Abstract

The rapid increase in the amount of data in the healthcare sector has increased the importance of machine learning and data analysis techniques based on artificial intelligence in disease prediction and risk identification. n this context, heart disease prediction is one of the most frequently addressed problems. In this section, classification algorithms used in health are discussed and a sample application in heart disease prediction is performed to demonstrate the accuracy and reliability of the algorithms. Using a dataset of 1025 samples from the UCI data repository, heart disease prediction was performed with supervised machine learning models such as Logistic Regression, Decision Trees, Support Vector Machines, K-Nearest Neighbor and Naive Bayes over 14 attributes and the results were interpreted. The study tries to show how different algorithms process the features in the dataset and which model performs better. As a result, it is shown how algorithms can be used in heart disease prediction with practical application and how the results can be interpreted.