A machine learning classifier trained on hiPSC-CM electrophysiological profiles achieved 89% accuracy in classifying Long QT Syndrome genetic variants by their associated risk levels.
Integrating hiPSC-CM electrophysiological profiling with machine learning provides a robust method for granular variant-specific risk stratification of LQTS patients.
Abstract Aims Long QT syndrome (LQTS) is a life-threatening genetic disorder characterized by prolonged QT intervals on electrocardiograms. Congenital forms are mostly associated with variants in the KCNQ1 and KCNH2 genes. Among pathogenic or likely pathogenic (P/LP) variants, some are associated with a significantly higher incidence of cardiac events compared to others. While therapies have significantly reduced mortality, some patients are unresponsive or intolerant to therapy, perpetuating their arrhythmic risk, including sudden cardiac death. Current approaches for risk stratification are insufficient, highlighting the critical need for more accurate identification and management of patients carrying high risk genetic variants. Here, we aimed to develop a refined risk stratification model for P/LP variants by applying machine learning classification to electrophysiological data measured in patient-specific human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs). Methods and Results Ten patient-specific hiPSC lines, each carrying one of six pathogenic or likely pathogenic (P/LP) variants in the KCNQ1 or KCNH2 genes, along with two healthy control hiPSC lines, were differentiated into cardiomyocytes (hiPSC-CMs). Electrophysiological responses from multielectrode array recordings at baseline and after application of selective ion channel blockers or pro-arrhythmic compounds were used to train a machine learning model to classify variant-specific risk levels based on in vitro electrophysiological readouts. An independent validation cohort of two additional KCNH2 hiPSC lines was used to test the model’s performance in predicting single-variant risk. Our findings revealed a correlation between variant risk level, hiPSC-CM electrophysiological profiles, and drug responses. The machine learning classifier, trained on multielectrode array recordings, achieved 89% accuracy in classification of P/LP genetic variants according to the associated risk levels. Conclusions This study demonstrates that integrating hiPSC-CM electrophysiological profiling with machine learning provides a robust method for granular variant-specific risk stratification of LQTS patients.
Khudiakov et al. (Thu,) conducted a other in Long QT syndrome (LQTS) (n=14). Machine learning classification of hiPSC-CM electrophysiological profiles was evaluated on Classification accuracy of pathogenic or likely pathogenic genetic variants according to associated risk levels. A machine learning classifier trained on hiPSC-CM electrophysiological profiles achieved 89% accuracy in classifying Long QT Syndrome genetic variants by their associated risk levels.