Low-cost detection of cardiovascular disease on chronic kidney disease and dialysis patients based on hybrid heterogeneous ECG features including T-wave alternans and heart rate variability

Accumulating evidence shows that cardiovascular disease (CVD) contributes substantial burden to dialysis patients, accounting for almost 50 percent of mortality in dialysis population. Traditional clinical risk factors may not totally explain and predict CVD high mortality. The aim of this research is to develop a non-invasive, low-cost method for dialysis patients to evaluate their risks on cardiovascular disease (CVD) by hybrid heterogeneous ECG features including T-wave alternans and heart rate variability. A decision-based neural network (DBNN) structure is used for feature fusion and it provides overall 71.07% accuracy for CVD identification.