An Enhanced Random Forest for Cardiac Diseases Identification based on ECG signal

Cardiac diseases are one of the foremost reasons of mortality in the worldwide. To cope with this issue, cardiology doctors insist on the early detection of cardiac diseases often with the use of an electrocardiogram (ECG) signal, providing timely and appropriate treatment for heart patients. In the literature, there are many efficient classification approaches like random forest method, conceived for ECG signal analysis to detect cardiac diseases. However, the execution of random forest requests introducing manually the number of trees as a parameter user, which is considered as a major drawback of this method, since often the user did not find the optimal tree value. In this paper, we propose to enhance the random forest method by suggesting a new simulated annealing (SA) algorithm to find the optimal number of trees where the accuracy of classifying the ECG signal is tackled as an objective function. The proposed system involves four main steps namely data collecting of ECG signal, pretreatment and denoising this data, feature extraction and classifying this signal using the enhanced random forest approach. To validate this proposal, a set of experiments was conducted on the well-known European Physionet ST-T and MIT/BIH databases as well as the USA Heart Disease Data Set and Arrhythmia Data Set of UCI machine learning repository. The results obtained showed that the enhanced random forest can reach 99.62% of classification accuracy according to the optimal found number of trees.