Heart Disease Prediction Using Machine Learning Algorithms

The cases of heart disease increase rapidly day by day and it is essential to predict that type of disease. The prediction is a critical task it must be performed accurately and precisely. This research paper focuses on which patient suffers from cardiovascular disease based on different medical attributes like age, cholesterol level, chest pain types, fasting blood sugar, etc. Taking the medical history of the patient we have created a cardiovascular disease prediction system to predict if the patient is suffering from disease or not. This prediction system is designed by using some of the machine learning algorithms or classifiers such as Decision Tree, Random Forest, Support Vector Machine, Naïve Bayes, K-Nearest Neighbor, Logistic Regression, and Gradient Boosting. Before running the model, the data is preprocessed to get the better accuracy. To train the model the dataset is divided into 20% testing and 80% training and achieves accuracy as follows: DT: 83.90%, RF: 88.78%, SVM: 83.90%, NB: 82.43%, K-NN: 95.60%, LR: 83.90% and GB: 86.82%. The prediction accuracy of the K-Nearest Neighbor is higher than the other algorithms. The given prediction system reduces the cost and enhances medical care. This prediction system helps us to predict patients with heart disease and is implemented in Colab .pynb format.