Early Diabetes Detection using Novel Hybird Machine Learning Algorithm

DOI

10.2991/978-94-6463-754-0_37How to use a DOI?

Keywords

K-fold; decision tree; Gradient; pregnancies; accuracy

Abstract

The early diagnosis and healthcare monitoring, is one of the major health concerns in worldwide. In order to develop precise model that classify the diabetes machine learning offers numerous algorithms. The machine learning techniques promised for detection of diabetes as fast as and also its cost effective when compared to the traditional methods. Therefore, in order to identify diabetes early, we proposed a novel hybrid technique in study that incorporates Decision Tree (DT) and Gradient Boosting Classifiers (GBC). In order to increase forecast accuracy, we incorporate new features like pregnancies, glucose, insulin, BMI, and age. The K-fold cross validation approach was used to train and test the machine learning techniques by using the Pima Indian Diabetes Dataset (PIDD). In the proposed system a novel hybrid algorithm achieved forecast accuracy rate of 90.5% and for K-fold cross validation it achieved forecast accuracy of 92%. The Decision Tree and Gradient Boost Classifiers achieved forecast accuracy rate of 78% and 80%. Also, we use precision, recall and F1-score to evaluate the algorithms performance. Those performance metrics are essential for predicting diabetes as they demonstrate the algorithms potential to accurately determine actual positive and minimize false positives. They emphasize the efficiency of algorithm in diabetes prediction in order to establish it as an essential tool for early prediction.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - B. Kalaivani
AU  - A. Chandrasekhar
AU  - P. Sangeetha
AU  - M. Renukadevi
AU  - M. Prakash
PY  - 2025
DA  - 2025/06/30
TI  - Early Diabetes Detection using Novel Hybird Machine Learning Algorithm
BT  - Proceedings of the 2025 International Conference on Advanced Research in Electronics and Communication Systems (ICARECS-2025)
PB  - Atlantis Press
SP  - 423
EP  - 433
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-754-0_37
DO  - 10.2991/978-94-6463-754-0_37
ID  - Kalaivani2025
ER  -