Automated Diagnosis System for Outpatients and Inpatients With Cardiovascular Diseases

Automated Diagnosis System for Outpatients and Inpatients With Cardiovascular Diseases

Abstract:

The identification of heart related diseases is challenging due to several contributory factors associated with patients, medical staff or medical materials used for diagnosis. Electrocardiogram (ECG) signal represents the electrical activity of the heart. It is the most common method used to diagnose patients with cardiovascular abnormalities. The evaluation commonly practiced by trained physicians can be sometimes subjective, time consuming and related to the observer status. This subjectivity can be more critical due to the double signification of the recorded ECG signals, mainly frequency and duration. In our paper, we present a comparative study of different Artificial Intelligence (AI) approaches as a very relevant tool to assist and improve the accuracy of cardiovascular diseases diagnosis. These models are trained on an online available MIT-BIH arrhythmia, normal rhythm sinus and BIDMC congestive heart failure databases and tested on our own collected data consisting of more than 72000 samples recorded in accordance with patients suffering from the same pathologies. The abnormal ECG signals are judged abnormal by comparison with normal heart beats. The work consists of testing and evaluating the performance of trained support vector machine (SVM), convolutional neural networks (CNN), quadratic discriminant, k-nearest neighbors and naiuml;ve Bayes as classifiers to correctly and efficiently classify newly unlabeled data. Further, methodology comprises continuous wavelet transform (CWT), discrete wavelet transforms (DWT), maximum overlap discrete transform (MODWT) and autoregressive modelling (AM) as feature extraction techniques. We tested the prelisted methods with principal component analysis (PCA) to evaluate the dimensionality reduction influence on the overall accuracy and runtime measures. The consistency of performance is evaluated using overall accuracy with confidence interval (CI), misclassification cost and runtime. The study resulted on an overall accuracy of 99.92% with a CI of 99.07-100% and 98.63% with a CI of 95.1%-100% using quadratic discriminant and KNN respectively, both with a certainty level of 99%. The developed approach is robust and accurate and can be used for automated diagnosis of cardiovascular diseases.