ENHANCED HEART DISEASE PREDICTION USING ADVANCED MACHINE LEARNING TECHNIQUES

Abstract

Heart disease continues to be a leading cause of mortality globally, underscoring the urgent need for effective predictive models that can facilitate early diagnosis and intervention. This paper presents a comprehensive approach to heart disease prediction by employing advanced machine learning techniques, specifically a hybrid model that integrates Random Forest and Support Vector Machine (SVM) algorithms. By leveraging the strengths of these algorithms, our model effectively captures complex patterns within clinical data, leading to enhanced prediction accuracy. We conducted extensive experiments using a robust dataset sourced from various healthcare repositories, demonstrating that the proposed hybrid model significantly outperforms traditional predictive models, achieving an accuracy of 92%. Additionally, our results indicate improved sensitivity and specificity, highlighting the model's potential to accurately identify patients at risk of heart disease. This research not only contributes to the field of predictive analytics in healthcare but also lays the groundwork for future studies that may incorporate additional data sources, such as genetic information and real-time health monitoring from IoT devices. Ultimately, our findings advocate for the integration of advanced machine learning techniques in clinical practice to improve patient outcomes and optimize healthcare delivery.