Comparative Analysis on Cardiac and Diabetic Disease Prediction Using Machine Learning Techniques

Diabetes and cardiac conditions are essentially distinguished by elevated blood glucose levels and cardiovascular disorders, respectively. A diverse array of complex illnesses, including but not limited to heart attack, renal failure, and stroke, are associated with it. Diabetes has a global prevalence of over 422 million people in 2014, making it the most common metabolic disease on the planet. The primary objective of this study is to evaluate and compare the performance of Support Vector Machines (SVM), Decision Trees, Artificial Neural Networks (ANN), and k-nearest Neighbors (KNN) in classifying diabetes and cardiac patients using a specific dataset. The present study serves as a roadmap for future research in predictive analytics for cardiac and diabetes ailments by analyzing current literature and identifying research gaps. The primary objective is to create the way for the generation of robust, accessible, and clinically feasible ML models that can significantly contribute to the early identification and management of these common health conditions, thus enhancing the outcomes of patients as well as decreasing the burden on healthcare systems around the world. Models based on supervised learning algorithms have been discussed along with other interesting findings that are important in developing overall understanding of model for disease prediction algorithms. This study carefully assesses the selected papers and finds gaps in the current literature that will be helpful for researchers to develop and use in clinical domains, especially on heart and diabetic disease data sets. This study will also help medical professionals to identify cardiac and diabetic risks in advance, enabling them to take preventive actions.