Artificial Intelligence-Enabled Electrocardiography for Detection of Left Ventricular Diastolic Dysfunction: A Systematic Review and Meta-Analysis

Artificial intelligence–enabled electrocardiography for assessment of left ventricular systolic dysfunction in the era of foundation models

Artificial intelligence (AI) applied to the standard 12-lead electrocardiogram (AI-ECG) is being developed as a scalable approach to screen for left ventricular systolic dysfunction (LVSD) and support triage for confirmatory testing. Supervised models trained on paired ECG–echocardiography data show high discrimination for reduced ejection fraction across thresholds and can identify individuals at higher risk of subsequent LV dysfunction despite a normal baseline echocardiogram. External validation of an FDA-cleared ECG-AI device across four geographically diverse U.S. health systems confirmed strong diagnostic accuracy, though signal-format compatibility and quality gating meaningfully affect real-world yield. Two pragmatic randomized trials demonstrate practice-level impact. In primary care, AI-ECG increased the number of new low-ejection-fraction diagnoses and directed echocardiography preferentially to screen-positive patients. In non-cardiology inpatient wards, AI alerts improved diagnostic yield through increased cardiology consultation rather than increased imaging volume. In emergency-department patients with dyspnea, AI-ECG supports a prioritization role with high negative predictive value, outperforming NT-proBNP, but requires confirmatory imaging given prevalence-dependent positive predictive value. In population cohorts, adding AI-ECG signals to PREVENT-HF improves near-term heart-failure risk discrimination and reclassification, though without demonstrated benefit on clinical outcomes such as heart-failure hospitalization or mortality. Foundation models pretrained on large ECG datasets reduce labeled-data requirements and improve transportability, but prospective echocardiography-anchored validation is required before broader deployment. FDA-cleared software is available for left ventricular ejection fraction ≤40% screening from 12-lead ECGs as clinician decision support. This review summarizes performance across thresholds and care settings, outlines threshold selection and calibration, and defines priorities for outcome-oriented trials, equitable deployment, and implementation governance.

AI Enabled Single Lead Wearable Electrocardiogram (ECG) Screening for Early Detection of Left Ventricular Systolic Dysfunction (LVSD)

Left ventricular systolic dysfunction (LVSD) is an important precursor to heart failure and may remain clinically silent until ventricular impairment has progressed. Although echocardiography remains the standard confirmatory method for assessing left ventricular ejection fraction, its use as a broad screening tool is limited by cost, infrastructure requirements, specialist availability, and delayed referral pathways. This paper examines the potential of artificial intelligence-enabled single-lead wearable electrocardiogram screening for early LVSD risk detection. The study proposes a diagnostic screening framework in which wearable ECG signals are acquired, preprocessed, segmented, and analyzed using an AI-based classification model to generate an LVSD probability score. In the simulated evaluation, LVSD was defined as LVEF ≤ 40%, and the proposed model achieved an accuracy of 89.0%, sensitivity of 87.5%, specificity of 89.3%, F1-score of 71.8%, negative predictive value of 97.4%, and AUROC of 0.91. These findings suggest that AI-enabled single-lead wearable ECG may be clinically useful for identifying high-risk individuals and ruling out low-risk cases before referral for confirmatory imaging. However, the system should not be interpreted as a replacement for echocardiography or clinician judgment. Its strongest value lies in preliminary screening, referral prioritization, remote monitoring, and community-based cardiovascular risk assessment. The paper concludes that AI-enabled wearable ECG screening may support earlier LVSD detection when integrated with validated algorithms, secure data systems, clinician oversight, and structured echocardiography referral pathways.

