Evaluating The Efficacy of Machine Learning Models in Predicting Heart Disease

Abstract:-Cardiovascular diseases (CVD) remain the leading cause of mortality worldwide, with the World Health Organization (WHO) estimating nearly 20 million deaths annually due to CVD-related complications. Various risk factors, including hypertension, obesity, smoking, excessive alcohol consumption, stress, and high cholesterol, contribute to the development of CVD, significantly impairing heart function and leading to conditions such as strokes and vascular dysfunction. Early and accurate detection of CVD is crucial for effective treatment and improved patient outcomes. Machine learning (ML) has gained substantial attention in the medical field for its ability to detect, diagnose, and predict diseases with greater accuracy. This study focuses on predicting the likelihood of heart disease using ML-based prediction systems, which provide valuable insights for both medical professionals and patients. A comparative analysis of multiple ML algorithms, including random forests, decision trees, and logistic regression, was conducted using a Kaggle dataset in the Python framework. Performance evaluation metrics such as accuracy, precision, and recall were utilized to assess the effectiveness of the models. The experimental results demonstrate that the logistic regression-based model outperforms traditional approaches, achieving an overall accuracy of 85%, which is higher than existing random forest and decision tree models. The findings indicate that ML-driven prediction systems can significantly enhance early diagnosis, clinical decision-making, and personalized treatment planning for CVD. Future research will focus on integrating deep learning models, optimizing feature selection techniques, and implementing realtime monitoring systems to further improve the reliability and efficiency of heart disease prediction

---