evidence on AI-enhanced ECG (AI-ECG) analysis in wearable and portable systems, with emphasis on the gap between technical performance and real-world implementation. Although many advances have been developed using conventional 12-lead ECG datasets, deployment in wearable and portable devices introduces additional challenges related to device-specific signal acquisition, preprocessing, domain shift, and user-led recording. Evidence is most mature for atrial fibrillation detection, while applications across conduction disease, other arrhythmias, structural phenotypes, and prognostic assessment remain earlier in development and are supported by fewer prospective, device-specific evaluations. Across the field, retrospective and dataset-based studies predominate, with limited evidence that improved detection translates into better patient outcomes or health-system efficiency. Future research should evaluate performance using the intended device, population, and clinical pathway, and determine whether AI-ECG changes management without increasing unnecessary investigation or workload. Establishing clinical value, rather than improving classification accuracy alone, will determine the role of wearable and portable AI-ECG in routine cardiovascular care.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 8","pages":"ztag155"},"PeriodicalIF":4.4,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658271/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186598","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 in cardiovascular medicine: a practical guide for clinicians and researchers.","authors":"Christian Basile, Alessandro Villaschi, Pasquale Ambrosino, Mario Enrico Canonico, Araz Rawshani, Emanuele Bobbio","doi":"10.1093/ehjdh/ztag153","DOIUrl":"10.1093/ehjdh/ztag153","url":null,"abstract":"<p><p>Artificial intelligence (AI) is transforming cardiovascular medicine by extracting clinically relevant patterns from complex digital health data, extending beyond traditional statistical approaches. However, the translation of AI from proof-of-concept studies to routine cardiovascular care remains constrained by methodological, ethical, and regulatory challenges. Key barriers include data quality and representativeness, model generalizability, calibration and clinical utility, interpretability, and the risk of bias amplification. To address this gap, this review synthesizes current evidence on AI applications in cardiology, demystifies foundational machine learning concepts for a clinical audience, and outlines a practical framework for best practices in model development, evaluation, and responsible clinical deployment.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 8","pages":"ztag153"},"PeriodicalIF":4.4,"publicationDate":"2026-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13644533/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139354","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 age prediction using a transformer trained on diverse global electrocardiograms.","authors":"Laurenz Berger, Kristina Preuer, Christoph Gross, Max Haberbusch, Mohammad Azizzadeh, Noemi Pavo, Marie-Kathrin Breyer, Francesco Moscato","doi":"10.1093/ehjdh/ztag149","DOIUrl":"https://doi.org/10.1093/ehjdh/ztag149","url":null,"abstract":"<p><strong>Aims: </strong>Artificial intelligence (AI) models trained on electrocardiograms (ECGs) can estimate age, with deviations from chronological age (Δage) serving as markers of accelerated cardiovascular ageing. We evaluated whether transformer-based AI models trained on globally diverse, heterogeneous ECG datasets outperform convolutional neural network (CNN)-based models in generalizability and physiological interpretability.</p><p><strong>Methods and results: </strong>Using 11 public datasets (435 203 recordings) from four continents and an independent external cohort (14 462 recordings), we trained and validated transformer and CNN architectures. The transformer model trained on global data achieved strong correlation with chronological age and maintained robust performance in the external cohort (<i>r</i> = 0.90), outperforming both a CNN trained on global data and a model trained exclusively on a homogenous population-based cohort (<i>r</i> = 0.88). Individuals with Δage ≥+8 years exhibited a two-fold increased mortality risk (hazard ratio = 2.08, 95% confidence interval 1.93-2.24). Explainability analysis identified the P-wave, particularly in lead V1, as the dominant contributor to age prediction, consistent with known electrophysiological changes associated with atrial remodelling and ageing. The model's attribution to early atrial conduction features was consistent across age strata, peaking in midlife (30-50 years), and correlated positively with disease burden, including hypertension and smoking.</p><p><strong>Conclusion: </strong>Our findings establish that transformer models trained on globally heterogeneous data generalize well and can provide insights to plausible ageing signatures. Furthermore, Δage may offer insight into underlying physiological ageing processes and associated risk, though further validation is needed to define its clinical utility in risk stratification.