Title: Novel machine learning model for fast and accurate diabetes prediction

Authors: Prosanjeet Jyotirmay Sarkar

Addresses: Department of Electronics and Communication Engineering, Dr. A.P.J. Abdul Kalam University, Indore, Madhya Pradesh, India

Abstract: Diabetes mellitus, one of the fastest spreading chronic diseases in the world and is related to anomalous, undeniably escalated levels of glucose in the blood. The primary step towards controlling and minimising the risk factor of diabetes is the early detection of diabetes. The adoption of machine learning algorithms in conjunction with the analysis of acquired data facilitates the early detection and prognostication of diseases. The aim of this study is to propose a reliable and efficient novel machine learning model for predicting diabetes mellitus with better accuracy. For experimental evaluation, the Pima India diabetes dataset (PIDD) and diabetes dataset are used. During the analysis, it was observed that the novel machine learning model outperformed other classifiers with 99.6% accuracy on the PIDD and 99.8% accuracy on the diabetes dataset. The findings reveal the newly developed machine learning model in prediction of diabetes mellitus more accurately.

Keywords: novel machine learning model; diabetes; accuracy; robustness; prediction.

DOI: 10.1504/IJBT.2025.144586

International Journal of Biotechnology, 2025 Vol.15 No.1, pp.87 - 103

Received: 31 Oct 2023
Accepted: 28 Dec 2023
Published online: 23 Feb 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article