Key result
AI-ECG identified HCM with 51.1% sensitivity and 96.1% specificity, and predicted 1-year composite clinical outcomes.
Why the study?
Does a commercially available AI-ECG algorithm improve diagnostic detection of phenotypic HCM and predict 1-year composite clinical outcomes compared with conventional ECG parameters in patients undergoing CMR?
Case-Control (n=404)
Does a commercially available AI-ECG algorithm improve diagnostic detection of phenotypic HCM and predict 1-year composite clinical outcomes compared with conventional ECG parameters in patients undergoing CMR?
Answers are grounded in this paper and cite their sources.
In patients undergoing CMR evaluation for HCM, a commercially available AI-ECG algorithm provides high specificity, incremental diagnostic reclassification over standard ECG, and prognostic stratification for treatment-related outcomes like ICD placement and septal reduction therapy.
BACKGROUND: Artificial intelligence-enabled electrocardiography (AI-ECG) may facilitate detection of hypertrophic cardiomyopathy (HCM), but its ability to identify higher-risk patients undergoing clinical evaluation for HCM remains uncertain. OBJECTIVES: To evaluate the diagnostic and prognostic performance of a commercially available AI-ECG algorithm among patients undergoing cardiac magnetic resonance imaging (CMR) for suspected or established HCM. METHODS: We studied 102 patients with HCM and 302 age-, sex-, and year-matched controls without HCM who underwent clinically indicated CMR. An AI-ECG algorithm was applied to the first available ECG preceding CMR. Diagnostic performance, incremental value beyond standard ECG features, and associations with clinical outcomes were assessed. RESULTS: ECGs preceded CMR by a median of 1.1 years. AI-ECG demonstrated moderate sensitivity (51.1%) and high specificity (96.1%) for identification of phenotypic HCM and incrementally improved discrimination and reclassification beyond demographic and conventional ECG variables (net reclassification improvement 0.19, p<0.001). Within one year of CMR, a positive AI-ECG was independently associated with the composite outcome (adjusted HR 2.68, 95% CI 1.42-5.09; p=0.003), driven by ICD placement and septal reduction therapy. Among patients with HCM, while exploratory, an AI-ECG probability ≥ 0.99 identified those at highest risk for subsequent events (HR 2.92, 95% CI 1.59-5.35; p=0.011). CONCLUSION: In conclusion, among patients undergoing clinical evaluation for HCM, AI-ECG provided incremental diagnostic value beyond conventional ECG parameters and identified individuals at increased risk for subsequent treatment-related clinical outcomes.
No takes yet. Share an insight, caveat, or question.
Morrison et al. (2026) conducted a case-control in Hypertrophic cardiomyopathy (HCM) (n=404). Commercially available artificial intelligence-enabled electrocardiography (AI-ECG) algorithm vs. Standard ECG features and demographic variables was evaluated on Diagnostic identification of phenotypic HCM and composite clinical outcome (including ICD placement and septal reduction therapy) within 1 year of CMR (HR 2.68, 95% CI 1.42-5.09, p=0.003). AI-ECG identified HCM with 51.1% sensitivity and 96.1% specificity, and predicted 1-year composite clinical outcomes.
Synapse has enriched 10 related papers. Consider them for comparative context: