Heart Disease Risk Prediction Expending of Classification Algorithms

Heart disease prognosis (HDP) is a difficult undertaking that requires knowledge and expertise to predict early on. failure on the rise as result of today’s lifestyle. The healthcare business generates vast volume patient records, which are challenging manage manually. When it comes data mining machine learning, having huge crucial for getting meaningful information. Several methods predicting HD have been used by researchers over last few decades, but fundamental concern remains uncertainty factor in output data, well need decrease error rate enhance accuracy HDP assessment measures. However, order discover optimal solution, this study compares multiple classification algorithms utilizing two separate heart datasets from Kaggle repository University California, Irvine (UCI) learning repository. In comparative analysis, Mean Absolute Error (MAE), Relative (RAE), precision, recall, f-measure, evaluate Linear Regression (LR), Decision Tree (J48), Naive Bayes (NB), Artificial Neural Network (ANN), Simple Cart (SC), Bagging, Stump (DS), AdaBoost, Rep (REPT), Support Vector Machine (SVM). Overall, SVM classifier surpasses other classifiers terms increasing decreasing rate, with RAE 33.2631 MAE 0.165, precision 0.841, recall 0.835, f-measure 0.833, 83.49 percent dataset gathered UCI. SC improves reduces dataset, 3.30% RAE, 0.016 MAE, 0.984% 0.984 98.44% accuracy.