A Predictive Model for Diabetes Mellitus Using Machine Learning Techniques - A Study in Nigeria

Aug 5, 2026

Upload by Jiven

Diabetes Mellitus is a metabolic disorder in which elevated blood glucose reflects inadequate insulin action, leading to serious complications and large global mortality burdens. Research on DM prediction has advanced in high-income settings, yet comparatively limited work applies locally relevant factors in middle/low-income contexts such as Nigeria. This study develops a machine learning model to predict DM at an early stage using nine DM attributes and three supervised algorithms, with results showing artificial neural networks achieving the highest accuracy of 97.40%.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Abstract

Introduction

Diabetes prevalence and global burden

Disease mechanism and clinical challenges

Motivation for machine learning in medical diagnosis

Keywords

Research context (Nigeria) and study objective

The African Journal of Information Systems | Volume 15 Issue 1 | Article 1 | | --- | --- | | January 2023
A Predictive Model for Diabetes Mellitus Using Machine Techniques (A Study in Nigeria)
Abraham Eseoghene Evwiekpaefe
Nigerian Defence Academy, Kaduna, Nigeria, [aeevwiekpaefe@nda.edu.ng](aeevwiekpaefe@nda.edu.ng)
Nafisat Abdulkadir
Nigerian Defence Academy, Kaduna, Nigeria, [nafisahabdulkadir@gmail.com](nafisahabdulkadir@gmail.com)
Follow this and additional works at: [https://digitalcommons.kennesaw.edu/ajis](https://digitalcommons.kennesaw.edu/ajis)
Part of the Computer Sciences Commons | Learning | Recommended Citation Evwiekpaefe, Abraham Eseoghene and Abdulkadir, Nafisat (2023) "A Predictive Model for Diabetes Mellitus Using Machine Learning Techniques (A Study in Nigeria)," The African Journal of Information Systems: Vol. 15: Iss. 1, Article 1. Available at: [https://digitalcommons.kennesaw.edu/ajis/vol15/iss1/1](https://digitalcommons.kennesaw.edu/ajis/vol15/iss1/1) This Article is brought to you for free and open access by DigitalCommons@Kennesaw State University. It has been accepted for inclusion in The African Journal of Information Systems by an authorized editor of DigitalCommons@Kennesaw State University. For more information, please contact [digitalcommons@kennesaw.edu](digitalcommons@kennesaw.edu). A Predictive Model for Diabetes Mellitus Using Machine Learning Techniques (A Study in Nigeria) Cover Page Footnote Our appreciation goes to the management and staff of 44 Nigerian army reference Hospital, Kaduna and Yusuf Dan-Tsoho Memorial Hospial, Tudun Wada, Kaduna, Nigeria for their assistance during the data collection. This article is available in The African Journal of Information Systems: [https://digitalcommons.kennesaw.edu/ajis/](https://digitalcommons.kennesaw.edu/ajis/)[ ](https://digitalcommons.kennesaw.edu/ajis/)vol15/iss1/1 A Predictive Model for Diabetes Mellitus Using Machine Learning Techniques (A Study in Nigeria) Research Paper Volume 15, Issue 1, January 2023, ISSN 1936-0282 Abraham Eseoghene Evwiekpaefe Nigerian Defence Academy [aeevwiekpaefe@nda.edu.ng](aeevwiekpaefe@nda.edu.ng) Nafisat Abdulkadir Nigerian Defence Academy [nafisahabdulkadir@gmail.com](nafisahabdulkadir@gmail.com) (Received January 2021, accepted May 2022) 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 ofK 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% . Keywords Diabetes mellitus, metabolic disorder, healthcare sector, artificial neural network. INTRODUCTION The prevalence of diabetes is on the rise worldwide. The International Diabetes Federation notes that there are about 382 million people living with diabetes in the world and that by 2035, this will be doubled, as 592 million (Pradhan et al., 2020) . This rise might be narrowed down to the age bracket of the populace, rate of urbanization, and continuous approval of unhealthy lifestyles. Some of these factors have inadvertently resulted in key health challenges around the world (Liu et al., 2013) . In 2021 The World Health Organization noted that abo

FAQs

What problem does the study address regarding diabetes prediction?

It addresses limited development of diabetes prediction models in middle/low-income countries like Nigeria using environment-specific factors.

Which machine learning techniques were used to predict diabetes mellitus?

The study uses three supervised learning algorithms: K-Nearest Neighbors (KNN), decision trees, and artificial neural networks (ANN).

What model achieved the highest accuracy and what was that accuracy?

Artificial neural networks (ANN) produced the highest accuracy, reaching 97.40%.

Aug 5, 2026

Upload by Jiven