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 8","pages":"ztag149"},"PeriodicalIF":4.4,"publicationDate":"2026-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13652029/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149169151","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":"Transportability of an artificial intelligence electrocardiography model for structural heart disease: external validation and recalibration of EchoNext-Mini in MIMIC-IV.","authors":"Emmanuel Otabor, Abdulraheem Hassan, Ayoyimika Okunlola, Justin Lam, Laith Alomari, Michael Hamilton","doi":"10.1093/ehjdh/ztag147","DOIUrl":"10.1093/ehjdh/ztag147","url":null,"abstract":"<p><strong>Aims: </strong>Structural heart disease is often underdiagnosed, and echocardiography is limited by access and referral thresholds. Artificial intelligence electrocardiography (AI-ECG) may identify echocardiographically defined structural heart disease. EchoNext-Mini is a released AI-ECG model, accompanied by a benchmark dataset, that detects a composite structural heart disease outcome and component conditions from 12-lead electrocardiogram waveforms together with age, sex, and electrocardiographic measurements. We assessed its transportability and recalibration.</p><p><strong>Methods and results: </strong>We linked electrocardiograms from MIMIC-IV to subsequent transthoracic echocardiograms, including adults whose electrocardiogram preceded an eligible echocardiogram within one year, one per patient. Labels were mapped to structured echocardiographic fields using original thresholds where available, harmonized definitions otherwise. The released model was applied without retraining to this cohort and its benchmark test set, then assessed for discrimination, calibration, recalibration, subgroups, and label sensitivity. Among 45 878 patients, structural heart disease prevalence was 47.2%. Composite area under the receiver operating characteristic curve was 0.790 (95% confidence interval, 0.786 to 0.794), against 0.820 on the benchmark test set. Component values ranged from 0.679 for left ventricular wall thickness to 0.837 for right ventricular dysfunction. The composite was near-calibrated (slope, 0.93), whereas all component probabilities overestimated risk in both settings. A shift derived from the released training prevalences, requiring no local outcome data, largely corrected it.</p><p><strong>Conclusion: </strong>EchoNext-Mini transported to MIMIC-IV with composite discrimination within the published external-validation range. Component probabilities behaved as ranking scores rather than absolute risks, a property of the released model rather than the validation setting, and require adjustment before use as risk estimates.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 8","pages":"ztag147"},"PeriodicalIF":4.4,"publicationDate":"2026-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13617667/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149077113","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 to support clinical practice across the inpatient heart failure care pathway: a systematic review.","authors":"Elias V Wolf, Miriam Grapp, Mechthild Hartmann, Hans-Christoph Friederich, Till Johannes Bugaj","doi":"10.1093/ehjdh/ztag151","DOIUrl":"10.1093/ehjdh/ztag151","url":null,"abstract":"<p><p>Heart failure is a complex clinical syndrome requiring repeated reassessment, close monitoring, and timely treatment decisions throughout hospitalization. With the increasing emergence of artificial intelligence applications, there is growing interest in how artificial intelligence-based tools may support physicians along the inpatient heart failure care pathway. This systematic review assessed artificial intelligence applications supporting adult patients with heart failure from admission through inpatient management to discharge. The review followed PRISMA guidelines and was prospectively registered in PROSPERO (CRD420261336670). PubMed, Web of Science, and Embase were searched through February 2026. Eligible studies evaluated artificial intelligence-based interventions or tools relevant to inpatient heart failure care. Studies limited to intensive care, isolated imaging settings, classic telemedicine, or theoretical prediction models without demonstrated clinical use were excluded. Study selection was performed using Covidence, and methodological quality was assessed with STROBE criteria for observational studies and RoB 2 for randomized controlled trials. 19 studies were included, comprising 16 observational studies and three randomized controlled trials. Seven studies addressed admission, four inpatient management, and eight discharge-related applications. During admission, artificial intelligence mainly supported early recognition of heart failure and reduced ejection fraction, with the strongest evidence for ECG-based models. In inpatient care, applications were heterogeneous and supported clinical decision-making, patient identification, and medication adherence prediction, using electronic health record-derived data. At discharge, large language models and digital tools mainly supported patient education and self-management, although limited actionability and implementation barriers remained. Artificial intelligence may support inpatient heart failure care, but evidence of measurable clinical benefit remains limited. <b>Trial Registration</b> PROSPERO: CRD420261336670.