Arrhythmia Detection - A Machine Learning based Comparative Analysis with MIT-BIH ECG Data

Cardiovascular arrhythmias are most common cardiac problem in the world. This work while focusing on development of automated detection and classification of arrhythmia using MIT-BIH database compared five machine learning algorithms with three different features. Pre-processing followed by beat detection is applied on one channel to get individual beats having PQRST window. Three features (viz. simple amplitude feature of 300 samples, area feature with non-overlapped sliding window, and area feature with overlapped sliding window) were used for five classifiers used in this study. It was observed that Artificial Neural Network with amplitude features gave best result with 99.59% accuracy which is comparable to state-of-the art methods.