Aims Myocardial ischaemia is associated with adverse prognosis. Identifying high-risk individuals who require a stress test is challenging, and a practical screening tool to detect these patients, especially in asymptomatic individuals, is lacking. We aimed to develop an artificial intelligence (AI) model based on a resting 12-lead electrocardiogram to detect patients with inducible myocardial ischaemia. Methods and results An AI model was developed using 12 074 resting 12-lead ECGs from 11 700 patients and tested on 1342 patients at two hospitals. Patients with inducible ischaemia were defined as those who received revascularisation for silent ischaemia, stable angina, or unstable angina between 2004 and 2020 (n = 6070). No ischaemia group included patients with 0% stenosis in all epicardial coronary arteries and coronary artery calcium score of ≤100 in coronary computed tomography angiography (n = 7346). The primary outcome was the model performance categorising patients with inducible myocardial ischaemia. We further validated the model through multiple reference and external validation datasets encompassing 35 898 patients. The model showed an area under the receiver operating characteristic curve (AUROC) of 0.90 (95% CI 0.88─0.92), and an area under the precision-recall curve (AUPRC) of 0.87 (95% CI 0.84─0.89). The model performance was robust regardless of age, sex, comorbidities, clinical diagnosis, or culprit vessels. Consistent results were demonstrated in an age- and sex-matched dataset (n = 7414; AUROC 0.85, 95% CI 0.83─0.87 and AUPRC 0.84, 95% CI 0.82─0.87), as well as in reference and external cohorts. Conclusion Electrocardiogram-trained AI demonstrated favourable performance in detecting inducible myocardial ischaemia. It may enable screening and risk stratification of high-risk patients.

Background Asymptomatic left ventricular systolic dysfunction (LVSD) is a well-established precursor of overt heart failure (HF), yet it often remains undiagnosed in the general population. Artificial intelligence–enabled electrocardiogram (ECG) analysis offers a scalable approach for early detection. Objectives The purpose of this study was to evaluate the diagnostic performance of an artificial intelligence–enabled ECG model (AiTiALVSD) for identifying asymptomatic LVSD in a large health screening population. Methods In this retrospective, single-center study, we evaluated the AiTiALVSD model among 40,713 self-referred adults who underwent a total of 60,711 ECG-transthoracic echocardiography (TTE) pairs between 2011 and 2023. LVSD was defined as a left ventricular ejection fraction ≤40%. Model discrimination was assessed using the area under the receiver-operating characteristic curve (AUROC) and the area under the precision–recall curve (AUPRC), and diagnostic performance metrics were compared with established HF risk scores. Results Among 60,711 ECG–TTE pairs, 32 cases (0.054%) met the criteria for LVSD. The AiTiALVSD model demonstrated excellent discrimination (AUROC 0.973; AUPRC 0.328), with a sensitivity of 90.6%, specificity of 99.4%, positive predictive value of 7.7%, and a negative predictive value of 100%. Established HF risk scores, including the MESA (Multi-Ethnic Study of Atherosclerosis) 5-year HF score and Pooled Cohort Equations to Prevent HF score, showed inferior discrimination (AUROC: 0.696 and 0.672, respectively). The MESA score was not designed to detect prevalent LVSD and was calculated without natriuretic peptide data, which may have disadvantaged its performance in this comparison. Simulation analyses suggested that approximately 1,841 ECGs and 13 confirmatory TTEs would be required to detect one case of LVSD. Conclusions In a real-world screening population with an extremely low prevalence of LVSD, the AiTiALVSD model demonstrated high diagnostic accuracy, supporting its potential role as a rule-out screening tool for HF prevention. Prospective validation is warranted.

