Abstract :

Diabetes Mellitus Is One Of The Most Rapidly Increasing Chronic Diseases In Today S World, And Early Diagnosis Is Crucial To Prevent Complications And To Otherwise Improve The Health Of Patients With The Condition. With The Expansion Of Clinical And Health Information And The Complexity Of Data Processing, Traditional Machine Learning Models Have Struggled To Meet The Growing Demand. The Explosion Of Clinical Data And Health Records Has Positioned New Challenges For Old Machine Learning Models In The Face Of Mounting Data Quantities And Processing Demand. In This Paper, A Machine Learning-based Approach For Diabetes Prediction Is Introduced Based On Distributed Data Processing Approach With Hadoop MapReduce Is Presented. The Data Pre-processing Methods, Feature Engineering Techniques, Hadoop Distributed File System (HDFS), MapReduce-based Parallel Processing, And Supervised Machine Learning Algorithms Are Also Suitable For Addressing The Challenges Of Analyzing Large Healthcare Datasets. The Data Pre-processing Methods, Feature Engineering Techniques, Hadoop Distributed File System (HDFS), MapReduce-based Parallel Processing And Supervised Machine Learning Algorithms Are Also Suitable For Addressing These Challenges. The Distributed Design Helps Fast Training Of Models And Prediction, With A High Classification Performance. Through The Experimental Evaluation, It Is Proven That The Proposed Framework Achieves Computational Efficiency, Scalability, And The Accuracy Of The Predictions As Compared To The Traditional Centralized Approaches. The Proposed Solution Offers A Scalable And Reliable Architecture For Intelligent Healthcare Analytics And Real-time, Clinical Decision Support.

Published:

14-2-2026

Issue:

Vol. 26 No. 2 (2026)

Page Nos:

366-372

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite