Heart Disease Prediction Using Machine Learning

The heart plays a pivotal role in the functioning of living organisms, making its diagnosis and prediction of related diseases a matter of utmost importance. Approximately 17.9 million individuals succumb to cardiovascular disease, accounting for 32% of worldwide fatalities. This global concern highlights the importance of early detection, as timely treatment can significantly reduce heart disease-related mortality. Errors in diagnosis can lead to severe consequences, including fatigue or even death. The increasing prevalence of heart-related diseases necessitates the development of precise prediction systems to enhance awareness. Machine learning, a subset of Artificial Intelligence (AI), offers robust tools for predicting various events based on patterns learned from natural occurrences. This research paper evaluates the accuracy of machine learning algorithms, specifically k- nearest neighbor, decision tree, linear regression, and support vector machine (SVM), in predicting heart disease. We utilize the UCI repository dataset for training and testing and employ the Python programming language through the Anaconda Jupyter notebook for implementation and the experimental findings indicate an accuracy rate of 95.7% using the heart disease prediction model, leveraging its extensive libraries and header files to ensure accuracy and precision in our analysis.