Pairwise Feature Interactions to Predict Arrhythmic Risk of Brugada Syndrome

Abstract

Electrocardiographic (ECG) indices were used for risk stratification in Brugada syndrome (BrS). However, nonlinear interactions between risk factors were ignored. Therefore, we adapted a generalized additive model with pair-wise interactions (GA2M) to predict BrS with spontaneous ventricular tachycardia/fibrillation (VT/VF) as outcomes based on specific ECG markers. A total of 191 adult patients with BrS from three centres (Germany, Greece and Hong Kong) were included for analysis. Depolarization and repolarization ECG markers were measured from the right precordial leads (V1 to V3). The proposed GA2M-based risk prediction model successfully identified a set of risk factors and their pairwise interactions in addition to the dispersion of repolarization/total repolarization (Tpeak- Tend x mean QT)). The model outperformed the baseline logistic model based on the same set of ECG measurements. In conclusion, the inclusion of pairwise interactions improved predictive performance and enabled more effective risk stratification in BrS.