Preemptive Diagnosis of Diabetes Mellitus Using Machine Learning

Abstract

Diabetes Mellitus (DM) is one of the most prevalent chronic diseases in the world with around 150 million patients. Patients with chronic diseases are highly susceptible to deterioration in their physical and mental health; consequently, hindering their independence, restricting their daily activities imposing a large financial burden on them and the government. If not discovered early, chronic diseases may lead to serious health complications or in extreme cases, death. Diagnostic solutions have been explored using intelligent methods, however, different ethnic groups have variant factors leading to the development of a disease. Therefore, the proposed system aims to preemptively diagnose DM in a region never explored before. Data are retrieved from King Fahd University Hospital (KFUH) in Khobar, Saudi Arabia. Data undergoes preprocessing to identify relevant features and prepare for identification/classification process. Experimental results show that ANN outperformed SVM, Naïve Bayes, and K-Nearest Neighbor with the testing accuracy of 77.5%.