Machine Learning, Ensembles, and Knowledge Graphs for Diabetes Prediction

DOI

10.2991/978-94-6239-648-7_72How to use a DOI?

Keywords

Diabetes Detection; Knowledge Graph; Ensemble Learning; Disease Prediction

Abstract

This article reviews the progress of machine learning in early prediction and risk identification of diabetes, focusing on three methods: traditional models (such as Logical Regression, SVM, RF, etc.), ensemble learning (such as Bagging, Boosting, Stacking and weighted voting) and Reasoning based on knowledge graph (KG). The traditional model has the advantages of robustness and strong interpretability, which is suitable for small samples and structured features. Ensemble learning further improves the accuracy and generalization ability through the complementarity of heterogeneous models. The knowledge atlas explicitly uses the entity relationship diagram for modeling, which takes into account interpretability and reasoning ability in the absence of features and incomplete knowledge. This article compares the application limitations of various methods in data utilization, feature engineering, category unbalance processing and model calibration. It points out that traditional methods rely on preprocessing and linear assumptions, integrated models need to achieve a balance between complexity and interpretability, and the cost of knowledge atlas construction and maintenance is high, but it is convenient for Physical decision-making support. From clinical applications perspective, it is recommended to strictly prevent information leakage, combine resampling and calibration indicators (AUC/PR-AUC, F1, Brier), introduce interpretation tools such as SHAP, and verify the robustness of the model on independent data. In a word, in order to achieve accurate prevention and intelligent management. It is helpful to seek the best balance between performance, complexity and interpretability according to tasks and resource conditions.

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  - Jiayi Jiang
PY  - 2026
DA  - 2026/04/24
TI  - Machine Learning, Ensembles, and Knowledge Graphs for Diabetes Prediction
BT  - Proceedings of the International Workshop on Advances in Deep Learning for Image Analysis and Computer Vision (IWADIC 2025)
PB  - Atlantis Press
SP  - 667
EP  - 675
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-648-7_72
DO  - 10.2991/978-94-6239-648-7_72
ID  - Jiang2026
ER  -