Predicting Coronary Artery Disease using an Ensemble Voting Model and Machine Learning Techniques

Ccoronary Artery Disease (CAD), a kind of cardiovascular illness, is well known for its proclivity to cause death. Plaque deposition in coronary arteries, which is largely calcium, fibrin, and cholesterol, produces a partial restriction of blood flow, leading to the development of CAD. In recent years, there has been a significant increase in the use of machine learning (ML) techniques in the medical area. The proposed study makes use of a unique machine learning technique to forecast the development of CAD sickness. The primary goal of this study was to create a unique model that used a machine learning technique to improve the accuracy of CAD prediction in a categorization scenario. An ensemble voting classifier is built using K-nearest-neighbor, decision tree, logistic regression, support vector machine, naive bayes, and XGboost. The efficiency of the ensemble models was then compared to that of a completely new model. The trials in this study used data from the Alizadeh Sani dataset, which contained information on 216 CAD patients chosen at random. This data set contains 216 instances of CAD and 87 healthy controls, each having 56 attributes. To uncover the problem of skewed data, a technique known as Synthetic Minority Over Sampling (SMOTE) was applied. Only a few of the several criteria used to evaluate performance are confusion accuracy, f1 score, recall, and precision. This study performed significantly better when the innovative approach was used, with a 92% prediction accuracy rate for CAD detection. These findings are comparable to the best produced using other methods.