A Study on Prediction of Cardiac Diseases Utilising a Machine Learning Approach for Logistic Regression

In this study, a system is developed to forecast heart disease that can help doctors identify a patient's potential cardiac problem or not based on clinical data about the patient. Our processes consist of three steps. Age, sex, cp, trestbps, chol, fbs, restecg, thalach, exang, old peak, slope, ca, and thaI were the initial 13 important clinical factors to be chosen. Second, we use these clinical characteristics to construct a machine learning model for heart disease prediction. The accuracy of predictions is over 62.2%. The final output is the HDPS, a user-friendly system for predicting heart disease. One of the elements of the HDPS system will be a place for adding clinical data. The method works well for figuring out whether a patient has cardiac disease. created by the HDPS system.