What question did this study set out to answer?

This research aims to evaluate the effectiveness of AI-based ECG tools in diagnosing hypertrophic cardiomyopathy (HCM).

February 28, 2026Open Access

Evaluation of artificial intelligence-based electrocardiogram analysis tools in patients with hypertrophic cardiomyopathy

Key Result

AI-based ECG tools showed modest accuracy in HCM patients, with only 41.2% scoring >50% probability for HCM and correlations to disease severity.

Key Points

This research aims to evaluate the effectiveness of AI-based ECG tools in diagnosing hypertrophic cardiomyopathy (HCM).
Analyzed digitized 12-lead ECGs from 681 patients with confirmed HCM.
Used three AI tools to calculate HCM and structural heart disease probabilities.
Assessed correlation between AI probabilities and clinical parameters.
AI-calculated HCM probabilities showed a median of 38.8%, with 41.2% of patients scoring above 50%.
HCM probabilities were significantly higher in patients with abnormal ECGs.
SHD probabilities had a median of 51.4%, with 51.2% scoring above 50%.

Structured PICO

Do AI-based ECG analysis tools accurately detect hypertrophic cardiomyopathy and structural heart disease in patients with confirmed HCM?

Population

681 patients with confirmed hypertrophic cardiomyopathy (HCM)

Intervention

Three artificial intelligence (AI)-based electrocardiogram (ECG) analysis tools: (1) HCM probability tool, (2) structural heart disease (SHD) probability tool, and (3) multi-category ECG diagnosis tool

Comparator

Manually assigned ECG diagnoses

Outcome

Distribution of AI-calculated probabilities, associations with clinical parameters, and agreement between AI-based and manually assigned ECG diagnoses using Cohen's kappasurrogate

AI-based ECG analysis tools developed for general populations demonstrated only modest performance in detecting HCM in a confirmed disease cohort, highlighting the need for disease-specific validation.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Abstract Aims Artificial intelligence (AI)-based electrocardiogram (ECG) analysis tools have shown promise in detecting various cardiac conditions. However, their performance in specific patient populations, such as those with hypertrophic cardiomyopathy (HCM), remains incompletely characterized. To evaluate the performance of three AI-based ECG analysis tools in patients with confirmed HCM: (1) a tool calculating HCM probability, (2) a tool calculating structural heart disease (SHD) probability, and (3) a tool providing ECG-based diagnoses across multiple categories. Methods and results We analysed digitized 12-lead ECGs from patients with confirmed HCM (n = 681) using three AI tools. We assessed the distribution of AI-calculated probabilities and their associations with clinical parameters and evaluated agreement between AI-based and manually assigned ECG diagnoses using Cohen’s kappa. Despite all patients having confirmed HCM, the AI-calculated HCM probabilities showed a relatively uniform distribution median 38.8% (IQR: 12.8–63.4%), with only 41.2% and 12.5% of patients receiving a probability score 50% and 75%. HCM probabilities were significantly higher in patients with abnormal vs. normal ECGs (P 0.001) and correlated with markers of disease severity. SHD probabilities were generally higher median 51.4% (IQR: 28.7–74.5%), with 51.2% and 25% of patients receiving scores 50% and 75%. Conclusion AI-based ECG analysis tools demonstrated modest performance in our HCM cohort. These findings highlight the challenges of applying AI tools developed in general populations to specific disease cohorts and underscore the need for disease-specific validation before clinical implementation.