AI-enhanced ECG models achieved a pooled sensitivity of 82% and specificity of 83% for detecting cardiac dysfunction in patients with HFpEF or related conditions.
Meta-Analysis
Does artificial intelligence enhanced electrocardiography accurately detect cardiac dysfunction in patients evaluated for HFpEF or LVDD?
AI-enhanced ECG models demonstrate high specificity and moderate sensitivity for detecting cardiac dysfunction, suggesting potential utility as a non-invasive rule-out screening tool, though high heterogeneity limits immediate clinical adoption.
Effect estimate: Pooled sensitivity 0.82 and pooled specificity 0.83 (95% CI Sensitivity 95% CI: 0.70–0.90, Specificity 95% CI: 0.74–0.89)
Absolute Event Rate: 82% vs 83%
p-value: p=<0.0001 for heterogeneity
Background: Heart failure (HF) remains a growing global health problem, with nearly half of all cases attributed to HF with preserved ejection fraction (HFpEF) and its precursor, left ventricular diastolic dysfunction (LVDD). Although echocardiography is the diagnostic gold standard, its high cost and limited availability restrict its use for large-scale screening. In contrast, the electrocardiogram (ECG) is inexpensive and widely accessible. Recent advances in artificial intelligence (AI) have created opportunities to leverage ECG data for the early detection of cardiac dysfunction. The objective of this study was to systematically review and meta-analyze the diagnostic performance of AI-based ECG models for detecting cardiac dysfunction. Methods: The QUADAS-2 tool was used to assess the risk of bias. Pooled sensitivity and specificity were estimated using a bivariate random-effects model, with heterogeneity quantified using the I2 statistic. Pre-specified subgroup analyses were conducted according to clinical endpoint and AI model type. Results: Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, nine eligible studies evaluating AI algorithms applied to ECG data for the detection of HFpEF were identified. Considerable methodological and population heterogeneity was observed across studies. Risk of bias was generally low for reference standards, although concerns were noted in patient selection. The pooled specificity of AI-ECG models was high at 0.83 95% confidence interval (CI): 0.74–0.89, while pooled sensitivity was 0.82 (95% CI: 0.70–0.90). Both estimates demonstrated extremely high heterogeneity (I2 > 96%). Subgroup analyses by endpoint and model type did not explain this variability. Discussion: AI-enhanced ECG models show good diagnostic accuracy, specifically in ruling out cardiac dysfunction due to their high specificity. However, the high and unexplained heterogeneity across these studies limits the immediate generalizability of the results. Large, prospective validation studies across diverse populations are essential before these models can be confidently adopted into routine clinical practice.
Shahzad et al. (2026) conducted a meta-analysis in Adults suspected of heart failure with preserved ejection fraction (HFpEF), left ventricular diastolic dysfunction (LVDD), or elevated left ventricular filling pressures. Artificial intelligence-enhanced electrocardiography (AI-ECG) models vs. Reference standard diagnostic methods including echocardiography or invasive hemodynamic assessment was evaluated on Diagnostic accuracy of AI-ECG models for detecting cardiac dysfunction (HFpEF, LVDD, or elevated filling pressures) (Pooled sensitivity 0.82 and pooled specificity 0.83, 95% CI Sensitivity 95% CI: 0.70–0.90, Specificity 95% CI: 0.74–0.89, p=<0.0001 for heterogeneity). AI-enhanced ECG models achieved a pooled sensitivity of 82% and specificity of 83% for detecting cardiac dysfunction in patients with HFpEF or related conditions.