Heart Disease Prediction Using Machine Learning

Cardiovascular disease, essentially a broad term for heart disease, has topped the list of causes of death in the world for several decades. Since this condition is influenced by several risk factors, there is a considerable need for precise and reliable methods that will enable early diagnosis and timely management. Data mining is emerging as an important technique for managing large amounts of medical data, helping health professionals make more precise predictions regarding heart disease.The present work uses various techniques of machine learning and data mining to analyze complex medical datasets. This work specifically focuses on supervised learning algorithms, including Naïve Bayes, decision tree, KNN, and random forest. The employed data set comes from the Cleveland database in the UCI repository, which deals with data from patients affected by heart diseases. Although the dataset has 303 instances and 76 attributes, the analysis is performed only on the selected 14 key attributes to estimate the performance of a few models. In this research, the determination of heart disease in patients is the goal.