Detection of Hypertrophic Cardiomyopathy by Artificial Intelligence-Enabled Electrocardiography in Children and Adolescents

There is currently no established screening approach for HCM. We recently developed an artificial intelligence (AI) convolutional neural network (CNN) for the detection of HCM based on the 12-lead electrocardiogram (ECG) in an adult population. We aimed to validate this approach of ECG-based HCM detection in pediatric patients. Methods We identified a cohort of children and adolescents with HCM who had an ECG and echocardiogram at our institution. These patients were age and sex-matched to a control population without HCM. Diagnostic performance of the AI-ECG model for the detection of HCM was estimated using the previously identified optimal diagnostic threshold of 11% (the probability output derived by the AI-ECG model above which an ECG is considered to belong to an HCM patient). Results We included 318 HCM patients (mean age 12±4.8 years, male 68%) and 22,996 age- and sex-matched non-HCM controls. AI-ECG probability for HCM was >11% in 91% of cases and 3% of controls. The AUC of the AI-ECG model for HCM detection was 0.98 (95% CI 0.97-0.99) with corresponding sensitivity 97% and specificity 91%. The model performed similarly in subgroups defined by gender and HCM genotype status. Model performance was best in the oldest subgroup (15-18 years) in both males and females. Conclusion A deep-learning, AI model can detect pediatric HCM with high accuracy from the standard 12-lead ECG.