Prediction of Heart Disease Using Machine Learning with Data Mining

Abstract

Aim: In this study, it was aimed to make a categorical estimation of the absent/presence of heart disease by using some parameters (age, sex, cp, trestbps, chol, fbs, restecg, thalach, exang, oldpeak, slope, ca, thalach) of healthy and heart disease individuals. Material and Methods: The classification was obtained with multiple linear regression (MLR) of machine learning in the R Studio program. Machine learning has been improved by selecting parameters that have a high contribution to the prediction by using the Akaike information criterion. Results: The classification was performed using the biomarkers from glm.fit.1, which produced the lowest AIC value (237.48). The accuracy of the MLR model used was 88%, the precision was 93%, the sensitivity was 86%, and the specificity was 91%. It was found that age data from biomarkers contributed little to the prediction. Conclusion: MLR is a preferable method for categorical disease classification.