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 8","pages":"ztag151"},"PeriodicalIF":4.4,"publicationDate":"2026-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13644536/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139412","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":"Preoperative troponin and the interpretation of perioperative myocardial injury prediction.","authors":"Güney Sarıoğlu","doi":"10.1093/ehjdh/ztag150","DOIUrl":"10.1093/ehjdh/ztag150","url":null,"abstract":"","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 8","pages":"ztag150"},"PeriodicalIF":4.4,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13621176/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149083185","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 digital tools in heart failure: results in three London hospital networks (Qual-HF).","authors":"Kyle McBeath, Jillian P Riley, Martin R Cowie","doi":"10.1093/ehjdh/ztag146","DOIUrl":"10.1093/ehjdh/ztag146","url":null,"abstract":"<p><strong>Aims: </strong>There are limited data on the experience and perspectives of patients or clinicians about the use of digital tools (DTs, such as internet resources, social media, and smartphone apps) in heart failure (HF). This study aimed to explore patient and clinician perspectives of DT use and provide insights into the factors that facilitate or obstruct such use.</p><p><strong>Methods and results: </strong>This was a mixed-methods study using semi-structured interviews with 14 people living with HF and 9 clinicians working as HF specialists. Recorded interviews underwent thematic analysis. Three main themes emerged: 'the dual nature of information', the 'recommendation gap', and 'self-care as a time-dependent behaviour'. Patients were generally fearful of information from DTs, with many disengaging from their use as a form of self-preservation. Patients described finding the 'right' information as a struggle, and their behaviour appeared related to their level of digital health literacy and degree of activation. Recommendation of DTs by clinicians was influenced by assumptions around the digital the capability of patients, the lack of evidence-based guideline recommendations, and a lack of local or international consensus around the use of DTs.</p><p><strong>Conclusion: </strong>Many patients living with HF are anxious about online information and withdraw from using DTs. A clinician's recommendation may help, providing an 'information prescription', but is limited by assumptions about patients and lack of training, local consensus, and clear international guidance. Routine assessment of digital capability, particularly in older patients, may balance some of these assumptions and support more consistent and equitable use.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 8","pages":"ztag146"},"PeriodicalIF":4.4,"publicationDate":"2026-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13617663/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149077110","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":"Diagnostic performance of artificial intelligence-enabled electrocardiography for pulmonary hypertension: a systematic review and meta-analysis.","authors":"Karan Raj Nazareth, Eyad Jamileh, Fahad Muhammad, Omar Farooq, Anisha Sequeira, Alishba Awais, Ibrahim Antoun","doi":"10.1093/ehjdh/ztag143","DOIUrl":"https://doi.org/10.1093/ehjdh/ztag143","url":null,"abstract":"<p><p>Pulmonary hypertension (PH) is a progressive, under-recognized condition with substantial morbidity and mortality. Its non-specific presentation and multimodal diagnostic pathway contribute to delayed diagnosis. Artificial intelligence (AI)-enabled electrocardiography (ECG) may offer a scalable approach to case finding. This PRISMA-DTA systematic review and meta-analysis was registered in PROSPERO (CRD420251241142). MEDLINE, Embase, Web of Science, Scopus, and IEEE Xplore were searched through July 2026, with Google Scholar and citation searching used as supplementary sources. Eligible studies evaluated AI-enabled ECG in adults against right-heart catheterization (RHC)-confirmed PH or echocardiographic PH-related phenotypes. Two reviewers independently screened studies, extracted data, and assessed risk of bias using QUADAS-2. One ECG-only area under the receiver operating characteristic curve (AUROC) per study was pooled using a random-effects model. Seven retrospective studies were included; six contributed to meta-analysis. The pooled AUROC was 0.885 (95% CI 0.855-0.915), with very high heterogeneity (I² = 98.68%; <i>P</i> < 0.0001). The estimate combined heterogeneous RHC, echocardiographic, and clinical-echocardiographic definitions and therefore did not represent accuracy for uniformly RHC-confirmed PH. Four studies performed external validation. Multimodal models outperformed ECG alone in two studies but were excluded from pooling. AI-enabled ECG shows promising discrimination for PH-related targets, but current evidence is retrospective and heterogeneous. It should be considered an investigational case-finding or triage aid rather than a definitive diagnostic stand-alone rule-out test.