Comparative Analysis of Machine Learning Algorithms for Diabetes Prediction - Finding the Optimal Approach

Aug 3, 2026

Upload by Noah

Diabetes is a chronic condition with a rapidly rising impact on human health, driven by intertwined factors such as obesity, high blood glucose, and other physiological triggers linked to impaired insulin function. This study proposes a machine learning–based solution using the Pima Indian diabetes (PID) dataset. Multiple algorithms, including SVM and Random Forest, are evaluated to forecast diabetes onset. The work aims to identify at-risk individuals for timely intervention and to support lifestyle and dietary adjustments, achieving both model development and strategy assessment objectives.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Introduction

Diabetes background and types

Motivation for early detection

Comparative study of machine learning algorithms

Paper organization

Comparative Analysis of Machine Learning Algorithms for Diabetes Prediction: Finding the Optimal Approach Aftab UL Nabia, Neetesh Kumarb,Waqas Chanderc, Sunil Kumard, Muhammad Waqas Pashae, Rajesh Kumarf* aDepartment of Computer science, South China University of Technology, China bDepartment of Computer Science & Information Technology, TIEST, NED University, Pakistan cDepartment of Electrical Engineering, Mehran University of Engineering and Technology, Pakistan dDepartment of Electronics Engineering, Quaid Awam University of Engineering and Technology, Pakistan eDepartment of Computing, Hamdard University, Pakistan fDepartment of Computer Science, University of Palermo, Italy [a](aEmail: aftab.shahani@mail.scut.edu.cn)[Email: aftab.shahani@mail.scut.edu.cn](aEmail: aftab.shahani@mail.scut.edu.cn), bEmail: [neeteshkumar@neduet.edu.pk](neeteshkumar@neduet.edu.pk) [c](cEmail: waqaschander445@gmail.com)[Email: waqaschander445@gmail.com](cEmail: waqaschander445@gmail.com), dEmail: [sunilrathi474@gmail.com](sunilrathi474@gmail.com) [e](eEmail: waqaspasha90@gmail.com)[Email: waqaspasha90@gmail.com](eEmail: waqaspasha90@gmail.com), fEmail: [rajesh.kumar@unipa.it](rajesh.kumar@unipa.it) Abstract Diabetes, as a chronic disease, poses a rapidly escalating risk to human health, stemming from a complex interplay of factors such as obesity, elevated blood glucose levels, and various other triggers. Central to its onset is the disruption of insulin hormone function, resulting in abnormal metabolism and increased blood sugar levels. In this paper, we propose a solution to this pressing issue using machine learning techniques. By applying various machine learning algorithms on the Pima Indian diabetes (PID) dataset, we aim to identify the most effective algorithm for this task. Leveraging powerful machine learning algorithms such as (SVM) Support Vector Machine, (RF) Random Forest and others, we endeavor to forecast the onset of diabetes. Through the amalgamation of these techniques, our objective is to proactively identify individuals at risk, enabling timely intervention and preventive measures to safeguard health. The primary goal of this initiative is to mitigate the risk of diabetes onset by forecasting individuals' susceptibility and advocating for lifestyle and dietary adjustments. This study has dual objectives: firstly, to develop and implement a predictive model for diabetes using machine learning techniques, and secondly, to explore effective strategies for achieving success in this endeavor. Keywords: Machine learning; Classification; Prediction; Support vector machine. Received: 4/25/2024 Accepted: 6/10/2024 Published: 6/21/2024 * Corresponding author. 1. Introduction The World Health Organization (WHO) stipulated that approximately 1.6 million individuals succumb to diabetes annually [1] . Diabetes manifests when the blood sugar, or glucose, levels in the body become excessively high. Health experts attribute diabetes to two main causes: inadequate insulin production by the pancreas (Type 1 diabetes) and ineffective utilization of the generated insulin by the body's cells (Type 2 diabetes) [2] . According to data from the Centers for Prevention and Control of Diseases (CDCP), type 2 diabetes saw a twenty-three percent surge in the United States from 2001 to 2009. Organizations, government agencies, and medical organizations worldwide are intensifying efforts toward the control and prevention of chronic diseases to avert premature fatalities. Diabetes is predominantly classified into two types: type I and type II. Type I diabetes, also referred to as Insulin-Dependent Diabetes Mellitus, arises when the body fails to produce sufficient insulin, accounting for 10% of all diabetes cases [3] . Type II diabetes, on the other hand, is distinguished by relative insulin deficiency due to pancreatic β-cell dysfunction and elevated levels of insulin in target organs [4] . According to the statistics releas

FAQs

What problem does the paper address in relation to diabetes?

The paper addresses early identification of individuals at risk of diabetes by forecasting diabetes onset. It links diabetes onset to disrupted insulin function and abnormal metabolism.

Which dataset and machine learning approach are used to compare algorithms?

The study applies multiple machine learning algorithms to the Pima Indian diabetes (PID) dataset. It compares algorithms across several categories to determine the most effective approach.

Which algorithms are highlighted for diabetes prediction?

The paper highlights Support Vector Machine (SVM) and Random Forest, along with other machine learning models. The goal is to evaluate their effectiveness for predicting diabetes onset.

Aug 3, 2026

Upload by Noah