Automated Heart Disease Prediction System using Machine Learning Approaches

The healthcare industry collects large, complex data. This information is not “extracted” to find hidden facts for effective decision-making. Heart disease, a non-communicable disease, is difficult to diagnose since it requires a patient's medical history. A accurate and effective automated system can detect cardiac problems. Modern data mining may solve this. In healthcare, association rule mining, classification, and clustering are used to predict cardiac disease. An automated Heart Disease Prediction System was created using data mining algorithms like Decision Trees, Naive Bayes, and Neural Networks. Results show that each strategy has a distinct advantage in reaching mining goals. Age, sex, blood pressure, and blood sugar can indicate heart disease risk. It helps establish important knowledge like heart disease trends and linkages. This showed that the prediction algorithm can accurately anticipate heart attacks.