European heart journal. Digital health最新文献

{"title":"A digital health program enhances walking capacity and health status in symptomatic peripheral artery disease.","authors":"Vishal Amlani, Bartosz Dobies, Carl-Magnus Wahlgren, Manne Andersson, Birgitta Sigvant, Anders Gottsäter, Moncef Zarrouk, Olga Nilsson, Hallur Hallsson, Linda Karlsdottir, Sæmundur Oddsson, Tryggvi Thorgeirsson, Joakim Nordanstig","doi":"10.1093/ehjdh/ztag072","DOIUrl":"10.1093/ehjdh/ztag072","url":null,"abstract":"<p><strong>Aims: </strong>Intermittent claudication (IC) is the most common manifestation of peripheral artery disease (PAD), an atherosclerotic condition associated with high cardiovascular morbidity and mortality. Management targets cardiovascular risk reduction and limb function, but effective non-invasive treatments for limb symptoms remain limited. The aim of this prospective, multicentre randomized controlled trial was to evaluate whether a 12-week multimodal smartphone-based digital health programme improves walking capacity and symptoms in patients with IC.</p><p><strong>Methods and results: </strong>The IPAD trial compared standard care alone with standard care plus a 12-week digital health intervention focused on lifestyle modification and physical activity, incorporating behavioural change techniques and gamification. The primary observer-blinded endpoint was maximum walking distance (MWD) during a 6-min walk test (6MWT), contextualized against minimal clinically important difference thresholds. Secondary endpoints included pain-free 6MWT distance and health-related quality of life (HRQoL). Over 21 months, 155 patients were randomized 1:1. Mean (SD) age was 71.8 (7.6) years. Compared with controls, the intervention group showed greater improvement in MWD (+21.44 m; 95% confidence interval [CI] 6.00-36.87; <i>P</i> = 0.007), exceeding the predefined 12-m MCID at the group level, and in pain-free walking distance (+32.95 m; 95% CI 0.68-65.23; <i>P</i> = 0.045). The relative risk of achieving an individual 12-m MCID did not differ between groups (risk ratio [RR] 1.27; 95% CI 0.91-1.76; <i>P</i> = 0.162). Exploratory analysis using a 20.1-m MCID showed a higher proportion of patients achieving the MCID in the intervention group (RR 1.97; 95% CI 1.16-3.34; <i>P</i> = 0.012). HRQoL improved nominally, with a between-group benefit on the EuroQol-5 Dimensions visual analogue scale (+6.29 points; 95% CI 1.33-11.20; <i>P</i> = 0.013).</p><p><strong>Conclusion: </strong>The digital health programme resulted in a clinically meaningful improvement in walking capacity in PAD patients with IC.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 5","pages":"ztag072"},"PeriodicalIF":4.4,"publicationDate":"2026-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13215472/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148058810","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":"Novel machine learning fusion architectures integrating electrocardiogram representations: applications to acute coronary event detection.","authors":"Rui Qi Ji, Nathan T Riek, Tanmay Gokhale, Zeineb Bouzid, Karina Kraevsky, Jessica K Zègre-Hemsey, Samir Saba, Christian Martin-Gill, Clifton W Callaway, Murat Akcakaya, Ervin Sejdić, Salah S Al-Zaiti","doi":"10.1093/ehjdh/ztag062","DOIUrl":"10.1093/ehjdh/ztag062","url":null,"abstract":"<p><strong>Aims: </strong>AI in electrocardiography (ECG) has diverged into two paths: traditional signal processing with machine learning, and deep learning of raw waveforms. The former preserves physiological interpretability but may miss novel patterns, while the latter overlooks a century of ECG science. No framework yet integrates both. This study introduces a fusion model combining handcrafted feature-based random forest and waveform-based convolutional neural network to improve the diagnosis of acute coronary events.</p><p><strong>Methods and results: </strong>This prospective, multicentre cohort study included pre-hospital ECGs recorded on emergency medical services from patients with a chief complaint of chest pain. Using this dataset, we developed four fusion frameworks that integrate ECG features with waveform information: (1) decision-level fusion combining predictions from random forest and convolutional neural network (CNN); (2) decision-level fusion with retraining; (3) feature-level fusion by concatenating CNN embeddings with ECG features; and (4) feature-level fusion combining CNN embeddings with tree-level outputs from the random forest. This study comprised of 10 393 ECGs from 7397 patients. On both outcomes, acute coronary syndrome and occlusion myocardial infarction, the proposed decision fusion with retraining (Approach 2) achieved an AUROC of 0.878 (95% CI, 0.837-0.915) and 0.961 (95% CI, 0.934-0.983) on the test set and an average precision score of 0.749 (95% CI, 0.681-0.810) and 0.850 (95% CI, 0.763-0.918), respectively, outperforming all other proposed fusion and individual models.