Predictive Techniques in Machine Learning for Heart Disease

Heart disease, also known as cardiovascular disease, is a broad term encompassing various conditions that affect the heart and blood vessels. These disorders can range from mild to life-threatening and significantly impact an individual’s quality of life. Given the multiple risk factors associated with heart disease, early detection is essential for effective management and treatment. Therefore, there is a pressing need for reliable, practical methods to identify individuals at risk and ensure timely intervention. Data mining has emerged as a powerful technique for extracting valuable insights from large healthcare datasets. By applying advanced algorithms and statistical methods, data mining can uncover hidden patterns, trends, and relationships indicative of disease progression, underlying conditions, or treatment responses. Through sophisticated data mining and machine learning techniques, researchers can analyze complex medical data on a large scale, improving the accuracy of heart disease risk prediction. This study focuses on exploring factors associated with heart disease and building predictive models using supervised learning techniques such as Naïve Bayes, K-nearest neighbors (KNN), decision trees, and random forests. A benchmark dataset from the UCI Machine Learning Repository, containing 303 patient records with 76 attributes, was used. For this research, 14 key attributes were selected to enhance prediction accuracy. The main aim is to predict an individual’s susceptibility to cardiovascular disease. Results show that the K-nearest neighbors (KNN) algorithm outperformed other models, achieving the highest predictive accuracy in assessing heart disease risk.