An Analysis of Heart Disease Prediction using Machine Learning

Abstract

Heart disease is a major cause of death worldwide, making early diagnosis and prevention essential. Predictive models have gained significant attention in recent years, with several algorithms being employed to develop these models. However, there are challenges in implementing heart disease prediction models, including data quality, model accuracy, ethical concerns, and limited data. Therefore, this project aims to develop a heart disease prediction model and analyze different algorithms used in disease prediction. In order to increase the predictive accuracy of machine learning algorithms, this study compares six algorithms, including KNN (K-Nearest Neighbor), Decision Tree, Random Forest, Support Vector Machines, Logistic Regression, and Neural Network. 13 attributes, including age, sex, and cholesterol, are used, and ensemble methods like boosting and bagging are used. The accuracy, recall, f1 score, and precision of each algorithm are calculated to determine the most accurate model. Additionally, this study identifies the limitations of heart disease prediction models and their implications for patient diagnosis and treatment, by developing and analyzing heart disease prediction models. In conclusion, while heart disease prediction models have the potential to be financially feasible and be useful in the future, their current limitations and challenges mean that they cannot be relied upon as the sole means of diagnosis or treatment decisions.