Distinct ECG Phenotypes Identified in Hypertrophic Cardiomyopathy Using Machine Learning Associated With Arrhythmic Risk Markers

Hypertrophic cardiomyopathy (HCM) is a common cardiac genetic disease and a major cause of sudden cardiac death (SCD) in young adults. Although most patients remain asymptomatic, others experience SCD triggered by ventricular arrhythmias. An accurate detection of these high-risk patients to provide them with appropriate treatment is therefore essential, but it remains a challenge because current electrocardiogram (ECG) biomarkers are not specific. This chapter describes computational methods for the analysis and interpretation of electrophysiologic clinical data to investigate the diversity of HCM phenotypes with the ultimate aim of improving risk stratification in HCM. First, by combining computational clustering and mathematical modeling, we identified four distinct ECG phenotypes that exhibit differences in hypertrophy distribution and risk for arrhythmia. The group with primary repolarization abnormalities and the coexistence of apical and septal hypertrophy showed a higher HCM risk-SCD score compared with other groups. Second, we explored the influence of structural and electrophysiologic mechanisms on the ECG to explain the four HCM phenotypes identified by using a whole-body personalized three-dimensional (3D) computer simulation framework. We showed that apicobasal repolarization heterogeneities explained the T-wave inversions in the high-risk group and that an abnormal Purkinje system may explain the QRS abnormalities in another group. Overall, this chapter contributes toward a better understanding of HCM phenotypic heterogeneity and the improvement of individual patient management.