Cardiovascular Disease Prediction Using Electrocardiogram (ECG) and K-Plus Nearest Neighbors Algorithm: Cases of Chadian Patients

Abstract

This article reviews the use of the electrocardiogram (ECG) and the k-nearest neighbor (KNN) algorithm for the prediction of cardiovascular disease. Cardiovascular diseases are a major public health problem, accounting for a significant proportion of global deaths. The ECG offers a non-invasive method to monitor the electrical activity of the heart, detecting abnormalities and predicting risk. The KNN algorithm, a supervised machine learning technique, is used to classify the examples based on the labeled examples. Using pre-processed ECG data, KNN can recognize characteristic patterns of cardiovascular disease, enabling accurate and rapid prediction. This approach has significant medical potential, enabling early detection and informed decision-making. However, cardiovascular disease prediction is complex and evolving, requiring careful selection of attributes and rigorous evaluation of model performance. The article will include a review of prior designs, choice of study design, performance evaluation criteria, results, and an in-depth discussion of those results.