</p><p><strong>Conclusion: </strong>This study demonstrates the significance of fusion models that integrate complementary ECG representations to improve diagnostic accuracy in acute coronary events, highlighting a promising approach for real-time AI-augmented cardiovascular disease detection across diverse use cases.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 5","pages":"ztag062"},"PeriodicalIF":4.4,"publicationDate":"2026-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13188221/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147990089","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 model for genotype prediction from echocardiographic videos in non-ischaemic dilated cardiomyopathy.","authors":"Yuko Kiyohara, Seito Fukagawa, Seitaro Nomura, Satoshi Kodera, Koki Nakanishi, Takashi Hiruma, Ryo Abe, Shunsuke Inoue, Junichi Ishida, Eisuke Amiya, Masaru Hatano, Hiroyuki Morita, Norihiko Takeda, Issei Komuro","doi":"10.1093/ehjdh/ztag068","DOIUrl":"10.1093/ehjdh/ztag068","url":null,"abstract":"<p><strong>Aims: </strong>Non-ischaemic dilated cardiomyopathy (DCM) is frequently characterized by the presence of pathogenic germline variants, and genotype positivity predicts poor prognosis. Despite its importance, genetic testing remains underutilized in the current era. Therefore, we aimed to develop a deep learning model to predict genotype positivity using echocardiographic videos.</p><p><strong>Methods and results: </strong>We included patients who were diagnosed with DCM and had genetic testing at the University of Tokyo Hospital, Japan, consecutively from 2014 to 2022. The apical four-chamber views of echocardiographic videos were collected. First, we developed a deep learning model based on the EchoNet-Dynamic model, and the area under the curve (AUC) was computed. Second, we calculated the Madrid genotype score (clinical scoring system) for each case. Third, we developed a logistic regression model that combined the Madrid genotype score and the deep learning model. Finally, we compared the AUC of the combined model with that of the Madrid genotype score alone by DeLong's test. Out of the 258 patients, 117 patients (45.3%) had genetic variants, and 141 (54.7%) did not. <i>TTN</i> (30.8%) was the most common genotype, followed by <i>LMNA</i> (18.8%). The deep learning model yielded an AUC of 0.64. The Madrid genotype score was well validated and achieved an AUC of 0.73. The combined model yielded an AUC of 0.76 with a significant improvement from the Madrid genotype score alone (<i>P</i> = 0.03).</p><p><strong>Conclusion: </strong>The deep learning model demonstrated modest discriminative ability to predict genotype positivity using echocardiographic videos. The accuracy of the clinical scoring system improved when combined with the deep learning model.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 5","pages":"ztag068"},"PeriodicalIF":4.4,"publicationDate":"2026-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13188222/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147990087","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 full-text screening and accelerated reviews using large language models with context-aware agents: an exploratory analysis in biomarker research.","authors":"Yongxin Ye, Martina Colombo, Jennifer Meessen, Negin Hajizadeh, Lauren De Vore, Hajar Ghaem Sigarchian, Christof Peters, Supraja Krovvidi, Shloke Meresh, Laurent Hasson, SaiRamesh Jakka, Benoit Tyl","doi":"10.1093/ehjdh/ztag070","DOIUrl":"10.1093/ehjdh/ztag070","url":null,"abstract":"<p><strong>Aims: </strong>Artificial intelligence (AI) tools utilizing large language models (LLMs) can accelerate scientific literature reviews by automating title, abstract, and full-text-based screenings of relevant patient populations and biomarkers. We developed an AI-based tool to automate and improve full-text screening performance using LLMs to accurately identify relevant publications that meet complex criteria.