An Experimental Study on Applying Supervised Machine Learning Techniques for Identification and Detection of Cardiac Attacks

Predicting cardiac disease is one of the most challenging undertakings in the medical industry. At this time, heart disease is responsible for about one death per minute. Using data science to process massive volumes of information is critical in the healthcare industry. Automating the forecasting procedure is necessary to reduce risks connected by it and warn the patient well in advance because predicting heart conditions can be a difficult undertaking. The healthcare sector employs millions of people worldwide and creates a considerable amount of data. The multidimensional medical datasets are being broken down by machine learning-based algorithms, which are revealing new information. In this study, a cardiovascular dataset is successfully categorized to produce illness predictions utilizing a number of cutting-edge supervised machine learning techniques. The findings showed that the Decision Tree classification model outperformed Naive Bayes and Logistic Regression in predicting cardiovascular disease. The Decision Tree was used to obtain accuracy of 74%. This technique may help doctors identify cardiac problems early and start treatment on schedule.