PREDICTION OF HEART DECEASE USING MACHINE LEARNING ALGORITHM

Abstract Despite significant advancements in medical science, early detection and diagnosis of CVDs continue to pose challenges due to the complex and diverse nature of heart disease patterns. Traditional diagnostic methods are often time-consuming, subjective, and reliant on expert interpretation, which may delay timely intervention. This study explores the development and optimization of machine learning (ML) models for the early prediction of cardiovascular diseases, emphasizing the role of hyperparameter optimization in improving model accuracy and reliability. Several ML algorithms including LR, RF, SVM, K-N Neighbors, and Artificial Neural Network were implemented and evaluated using performance metrics such as accuracy, precision, recall, and F1-score. The Artificial Neural Network (ANN) demonstrated superior performance, highlighting the potential of deep learning models in capturing complex medical patterns. The study adopted the Extreme Programming (XP) model of the Software Development Lifecycle (SDLC) to ensure iterative design, testing, and refinement, enhancing system responsiveness to user requirements. Results revealed that hyperparameter tuning significantly improved the efficiency and robustness of ML models, enabling accurate disease prediction while minimizing false classifications. This research contributes to the growing field of AI-driven healthcare by presenting a reliable and interpretable ML-based diagnostic tool capable of supporting medical professionals in making timely, data-informed decisions. Furthermore, it emphasizes the importance of high-quality datasets, ethical data handling, and model interpretability for real-world clinical integration. The study concludes that the integration of optimized machine learning systems into healthcare has the potential to revolutionize early CVD diagnosis, improve patient outcomes, and reduce global mortality rates. Keywords: Cardiovascular diseases, Machine Learning, Hyperparameter Optimization, Artificial Neural Network, Predictive Modeling, Early Diagnosis, Healthcare Systems.