HeartSense: Leveraging Machine Learning to Predict Cardiovascular Risk
Abstract:
Heart disease, also known as cardiovascular disease, remains one of the leading causes of mortality worldwide. Accurate prediction models are critical to advance early detection and preventive measures. This research intro duces a specialized machine learning framework to predict the severity of heart disease using Kaggle’s ”UCI Heart Disease Data,” a multivariate data set derived from the Cleveland database. This data set includes 14 predictive attributes, including clinical and demographic factors, which were used to train and evaluate various supervised learning algorithms. Notable models included logistic regression, decision trees, random forests, and gradient boosting machines. The highest performing model (XGBoost) achieved an accuracy of 62.5%. The model evalua tion relied on metrics such as precision, recall, and F1 score, which were enhanced through systematic hyperpa rameter optimization. Advanced feature engineering and cross-validation techniques further refined the model’s predictive capability. This study demonstrates how machine learning can uncover nuanced patterns within medical datasets, offering actionable insights into cardiovascular health and aiding in clinical decision-making.
