Early Detection of Diabetics using Machine Learning

Read full text Summarise with VIRAT
Authors: A. Meena Kabilan, Divya Dharshini K V
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Diabetes stands out as a long-term metabolic issue affecting countless folks around the world. Early spotting of it really matters for keeping preventive care on track. This work lays out a machine learning setup for predicting diabetes. It relies on just three key body measures. Those include BMI, glucose readings, and age. The goal is to sort people into diabetic or not diabetic groups. We cleaned up the data set first. Then we looked it over closely. After that, we fed it into various supervised learning methods. In the end, the chosen model hit 69 percent accuracy. This shows how even a small set of strong features can lead to useful health predictions. Overall, the tool works as a simple aid for checking diabetes risks early on.

Fields of Study & Subjects

Artificial Intelligence in Healthcare Data Mining and Machine Learning Applications Natural Antidiabetic Agents Studies

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
30 March 2026
Language
EN