</p><p><strong>Methods and results: </strong>We conducted a literature review utilizing the Population, Intervention-biomarkers, Comparison, Outcome framework to define our inclusion and exclusion criteria, focusing on biomarkers in heart failure with reduced ejection fraction (HFrEF). An AI-based full-text screening tool was created to process 5405 selected publications, combining multi-level and task-oriented retrieval-augmented generation (RAG) and agent-based methods, establishing ground truth standards to evaluate performance metrics both for the tool and human reviewers. Intra-LLM reliability was assessed by rerunning screenings on a batch of publications. Among the public and private domain models, LLaMA 3.3 70B was selected for its superior accuracy (82%), precision (71%), and recall (100%) in screening 49 manuscripts by LLMs. During the training phase, based on several hundred manuscripts, performance metrics significantly improved. Validation results showed a sensitivity of 91.4%, specificity of 53.2%, a false positive rate of 46.8%, and a false negative rate of 8.6%. The LLM outperformed human reviewers in F1 score and interrater reliability, achieving 100% consistency across multiple runs, with each run consisting of multiple LLMs on 1000 documents.</p><p><strong>Conclusion: </strong>Our study demonstrated that AI tool can reduce labour-intensive efforts while maintaining accuracy in literature reviews, with greater inter-rater agreement compared to human reviewers.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 5","pages":"ztag070"},"PeriodicalIF":4.4,"publicationDate":"2026-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193579/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148019169","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 Rlign algorithm for enhanced electrocardiogram analysis through heart rate-corrected ECG alignment for explainable classification and clustering.","authors":"Lucas Plagwitz, Lucas Bickmann, Michael Fujarski, Alexander Brenner, Warnes Gobalakrishnan, Lars Eckardt, Antonius Büscher, Julian Varghese","doi":"10.1093/ehjdh/ztag067","DOIUrl":"10.1093/ehjdh/ztag067","url":null,"abstract":"<p><strong>Aims: </strong>Electrocardiogram (ECG) recordings are fundamental for diagnosing cardiac conditions. Recent advances in automatic ECG analysis have been dominated by deep learning, particularly convolutional neural networks (CNNs). CNNs excel in processing high-dimensional signal data, where their ability to automatically extract complex features has enabled significant progress. However, while CNNs are powerful for biomedical signal analysis, their application to ECG data also carries disadvantages, such as the requirement for large annotated datasets and limited explainability. To address these challenges, we aim to reintroduce shallow learning methods, such as linear classifiers, by leveraging the cyclic nature of ECG signals.</p><p><strong>Methods and results: </strong>We developed an adaptive transformation that restructures ECG signals into a fully structured format suitable for shallow learning algorithms. This method aligns R-peaks across all signals in a dataset and resamples the inter-QRS segments to match a predefined reference heart rate. The approach was systematically evaluated across tasks including classification, clustering, and explainability. Our transformation substantially improved the performance of shallow learning techniques. Compared with CNN approaches, shallow models trained on transformed ECGs achieved superior accuracy and interpretability in data-limited scenarios.</p><p><strong>Conclusion: </strong>We demonstrate that shallow machine learning methods, when combined with our alignment-based transformation, can reach CNN level performance in ECG analysis, especially under conditions of limited training data. This approach offers clear advantages in classification, clustering, and explainability and provides an accessible alternative to deep learning. To facilitate adoption and further research, we release a publicly available framework for ECG signal alignment at https://github.com/imi-ms/rlign.