Coronary Artery Disease Detection Based on ECG Using Machine Learning Approach

Computer Science and Engineering

The well known (ECG)electrocardiogram is one of the commonly employed tools to diagnose cardiovascular issues. The electrical and muscular functions of the heart are frequently assessed using a diagnostic instrument called an electrocardiogram (ECG or EKG). Although the test itself is relatively straightforward, it takes a lot of training to interpret the ECG charts. Such paper ECG records can be digitally digitized for automated analysis and diagnosis. The main goal of this project is to transform paper recordings of electrocardiograms into a 1-D signal using machine learning. The P, Q, R, S, and T waves that are available in ECG data may be extracted in order to illustrate cardiac electrical activity by applying a variety of methods. The techniques include splitting the original ECG report into 13 Leads, extracting and converting into the signal, smoothing, converting them to binary images using threshold and scaling. Post-feature extraction, dimension reduction techniques like Principal Component Analysis are applied to understand the data. Multiple classifiers like the use of k-nearest neighbor (KNN), logistic regression (LR), Support Vector Machine (SVM), and voting-based ensemble classifier will result in to the the conclusion of the model once it satisfies the necessary standards for precision, recollection, accuracy, f1-score, and support. This final model will aid in the diagnosing of cardiac diseases, to detect whether a patient has/had Myocardial Infarction, Abnormal Heartbeat, or the patient is hale and healthy by inferring the ECG reports

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.