Real-World Artificial Intelligence-Based Electrocardiographic Analysis to Diagnose Hypertrophic Cardiomyopathy.

Abstract

Background: There is an emerging interest in artificial intelligence-enhanced 12-lead electrocardiogram (AI-ECG) in detection of hypertrophic cardiomyopathy (HCM).

Objectives: This study describes the initial real-world experience of using AI-ECG (Viz-HCM, developed using a convolutional neural network trained algorithm) in our center.

Methods: All patients undergoing 12-lead electrocardiograms at Cleveland Clinic, Cleveland, Ohio, between February 19, 2024, and November 1, 2024, were prospectively analyzed for potential HCM using AI-ECG. The numbers of patients flagged for potential HCM were recorded. Presence of confirmed HCM, a new diagnosis of HCM following AI-ECG assessment (with a negative prior clinical evaluation), and alternative non-HCM diagnosis were recorded. Assessment of AI-ECG diagnostic performance was done using various HCM probability thresholds (≥0.95, ≥0.90, and ≥0.85).

Results: Of 103,492 electrocardiograms analyzed in 45,873 patients, AI-ECG flagged potential HCM in 1,265 (2.7%) unique patients. Of these, 511 (40.4%) had confirmed HCM, 63 (5%) had new HCM diagnosis, and 691 (54.6%) had an alternate diagnosis. HCM probability threshold of ≥0.85 provided the highest sensitivity (95%) for diagnosis of HCM with high specificity and accuracy (all >98%). The positive predictive value was the highest (66%) at the cutoff ≥0.95 but with a lower sensitivity at 50%. The AI-ECG algorithm performed similarly in both men and women, and was more sensitive in individuals <50 years but more specific in individuals ≥50 years.

Conclusions: Prospective real-world application of the AI-ECG algorithm to detect HCM was associated with a high degree of accuracy, varying with the chosen probability threshold. It also enabled the identification of 5% of patients with no prior HCM diagnosis.