Electrocardiograms (ECGs) remain widely archived as paper ECG charts. In the 12-lead paper ECG chart layout, each lead shows only 2.5-second visible segments. Therefore, digitized charts are incomplete, leaving most of the 10-second recording invisible and misaligned with the digital standard required by ECG-AI models. Previous work has attempted to recover these invisible segments but has shown markedly lower performance than visible segments. We propose the Visible Context Propagation (VCP) architecture, an extension of ECGrecover, which leverages the quasi-periodic structure of ECGs and employs cross-attention to propagate contextual information from visible to invisible segments. Our model consistently outperformed ECGrecover, the strongest baseline, reducing RMSE by 32.4% overall, including 12.0% on invisible segments. Beyond recovery accuracy, evaluations on ECG applications demonstrated that recovered ECGs achieved performance comparable to raw ECGs in both diagnostic classification and ECG feature measurement. These results highlight the effectiveness of explicitly modeling the propagation of visible-to-invisible context and establish VCP as a robust solution for recovering incomplete paper-based ECGs, enabling reliable surrogates for clinical and analytical use.

Artificial intelligence-enabled electrocardiography (AI-ECG) is rapidly expanding, yet its real-world clinical integration remains limited by data heterogeneity, unclear workflows, and uncertainty about clinical impact. This review synthesizes evidence from pragmatic trials and prospective studies demonstrating that AI-ECG can improve early detection, enable opportunistic screening, and guide personalized care across diverse settings. We highlight persistent challenges—including bias, explainability, and regulatory adaptation—and propose practical strategies for safe, scalable deployment. By integrating clinical and technical perspectives, this review outlines how AI-ECG can evolve into a reliable digital biomarker that enhances cardiovascular care.

Left bundle branch block (LBBB) significantly increases the risk of left ventricular systolic dysfunction (LVSD) due to cardiac dyssynchrony. Although artificial intelligence–enabled electrocardiography (AI-ECG) models show promise in detecting LVSD, their performance in LBBB patients remains underexplored. We hypothesized that an AI-ECG model clinically validated for detecting LVSD would accurately detect LVSD and predict future clinical outcomes in LBBB patients.

Several artificial intelligence–enhanced electrocardiogram (AI-ECG) models have shown promise in detecting left ventricular systolic dysfunction (LVSD), but their head-to-head agreement and performance have not been independently compared within the same cohort.

Left ventricular filling pressure (LVFP) is associated with heart failure symptoms, a key prognostic marker, and a therapeutic target, but is difficult to measure non-invasively. We aimed to develop and validate a deep learning-based artificial intelligence (AI) model using a standard 12-lead electrocardiogram (ECG) to detect elevated LVFP and assess its prognostic value.

Artificial intelligence–enabled electrocardiography (AI-ECG) accurately detects left ventricular systolic dysfunction (LVSD). Prior studies suggest higher AI-ECG LVSD scores predict adverse outcomes in heart failure with reduced ejection fraction (HFrEF). Whether serial changes in these scores predict recovery to heart failure with improved ejection fraction (HFiEF) is unclear. If validated, AI-ECG could offer a non-invasive alternative to frequent transthoracic echocardiography (ECHO) for monitoring ejection fraction (EF).We investigated whether sequential 12-lead AI-ECG LVSD scores are associated with EF improvement in HFrEF, potentially enabling clinicians to detect HFiEF without relying solely on serial ECHO.This single-center, retrospective cohort study included all adults (≥19 years) with at least one ECHO-confirmed LVEF ≤40% (2017–2025). Exclusion criteria included left ventricular assist device, heart transplantation, ECMO, or IABP. Each ECG was analyzed by an AI-ECG model, yielding an LVSD probability (0.0–100.0). ECHOs within 14 days of an ECG formed ECG-ECHO pairs. Baseline HFrEF was defined by the first LVEF ≤40%. HFiEF required a ≥10% absolute increase in LVEF from baseline after ≥90 days. We defined the “Delta score” as (baseline AI-ECG probability − follow-up AI-ECG probability). Associations were assessed using Cox proportional hazards regression, adjusted for age, sex, obesity, hypertension, diabetes, and ischemic heart disease (IHD). Kaplan-Meier analysis was conducted to compare the probability of achieving HFiEF among the three distinct Delta score groups (1st, 2nd, and 3rd tertile), with statistical significance assessed using the log-rank test.Among 832 patients (mean age 64.0±14.0 years; 66.6% male), 426 (51.2%) achieved HFiEF. They were younger (62.1±13.7 vs. 66.1±14.0 years, p<0.001) and had lower IHD prevalence (38.3% vs. 58.1%, p<0.001). Baseline LVEF was lower in the HFiEF group (29.15% vs. 32.17%, p<0.001), with a significant rise at follow-up (49.89% vs. 33.26%, p<0.001). Baseline AI-ECG scores were similar (57.56 vs. 53.63, p=0.069) but dropped substantially in the HFiEF group at follow-up (19.52 vs. 48.45, p<0.001). Each 1-point higher baseline AI-ECG score predicted a 0.9% lower chance of HFiEF (aHR 0.991, p<0.001), while each 1-point increase in Delta score predicted a 3.9% higher HFiEF likelihood (aHR 1.039, p<0.001), with a significant interaction (p=0.004). Kaplan-Meier analysis demonstrated significant differences among the three distinct Delta score groups in predicting recovery to HFiEF (p < 0.0001).Baseline AI-ECG LVSD scores and their serial decreases both predict EF recovery in HFrEF. Incorporating AI-ECG into routine care could offer a simple, non-invasive strategy to track LV function improvement—complementing or reducing the need for repeated ECHO.

Recognizing the need for explainable AI (XAI) approaches to enable the successful integration of AI-based ECG prediction models(AI-ECG) into clinical practice, we introduce a framework generating CounterFactual ECGs (i,e., named CoFE) to illustrate howspecific features, such as amplitudes and intervals, influence themodel’s predictive decisions. To demonstrate the applicability ofthe CoFE, we present two case studies: atrial fibrillation classification and potassium level regression models. The CoFE revealsfeature changes in ECG signals that align with the establishedclinical knowledge. By clarifying both where valid features appear in the ECG and how they influence the model’s predictions, we anticipate that our framework will enhance the interpretability of AI-ECG models and support more effective clinicaldecision-making. Our demonstration video is available at: https://www.youtube.com/watch?v=YoW0bNBPglQ.

Artificial intelligence-enhanced electrocardiogram (AI-ECG) using single-lead ECG can detect Left Ventricular Systolic Dysfunction (LVSD). However, most models are trained on Lead I from 12-lead ECGs, which differs fundamentally from smartwatch ECGs. In real-world settings, smartwatch ECGs not only differ structurally and physically from standard ECGs but are also affected by noise and user-related artifacts. Furthermore, validation remains limited due to the scarcity of data from self-recorded smartwatch ECGs.This study investigates whether self-recorded smartwatch ECGs can reliably monitor LVSD in real-world settings by comparing AI-ECG scores with ejection fraction from echocardiography.From July to October 2024, we enrolled participants who had recently undergone or were scheduled for echocardiography. Eligible individuals were instructed to record ECGs using their smartwatches (Samsung Galaxy or Apple Watch) at least twice daily for over a week, with a paired echocardiogram performed within 14 days. We adapted our previously developed convolutional neural network-based AI-ECG model to analyze smartwatch ECGs. The model was fine-tuned using smartwatch ECG data, leveraging the foundation model architecture with an integrated preprocessing module to manage signal noise inherent to smartwatch-derived data. It outputs a score between 0 and 100, with higher scores indicating a greater likelihood of LVSD. We evaluated model performance using two approaches: (1) Approach 1: All available ECGs were analyzed individually to generate scores and assess overall performance (2) Approach 2: Three ECGs per day were randomly selected for each participant, and their median score was used as the representative value for performance evaluation. All ECGs were processed without explicit adjustment for signal noise.A total of 27 participants were included, with 77.4% using Samsung Galaxy Watches and 22.6% using Apple Watches. Echocardiography, performed at a median interval of 6 days, identified 7 participants (36.5%) with LVSD. The median AI-ECG score was 55.0 in the LVSD group and 6.5 in the non-LVSD group. Overall, 1,497 ECGs were collected, including 866 from the LVSD group. When analyzing all available ECGs, the area under the receiver operating characteristic curve (AUROC) was 0.915 (95% confidence interval: 0.900–0.927). When analyzing only three randomly selected ECGs per day, the AUROC was 0.864.Our study demonstrates that an AI-based single-lead ECG approach can reliably monitor LVSD when applied to self-recorded smartwatch data in real-world settings. These findings provide important evidence supporting the extension of our AI-ECG model to analyze smartwatch ECGs.