Automated prediction of sudden cardiac death using statistically extracted features from electrocardiogram signals

Sudden cardiac death (SCD) is becoming a severe problem despite significant advancements in the usage of information and communication technology (ICT) health industry. Predicting an unexpected SCD person high importance. It might increase survival rate. In this work, we have developed automated method for predicting utilizing statistical measures. We extracted intrinsic attributes electrocardiogram (ECG) signals using Hilbert-Huang wavelet transforms. Then machine learning (ML) classifier, are these traits to automatically classify regular existing risks. Support vector (SVM), decision tree (DT), naive Bayes (NB), discriminate k-nearest neighbors (KNN), analysis (Disc.), as well ensemble classifiers also utilized (Ens.). The efficiency practicality proposed methods evaluated standard database measured ECG data obtained from 18 records cases normal cases. For scheme, set features can predict very fast that is, half hour before occurrence with average accuracy 100.0% 99.9% 98.5% 99.4% 99.5% (Ens.)