Utilizing the Machine Learning-Driven Techniques Used to ECG Dataset for Predicting Coronary Heart Disease

Abstract

The worldwide cause of mortality is cardiovascular heart disease. The automatic prediction of heart disease can be made to possible for accurate detection in initial stage. That is very significant and better improvement of patient’s outcomes. In recent year, the artificial intelligence approaches have provided the promising outcomes for prediction of numerous heart disease in medical conditions. The purpose of this outcomes is enhancement of various machine learning techniques used to cardiovascular heart disease (CHD) prediction for electrocardiogram (ECG) datasets. ECG provide the electrical Signal from the heart that identify the disease are present or not. The preprocessing method are used for improving the quality of ECG signals and extract the features from patients. There are various numbers of well-known machine learning approaches that includes the support vector machine, k nearest neighbour, logistic regression and decision tree classifier used for prediction. So, our finding of this paper will provide the new understanding regarding CHD prediction using different machine learning techniques. The predicting models of machine learning decision tree are providing the accuracy with various parameter as precision, recall and f1 score is 92%, 94%, 61%, 98% which is better than rest of other comparative machine learning models respectively. According to machine learning algorithms can offer insightful analysis and better forecasting abilities when processing ECG data for CHD prediction.