Prediction of Left Ventricular Systolic Dysfunction Using an Artificial Intelligence-Based Electrocardiogram Analysis Model in Patients Presenting to the Emergency Department

Background: Left ventricular systolic dysfunction (LVSD) is a precursor to heart failure arising from diverse cardiac conditions. Although echocardiography remains the reference standard for LVSD diagnosis, its routine use in the emergency department (ED) may be constrained by cost, time, equipment availability, and the need for specialized expertise. We evaluated the diagnostic performance of an artificial intelligence-based electrocardiogram analysis model (AI-ECG model) for detecting LVSD in patients presenting to the ED. Methods: This retrospective observational study included patients treated at a single tertiary hospital between 2020 and 2022 who underwent 12-lead electrocardiography within 24 h of ED admission and echocardiography within 30 days. Electrocardiographic data were analyzed using AiTiALVSD version 1.00.00, with a predefined cutoff score of 9.7 used to classify patients as being at high or low risk of LVSD. Diagnostic performance was assessed using standard discrimination and classification metrics. Results: Among 4529 included patients, 531 had LVSD. The AI-ECG model demonstrated high discrimination, with an area under the receiver operating characteristic curve (AUROC) of 0.934 (95% confidence interval [CI]: 0.923–0.945). Performance remained robust in patients with a shock index ≥ 0.9 (n = 453; AUROC, 0.895; 95% CI: 0.854–0.937) and in those with hypotension (n = 75; AUROC, 0.885; 95% CI: 0.786–0.984). Conclusions: The AI-ECG model accurately identified LVSD in ED patients in this cohort despite heterogeneous acquisition conditions and retained good discrimination in hemodynamically unstable subgroups, although findings in the smaller hypotensive subgroup should be interpreted as exploratory.

Composite Artificial Intelligence-Enabled Electrocardiogram for Detection and Prediction of Structural Heart Disease

Artificial intelligence–based ECG as a triage tool for acute myocardial infarction: a diagnostic systematic review and meta-analysis

Abstract 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.

Utility of ECG-Vision for Surveillance of Left Ventricular Dysfunction in Patients With Hypertrophic Cardiomyopathy Initiated on Mavacamten.

BACKGROUND Frequent transthoracic echocardiograms (TTEs) are required to monitor for left ventricular systolic dysfunction (LVSD) in patients with obstructive hypertrophic cardiomyopathy receiving myosin inhibitors. This requirement may be cumbersome and limit access in underserved and rural areas. The objective of this study was to evaluate the performance of an artificial intelligence (AI)-enabled ECG tool in predicting LVSD in hypertrophic cardiomyopathy patients on mavacamten. METHODS At Morristown Medical Center/Atlantic Health, 147 patients initiated on mavacamten between June 2022 and June 2025 underwent ECGs and TTEs at baseline and clinically available follow-up visits. A validated AI-enabled ECG algorithm predicted the probability of LVSD. Sensitivity, specificity, negative predictive value, positive predictive value, and area under the curve were calculated for left ventricular ejection fraction <50%, with CIs accounting for repeated paired ECG-TTE observations within patients. RESULTS In 147 patients, mean age was 65±14 years; 44% were male. Among 453 paired ECG-TTE observations, 8 LVSD event observations occurred. At an AI probability threshold of 20%, sensitivity was 100% (95% CI, 68%-100%), specificity was 75% (95% CI, 69%-82%), positive predictive value was 7% (95% CI, 3%-11%), and negative predictive value was 100% (95% CI, 99%-100%). The area under the curve was 0.94 (95% CI, 0.90-0.98). Patient-level classifications between AI-enabled ECG and echo-confirmed LVSD were concordant in 127 of 147 patients (86%), inconclusive in 17 of 147 (12%), and discordant in 3 of 147 (2%). CONCLUSIONS In this single-center exploratory cohort of patients with obstructive hypertrophic cardiomyopathy receiving mavacamten, ECG-Vision left ventricular demonstrated high observed sensitivity and negative predictive value for TTE-defined LVSD, although estimates were imprecise because LVSD events were infrequent. These findings support prospective multicenter validation of AI-enabled ECG as a potential adjunctive triage tool.