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 5","pages":"ztag067"},"PeriodicalIF":4.4,"publicationDate":"2026-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13184624/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147984588","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":"Respiratory signal extraction from the electrocardiogram for risk stratification in cardiac patients.","authors":"Viktoria Sanders, Ruben Alejandro Amort, Petra Barthel, Alexander Müller, Julia Allescher, Michael Dommasch, Helene Hildegard Heidegger, Eimo Martens, Manuel Rattka, Arne M Müller, Karl-Ludwig Laugwitz, Georg Schmidt, Daniel Sinnecker, Alexander Steger","doi":"10.1093/ehjdh/ztag060","DOIUrl":"10.1093/ehjdh/ztag060","url":null,"abstract":"<p><p>Respiration is a fundamental vital sign and an established marker of disease severity and mortality risk, particularly in patients with cardiovascular disease. Despite its prognostic significance, respiratory monitoring remains underused in routine clinical practice and remote telemonitoring. At the same time, advances in biosignal processing enable robust extraction of respiratory information from the ubiquitous electrocardiogram, allowing respiratory assessment without additional sensors. This review highlights respiration as an underused biosignal in cardiovascular medicine and summarizes physiological principles and technical approaches for electrocardiogram-derived respiration, including respiratory sinus arrhythmia, respiration-related QRS amplitude modulations, and electrical axis shifts. It emphasizes the potential of electrocardiogram-derived respiration-especially nocturnal respiratory rate-in cardiac patients to enhance risk stratification and guide clinical decision-making, including patient selection for implantable cardioverter-defibrillator therapy. The feasibility of integrating nocturnal respiratory rate monitoring into standard surveillance of cardiac patients is discussed, alongside emerging evidence that this marker may identify patients with limited benefit from prophylactic implantable cardioverter-defibrillator therapy. The technical possibility to derive respiration from routine electrocardiographic recordings represents a significant yet under-utilized opportunity. Electrocardiogram-derived respiratory rate is a promising scalable non-invasive biomarker for individualized risk stratification and may complement conventional indicators such as left-ventricular ejection fraction. Large-scale prospective randomized trials are now needed to establish whether incorporating electrocardiogram-derived respiratory markers into routine practice can improve patient outcomes and optimize therapy allocation.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 5","pages":"ztag060"},"PeriodicalIF":4.4,"publicationDate":"2026-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13182715/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147977562","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":"Cardio amyloid-artificial intelligence: advanced multi-modal screening for transthyretin cardiac amyloidosis in severe aortic stenosis patients.","authors":"Nusrat Binta Nizam, Ashley N Beecy, Jacob W Groenendyk, Fengbei Liu, Nelson I Barrera, Chris Kelsey, David vanMaanan, Jeffrey Ruhl, Naomi Tesfuzigta, Ilan Richter, Mathew S Maurer, Gabriel Sayer, Deborah Estrin, Parag Goyal, Nir Uriel, Mert R Sabuncu","doi":"10.1093/ehjdh/ztag064","DOIUrl":"10.1093/ehjdh/ztag064","url":null,"abstract":"<p><strong>Aims: </strong>Early detection is important given the availability of new disease-modifying therapies and the high prevalence of transthyretin amyloid cardiomyopathy (ATTR-CM) among patients with aortic stenosis (AS) undergoing transcatheter aortic valve replacement (TAVR). We developed a multi-modal artificial intelligence (AI) model for early detection of ATTR-CM using chest computed tomography (CT), echocardiography, and electrocardiography. This approach may provide a scalable strategy for preclinical monitoring.</p><p><strong>Methods and results: </strong>This retrospective study included patients who underwent technetium-99m-pyrophosphate (PYP) scintigraphy at two academic medical centres: Columbia University Irving Medical Center and Weill Cornell Medicine. ATTR-CM status was determined using a composite reference standard incorporating PYP scan interpretation, laboratory tests, and endomyocardial biopsy results when available. The diagnostic performance of the model was measured by the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and predictive values at various thresholds. Among 816 patients (median age 79.0 years, 61.2% male), 127 (15.6%) had confirmed ATTR-CM. Patients with ATTR-CM were older, more often male, and had characteristic echocardiographic features, including increased wall thickness and reduced ejection fraction. In the independent TAVR test cohort, the multi-modal AI model achieved an AUROC of 0.85 [95% confidence interval (CI): 0.74-0.93], significantly outperforming single-modality approaches in our data. At the optimal threshold, the model demonstrated 73.3% sensitivity, 82.9% specificity, and 96% negative predictive value.