Advancing Heart Disease Prediction through Synergistic Integration of Machine Learning and Deep Learning Techniques

The alarming and critical need for early identification of heart disease is heightened by the daily rapid increase in the prevalence of this condition. The process of making a cardiac diagnosis is complex and time-consuming, requiring expert judgment. It is essential for cardiologists to accurately diagnose and predict the prognosis of cardiovascular disease to properly categorize and treat their patients. Due to their capacity to recognize data patterns, Machine Learning (ML) algorithms are increasingly used in healthcare. There may be fewer misdiagnoses of cardiac disease if diagnosticians use machine learning to categorize patients. Using certain parameters, this study aims to construct a machine-learning model that can predict the incidence of heart disease. The UCI Machine Learning Heart Disease dataset is analyzed in thiswork using a range of ML and Deep Learning (DL) approaches. In the sample, heart disease is associated with fourteen different factors. Machine learning methods such as Naive Bayes (NB), Support Vector Machines (SVM), K-Nearest Neighbours (KNN), and Randam Forest (RF) are widely used. More so than competing ML methods, CNN achieves superior results in processing economy and prediction accuracy. In the research, the region of curve (ROC) curve and Area under curve (AUC) were used. To verify the findings, the accuracy and AUC ratings were checked. With both training and testing data, the CNN model excels, leading to better results.