Heart Disease Prediction using Machine Learning

Computer Engineering

Heart disease (HD) is one of the most common diseases nowadays, and people who provide health care, it is very necessary to work with them to take care of their patient's health and save their life. In this paper, different classifiers were analyzed by performance comparison to classify the Heart Disease dataset to classify it correctly and or to Predict Heart Disease cases with minimal attributes. Large amounts of data that contain some secret information were collected by the healthcare industries. This data collection is useful for making effective decisions. Some advanced data mining techniques are used to make proper results and make effective decisions on data. In this case, a Heart Disease Prediction System (HDPS) is developed using Logistic Regression, K Nearest Neighbour, Decision Tree, Random Forest Classifier, and Support Vector Machine algorithms to predict the heart disease risk level. The results reveal that the Random Forest Classifier and Support Vector Machine obtained the the highest accuracy of 91.23%, whereas 86.79%, 71.69%, and 83.47% accuracy scores are obtained by logistic regression, KNN classifier, and decision tree respectively.

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