iCardo 3.0: A Machine Learning Framework for Prediction of Conduction Disturbance in Heart

One of the leading causes of mortality in the world is cardiovascular disease. Electrocardiography (ECG) is a non-invasive tool for assessing heart function abnormalities. The paper presents the prediction of conduction disturbance or disorders (CD) which lead to chronic heart failure or cardiac arrest through a 12-lead electrocardiogram (ECG). A publicly available large electrocardiography data set named PTB-XL is used in the study. Bagging and boosting-based machine learning algorithms, i.e. random forest (RF) and XGBoost along with the support vector machine (SVM), have been used to classify the CD and normal subjects. Two demographic features, age and sex of the subject, have been added to the ECG to prepare the final data for the input of the classifiers. The performance in terms of accuracy with random forest (RF) and XGBoost performance is similar, whereas the total number of true predictions is higher in the case of RF.