</p><p><strong>Conclusion: </strong>A multi-modal AI approach using routinely acquired chest CT, echocardiography, and electrocardiography data can enable screening for ATTR-CM in TAVR patients, potentially facilitating earlier diagnosis and treatment initiation.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 6","pages":"ztag064"},"PeriodicalIF":4.4,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13347972/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148426920","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":"Applications of artificial intelligence and computational approaches to imaging for hypertension identification, phenotyping, and outcome prediction: a systematic review.","authors":"Mohanad Alkhodari, Prenali D Sattwika, Hannah R Cutler, George Milner, Turkay Kart, Leontios J Hadjileontiadis, Ahsan H Khandoker, Adam J Lewandowski, Winok Lapidaire, Abhirup Banerjee, Paul Leeson","doi":"10.1093/ehjdh/ztag063","DOIUrl":"10.1093/ehjdh/ztag063","url":null,"abstract":"<p><p>Current hypertension guidelines focus on blood pressure control, but incorporating end-organ imaging could improve understanding of disease manifestations. We undertook a systematic review to evaluate current task-level applications of artificial intelligence (AI) and computational approaches to imaging for hypertension identification, phenotyping, and outcome prediction. A systematic search was conducted across multiple databases up to end of December 2025. Retrieved studies were grouped by AI task, and a thematic qualitative analysis per-task was conducted to evaluate organ-specific findings, AI methodologies, and research gaps. For quantitative synthesis, the I2 statistic derived from Cochran's Q test was used to assess heterogeneity, and forest plots were generated to visualize effect sizes. The review was registered with PROSPERO (CRD42023427430). The search strategy yielded 48 studies. Thematic analysis categorized the studies into five major tasks, with the majority employing supervised learning for classification processes. Nearly half of the studies focused on the heart. However, paucity of studies performed multi-organ assessment, external validation, and phenotyping or predicting future risk. AI and computational approaches in imaging achieved an overall sensitivity of 0.84 [0.69-0.93] in identifying hypertension from normotension, highest with brain imaging. Sensitivity reached 0.92 [0.90-0.94] in discriminating hypertension from hypertrophic cardiomyopathy. Current research focusses primarily on hypertension prediction using single organ information. While results are promising, datasets remain small with limited external validation. There remains a need for discovery-oriented research to uncover disease heterogeneity, multi-organ phenotypes, and support personalized and targeted interventions.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 4","pages":"ztag063"},"PeriodicalIF":4.4,"publicationDate":"2026-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13175042/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147966091","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 breaking the learning curve for echocardiography: a secondary analysis of a multicentre trial.","authors":"Caroline Schissel, Daniel Trotzky, Noa Avisar, Talia Amar, Itay Kezurer, Dan Spiegelstein, Christopher W Baugh, Nicole M Duggan, Sachin Shah, Sarju Ganatra, Sourbha Dani, Andrew Goldsmith","doi":"10.1093/ehjdh/ztag065","DOIUrl":"10.1093/ehjdh/ztag065","url":null,"abstract":"<p><strong>Aims: </strong>The integration of point-of-care ultrasound (POCUS) by non-specialists and the shortage of trained sonographers highlights the need for scalable training approaches. This study aimed to evaluate the learning curve of novice operators performing artificial intelligence (AI)-guided limited transthoracic echocardiography (TTE) and to assess whether acquired images were sufficient for diagnostic interpretation of structural cardiac disease.