A NOVEL NEURAL NETWORK APPROACH FOR HEART DISEASE DETECTION

Abstract

Heart disease remains a leading cause of morbidity and mortality globally, emphasizing the critical need for accurate and timely diagnostic methods. This review paper systematically explores the application of optimum methods for heart disease detection, offering a comprehensive survey of various algorithms employed in this domain. The paper begins by elucidating the significance of early detection and diagnosis in mitigating the impact of heart disease on public health. The review meticulously investigates and compares diverse algorithms utilized in heart disease detection, ranging from classical ML approaches to state-of-the-art DL techniques. These algorithms include but are not limited to decision trees, support vector machines,NNs, and ensemble methods. The study critically evaluates the strengths and limitations of each algorithm, considering factors such as computational efficiency, interpretability, and scalability. Additionally, the review highlights recent advancements in feature selection and extraction techniques that contribute to enhancing the performance of heart disease detection models. The discussion also delves into the integration of innovative technologies, such as wearable devices and internet of things (IoT), to facilitate continuous monitoring and early detection of cardiac anomalies.