Prediction of Pre-Diabetes Based on Random Forest

DOI

10.2991/978-94-6239-648-7_7How to use a DOI?

Keywords

Pre-Diabetes; Random Forest; Early Risk Prediction

Abstract

Diabetes, as one of the most severe chronic diseases globally, has seen an increase in prevalence in recent years rather than a decrease. Early screening for diabetes relies on traditional biochemical indicators, resulting in a high rate of missed diagnoses and insufficient resources at the grassroots level. It has become urgent to construct a diabetes risk early warning analysis model through machine learning. This study uses 768 cases of Pima Indians data as the object to construct a 100-tree Random Forest (RF) model, aiming to improve the accuracy and interpretability of diabetes prediction. Methodologically, missing values are filled with the median, the training/test set is divided at 79.9%/20.1%, and feature contributions are quantified through permutation importance. The experimental results demonstrate that the accuracy of the test set reaches 80.52%, with an F1 score of 0.85. The contributions of Glucose, BMI, and Age are 27.4%, 18.1%, and 15.3%, respectively. The finding indicates that Random Forest is robust and effective in small-sample medical scenarios, and its permutation importance analysis can be directly translated into clinically actionable decision-making basis, providing both accuracy and operability for early screening of diabetes.

Copyright

© 2026 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  - Qihan Li
PY  - 2026
DA  - 2026/04/24
TI  - Prediction of Pre-Diabetes Based on Random Forest
BT  - Proceedings of the International Workshop on Advances in Deep Learning for Image Analysis and Computer Vision (IWADIC 2025)
PB  - Atlantis Press
SP  - 50
EP  - 59
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-648-7_7
DO  - 10.2991/978-94-6239-648-7_7
ID  - Li2026
ER  -