Predicting Heart Disease Using Machine Learning by using Logistic Regression Approach for Early Detection and Prevention

For the past decade, cardiac infection is the important source of death for several populations around world. Nowadays, heart attacks occurring in the younger generation are becoming common. The factors leading to heart disease are obesity, weight, high blood pressure, body cholesterol levels, and work environment. The biggest challenge in the medical industry is predicting and diagnosing heart disease. Machine Learning is gradually becoming established in the healthcare sector, giving us a notice of a time when data, analysis, and innovation will all work together to benefit a great number of patients. Heart Disease Prediction relies on physical examination and signs and symptoms of patients. Thus, in our work, we will be using a machine-learning algorithm to predict cardiac disorder. It has forecasted based on some properties like life time of a person, feminine, heart rate, cholesterol, etc. As implemented in this work, data processing will be used to analyze heart patients’ data. We are using a Logistic Regression machine learning algorithm to train our model for the task of predicting heart disease. LR is perfect for cardiac infection because of its straight forward approach, easy to understand for obtaining binary classification procedures, then comes the play of ML. Research and prevention for heart diseases can be improved by improving the systems that generate data; therefore, Healthy people, healthy lives. Here the comparison also done with XGBOOST and decision tree like methods.