Heart disease is a global epidemic that affects millions of people and is responsible for a significant portion of annual deaths worldwide. Timely diagnosis and prediction of heart disease can save countless lives, and advancements in information technology have opened up new avenues for improving medical diagnosis. In this project, we aimed to explore the use of machine learning classification techniques for predicting the presence of heart disease in patients. We deployed five classification techniques: Logistic Regression, Decision Tree, Random Forest, K Nearest Neighbors, and Support Vector Machine. We used a dataset of 1025 observations with 13 features and one target variable. The features were selected through statistical analysis, including the T-test and Chi-Square Test. The model's performance was evaluated based on metrics such as overall accuracy, balanced accuracy, precision, recall, and area under the curve. The study results showed that KNN and Random Forest were the best-performing models. These models' performance was verified through a receiver operating characteristic (ROC) plot. Our research concluded that the proposed system could be easily implemented in the healthcare sector to accurately predict the presence of heart disease in patients. Overall, this study highlights the potential of machine learning techniques in improving the early diagnosis and treatment of heart disease, ultimately saving lives.
Professional Studies (MS)
Department, Program, or Center
Graduate Programs & Research (Dubai)
Alshamsi, Wadeema, "Identifying The Causes of Heart Disease Using Classification Techniques" (2023). Thesis. Rochester Institute of Technology. Accessed from