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 8","pages":"ztag143"},"PeriodicalIF":4.4,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13637041/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119164","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-based ECG as a triage tool for acute myocardial infarction: a diagnostic systematic review and meta-analysis.","authors":"Giulia Caldeira Gaelzer, Pedro Gomes Batista, Marcela Vasconcelos Montenegro, Railla Raquel Albino Dos Santos Silva, Mushrin Malik, Maria Leticia Carnielli Tebet, Caroline O Fischer-Bacca, Juliana Giorgi, Gustavo Lenci Marques","doi":"10.1093/ehjdh/ztag075","DOIUrl":"10.1093/ehjdh/ztag075","url":null,"abstract":"<p><p>Early identification of acute myocardial infarction (AMI) remains challenging, particularly in non-ST-segment elevation presentations and occluded myocardial infarction, where conventional electrocardiogram (ECG) interpretation has limited sensitivity. Artificial intelligence-enabled ECG (AI-ECG) has emerged as a promising strategy to enhance early triage and diagnostic accuracy. To systematically evaluate the diagnostic performance of AI-enabled ECG algorithms for the detection of AMI, including ST-segment elevation myocardial infarction (STEMI) and non-ST-segment elevation myocardial infarction (NSTEMI), across diverse clinical settings. This diagnostic systematic review and meta-analysis was conducted in accordance with PRISMA guidelines and registered in PROSPERO (CRD420261292271). PubMed, Embase, and Cochrane CENTRAL were searched through January 2026. Studies evaluating AI-based ECG models for AMI detection and reporting sufficient data to reconstruct 2 × 2 contingency tables were included. Pooled sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were estimated using random-effects models (restricted maximum likelihood). Summary receiver operating characteristic (SROC) curves and area under the curve (AUC) were generated. Pre-specified subgroup analyses were performed for STEMI and NSTEMI Ten observational studies comprising 94 510 participants were included. For overall AMI detection,. AI-ECG demonstrated a pooled sensitivity of 89.4% (95% CI, 79.7-94.8) and specificity of 96% (95% CI, 91.2-98.2). The pooled NPV was 98.7% (95% CI, 94.1-99.7), and the pooled PPV was 73.3% (95% CI, 50.2-88.2). The SROC AUC was 0.97 (95% CI, 0.92-0.98). In STEMI, pooled sensitivity and specificity were 94.4% and 97.5%, respectively (AUC 0.98). In NSTEMI, pooled sensitivity was lower at 65.0%, with specificity of 87.5% and an AUC of 0.71. Heterogeneity was substantial, particularly among NSTEMI cohorts. AI-enabled ECG demonstrates high sensitivity and consistently excellent negative predictive value for AMI detection, supporting its role as a scalable, non-invasive triage adjunct at first medical contact. These findings highlight the potential of AI-ECG to facilitate early rule-out strategies and improve prioritization of patients requiring urgent ischaemic evaluation. Beyond diagnostic accuracy, AI-ECG may support probabilistic risk stratification and integration into early clinical decision-making pathways.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 7","pages":"ztag075"},"PeriodicalIF":4.4,"publicationDate":"2026-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13525340/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148857994","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":"Subtype specific artificial intelligence modelling of cardiac amyloidosis using echocardiography and electrocardiography.","authors":"Jose K James, Surendra Dasari, Jennifer M Amadio, Christopher G Scott, Eli Muchtar, Morie A Gertz, Shaji Kumar, Francis K Buadi, David Dingli, Taxiarchis V Kourelis, Itzhak Z Attia, Francisco Lopez-Jimenez, Omar AbouEzzeddine, Dennis H Murphree, Paul A Friedman, Martha Grogan, Angela Dispenzieri","doi":"10.1093/ehjdh/ztag121","DOIUrl":"10.1093/ehjdh/ztag121","url":null,"abstract":"<p><strong>Aims: </strong>We aimed to develop and validate echocardiography-based prediction models for light chain (AL) and transthyretin (ATTR) cardiac amyloidosis and to quantify the incremental value of integrating artificial intelligence-derived electrocardiography (ECG) probabilities.</p><p><strong>Methods and results: </strong>We conducted a retrospective, multisite study within a single health system including patients with AL or ATTR cardiac amyloidosis and matched control subjects. AL and ATTR cohorts were handled independently. For each subtype, patients were randomly split into training and test cohorts, with an additional temporally distinct test cohort. Logistic regression models were developed using structured echocardiographic variables with parsimonious core and extended feature sets, as well as models integrating these features with a previously validated AI ECG probability. Model performance was assessed using receiver operating characteristic and precision-recall (PR) analyses. In AL amyloidosis, echocardiography-based models demonstrated moderate discrimination in the primary test cohort (area under the PR curve, AUPRC 0.674) but were inferior to ECG alone (AUPRC 0.824, <i>P</i> < 0.001), with no significant improvement from model combination (AUPRC 0.841 vs. ECG, <i>P</i> = 0.267). In contrast, for ATTR amyloidosis, echocardiography alone (AUPRC 0.687) performed worse than ECG (AUPRC 0.745, <i>P</i> = 0.140), while the combined model showed substantial improvement (AUROC 0.845, <i>P</i> < 0.001). Absolute performance declined in temporally distinct cohorts, but AUPRC comparisons were preserved.</p><p><strong>Conclusion: </strong>Subtype-specific echocardiography-based models demonstrate robust discrimination for cardiac amyloidosis, with divergent contributions of echocardiographic features by subtype. These results support tailored modelling strategies and prospective concurrent deployment of AL and ATTR models.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 7","pages":"ztag121"},"PeriodicalIF":4.4,"publicationDate":"2026-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13524381/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148852104","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}