Utilizing Machine Learning for Predicting Diabetes in Pregnant Women - A Comparative Analysis of Logistic Regression, Random Forest, and Naive Bayes Models

Aug 6, 2026

Upload by Ivy

Diabetes is a major global health issue marked by elevated blood glucose due to insufficient insulin synthesis or impaired insulin activity. This study examines machine learning and AI methods for predicting diabetes in pregnant women, a group with higher risk, using Logistic Regression, Random Forest, and Naive Bayes. The work aims to forecast onset, enable earlier identification, and reduce complications through faster decision support for medical professionals. Random Forest demonstrates the strongest performance with 98% accuracy on the dataset.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Keywords and Publication Details

Received and Accepted Dates

Abstract

Introduction

Diabetes background and complications

Role of AI and machine learning in diabetes prediction

Study purpose and problem scope

19(2): S. I (1), 590-596, 2024 [www.thebioscan.com](www.thebioscan.com) Utilizing Machine Learning for Predicting Diabetes in Pregnant Women: A Comparative Analysis of Logistic Regression, Random Forest, and Naive Bayes Models UTHAYA KUMAR.J1, SARITHA P.S2, RESHMA P3, Dr.RAMASAMY.S4 1. Assistant Professor, Department of Computer Science Engineering, Hindusthan Institute of Technology, Coimbatore – 32. 2. Assistant Professor, Department of Artificial Intelligence and Data Science, Dhanalakshmi Srinivasan College of Engineering, Coimbatore – 105. 3. Assistant Professor, Department of Artificial Intelligence and Data Science, Dhanalakshmi Srinivasan College of Engineering, Coimbatore – 105. 4. Associate Professor, Department of Computer Science Engineering, Hindusthan Institute of Technology, Coimbatore – 32. DOI: [https://doi.org/10.63001/tbs.2024.v19.i02.S.I](https://doi.org/10.63001/tbs.2024.v19.i02.S.I)(1).pp590-596 5. KEYWORDS Random Forest, Machine Learning, Accuracy Received on: 20-07-2024 Accepted on: 14-12-2024 ABSTRACT Diabetes is a significant worldwide health condition that affects millions of people regardless of demographic variations. Diabetes is characterized by increased blood glucose levels that are caused by inadequate insulin synthesis or activity. The purpose of this study is to investigate the use of machine learning and artificial intelligence approaches in the prediction of diabetes, specifically among pregnant women, who are a population that is at a higher risk. Through the use of sophisticated computational methods including Logistic Regression, Random Forest, and Naive Bayes models, the main objective of this work is to forecast the start of diabetes and reduce the difficulties that are connected with it. Out of all of them, the Random Forest method stands out because to its remarkable accuracy rate of 98% on the dataset, which demonstrates its potential for early identification. This research highlights the revolutionary role that machine learning plays in the delivery of prompt medical diagnosis, especially in underprivileged communities where delayed medical treatment often exacerbates health consequences. Through the simplification of the diagnosis procedure, these computational tools make it possible for medical professionals to perform diabetes management in a more effective and proactive manner. INTRODUCTION As a result of the fact that diabetes is a widespread worldwide health problem that impacts millions of people across all age groups, it has been given the nickname of the "silent pandemic"of our recent period. As a result of its extensive occurrence and the serious problems it causes, there is an immediate and pressing need for effective measures in the areas of prevention, early detection, and treatment. It is of the utmost importance to successfully address diabetes, as it continues to be one of the major causes of morbidity and death throughout the globe. A consistently increased blood glucose level is the defining characteristic of diabetes. This raised blood glucose level is caused by abnormalities in the insulin regulatory system. Insulin, a hormone that is generated by the pancreas, enhances glucose metabolism in the liver while also facilitating the absorption of glucose by muscle and fat cells. Insulin is an essential hormone atthe same time. Together, these processes bring to a reduction in blood sugar levels and help to keep the metabolic system in balance. Individuals who have diabetes, on the other hand, have this route disrupted because they have insufficient insulin synthesis, poor secretion, or resistance to the effects of insulin. Type 1 and Type 2 diabetes are the two most frequent types of diabetes, and they are both caused by this disturbance. Diabetes type 1, which is an autoimmune condition, is responsible for around five percent of all occurrences of diabetes. The condition often presents itself at an early age, when the immune sys

FAQs

Why is early diabetes prediction important for pregnant women?

Pregnancy increases risk for diabetes, and early identification helps reduce complications and supports timely clinical intervention.

Which machine learning models are compared in the study?

The study compares Logistic Regression, Random Forest, and Naive Bayes for predicting diabetes onset.

What model shows the best accuracy according to the document?

Random Forest stands out with 98% accuracy on the dataset, indicating strong potential for early detection.

Aug 6, 2026

Upload by Ivy