</p><p><strong>Methods and results: </strong>In this multicentre, prospective secondary analysis, nine novice operators performed limited TTE scans on 159 patients using a handheld device with AI-based acquisition guidance. Following eight hours of standardized training, novices independently obtained six standard TTE views. Three blinded expert reviewers graded image quality on a 1-5 scale and assessed diagnostic adequacy. Image scores were used to generate learning curves, and subgroup analyses examined the influence of patient characteristics. Of 954 novice-acquired images, 97.7% met the diagnostic threshold (score ≥3). After training, all operators achieved mean scores ≥3 across patients. AI-guidance consistently enabled high-quality imaging across all views, with minimal impact from sex, age, or pathology. Body mass index (BMI) showed a significant effect (<i>P</i> = 0.0029), though all subgroups exceeded diagnostic thresholds: 4.44 ± 0.17 (BMI <18), 4.40 ± 0.04 (18-24), 4.12 ± 0.12 (25-29), and 4.07 ± 0.07 (>30). Experts reliably ruled out left ventricular dysfunction (99.4%) and hypertrophy (98.7%); agreement was lower for wall motion abnormalities (80.7%) and atrial dilation (86.6%).</p><p><strong>Conclusion: </strong>Novices with no prior POCUS experience achieved diagnostic-quality TTE images after one day of AI-guided training. AI may supplement conventional echocardiography training, and future research should evaluate its integration into routine clinical workflows.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 4","pages":"ztag065"},"PeriodicalIF":4.4,"publicationDate":"2026-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13175043/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147966049","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 adoption in French cardiovascular care: a multiprofessional survey of barriers and facilitators.","authors":"Nabil Bouali, Séverine Domart, Walid Amara, Christophe Laure, Floran Begue, Johann Reisberg, Thierry Garban, Guillaume Bailly, Simon Viscogliosi, Chaimae Aboueddahab, Soundous M'Rabet, Sébastien Hascoet, Guillaume Baudry, Manveer Singh, Youssef Lakhal, Paul Lucain, Gauthier Beuque, Philippe Régnier, Antonin Trimaille, Marc Villaceque, Orianne Weizman, Jérémie Barraud, Stéphane Lafitte, Cyril Ferdynus, Louis-Marie Desroche","doi":"10.1093/ehjdh/ztag042","DOIUrl":"10.1093/ehjdh/ztag042","url":null,"abstract":"<p><strong>Aims: </strong>Responsible adoption of artificial intelligence (AI) in cardiology remains uneven. We aimed to map knowledge, attitudes, beliefs and practices among cardiovascular professionals in France and to identify levers for implementation.</p><p><strong>Methods and results: </strong>We conducted a national multiprofessional survey across cardiovascular care from 4 December 2024 to 1 March 2025. Prespecified outcomes included regular use in practice, confidence in diagnostic outputs, performance expectations, training needs, and social influence. Seven hundred fifty-six professionals completed the survey (58.2% cardiologists, 24.3% allied-health professionals, 17.8% other professionals; median age 37 years; 46.7% women). AI use was reported as regular (≥ weekly) by 23%, occasionally by 40%, and none by 37%; only 7.8% had formal AI training. Use concentrated on AI-assisted imaging (32%) and patient monitoring/management (18%). The most valued benefit was improved diagnostic accuracy (29%); leading concerns were algorithmic bias (29.9%) and data privacy (28.2%). Explainability increased confidence (among cardiologists, high confidence 64% in therapeutic contexts vs. 84% with explanations). In multivariable analyses, prior training (aOR 3.22, 95% CI 1.60-6.55), research involvement (2.94, 1.90-4.58), and male sex (1.64, 1.05-2.59) were associated with higher use, while age > 40 years was associated with lower use (0.62, 0.40-0.96). Allied-health professionals reported lower social influence and training needs.</p><p><strong>Conclusion: </strong>Adoption of AI in cardiology remains limited, and four levers emerged for responsible scale-up: Training (education), Explainability (transparent outputs), Integration (workflow embedding), and Accompaniment (peer support, evaluation). These priorities should guide education, governance, and procurement strategies.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"7 4","pages":"ztag042"},"PeriodicalIF":4.4,"publicationDate":"2026-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13131982/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147824144","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}