Abstract
Diabetes Mellitus (DM) is a metabolic disorder that occurs when the blood sugar level in the body is considered to be high, thereby resulting in inadequate insulin in the body leading to a myriad complications. The World Health Organization in 2021 indicated that in 2019, diabetes was the direct cause of 1.5 million deaths. Though some research has been carried out in the area of DM prediction in high-income countries, not much has been done in middle/low-income countries like Nigeria, using factors that are peculiar to their environment. This paper, therefore, aims to develop a machine learning model that predicts DM in individuals at an early stage. The study identified nine DM attributes and used three supervised learning algorithms of K Nearest Neighbors (KNN) decision trees, and artificial neural networks (ANN) to predict DM from a locally collected dataset in Nigeria. The results indicate that ANN produced the highest accuracy, at 97.40%.
