Cardiomyopathy -induced arrhythmia classification and pre-fall alert generation using Convolutional Neural Network and Long Short-Term Memory model

Abstract

Automatic analysis of Electrocardiogram (ECG) signals plays an important role in the medical field to deal with various crucial cardiac conditions. Currently, the detection of cardiomyopathy and arrhythmias considered a challenging task. Machine learning-based techniques have gained a huge attraction to classify these patterns, but most of the existing works have focused on arrhythmia classification. The researchers don't contribute much work towards, the cardiac disease case where Cardiomyopathy induced arrhythmia based classification. This work presents a novel approach to classify cardiomyopathy and cardiomyopathy with arrhythmia using a Convolutional Neural Network (CNN) based model. Along with classification, this work combines a pre-fall alert generation based on the heart rate conditions. The existing CNN models suffer from computational complexity; hence, this work incorporates the Long Short-Term Memory (LSTM) layer and developed CNN–LSTM based architecture. The proposed model is implanted on MIT-BIH data where these two classes segregated with the help of expert clinicians. In order to show the robust performance of the proposed model, the performance of CNN–LSTM has compared with state-of-art classifiers such as decision tree, support vector machine, and neural network. The comparative study shows that the proposed classification methods achieved significant improvement in the classification accuracy rate.