HEARTFIT: Heart Disease Prediction Using Machine Learning Techniques

“Worldwide, heart disease is the leading killer. Several forms of cutting-edge medical technology are utilized to treat cardiac illnesses. The biggest issue in hospitals is that many doctors lack the necessary training and experience to manage patients. This leads to them making poor decisions, which unfortunately often result in patient deaths. Hospitals are pivotal in automating diagnosis through the use of data mining and machine learning algorithms to tackle these issues with heart disease forecasts. By examining the patient’s various vital signs, it is possible to forecast the course of heart disease. Various techniques including ANNs, decision trees, KNN, and naïve Bayes can be employed for the purpose of cardiac disease prediction. Several factors have been employed in the prediction of cardiac disease. Gender, age, and cerebral palsy are the three criteria that must be taken into account. Cerebral palsy (CP), blood pressure, gender, fasting blood sugar test (FBS), etc. For this research, we drew on an integrated dataset. Using the same dataset, we have created five distinct approaches to forecast cardiac illness. A number of algorithms have been put into use, including ANN, Decision trees, Naive Bayes, k-nearest Neighbor (KNN), Random Forest. Finding the most accurate method for forecasting the occurrence of heart disease from a variety of health indicators is the focus of this investigation. Based on the results of the experiment, Naïve Bayes achieved the best accuracy rate of 88%.”