HeartShield: Machine Learning-Based Heart Disease Risk Prediction

Heart disease is one of the leading causes of death globally. Early detection can significantly improve outcomes, yet conventional risk assessment methods can be slow or inaccessible. This paper introduces HeartShield, a machine learning-based application designed to predict the risk of heart disease using user-provided data such as age, blood pressure, and cholesterol. Using a Random Forest Classifier trained on the UCI Heart Disease dataset, the model achieved an accuracy of 81.33%. This paper outlines the methodology, challenges encountered, experimental results, and discusses future improvements for expanding the model’s clinical relevance.