Advancing Diabetes Prediction: A Nuanced Six-Class Classification System and Risk Factor Interactions Investigation

DOI

10.2991/978-94-6463-300-9_71How to use a DOI?

Keywords

Machine Learning; Diabetes Prediction; Interaction Effects Analysis

Abstract

This study advances diabetes prediction by introducing a nuanced, six-class classification system and examining the interaction effects of various risk factors. Rather than the traditional binary classification, this research proposes six distinct diabetes classes: normal, pre-diabetic, diabetic under control, diabetic fair control, diabetic poor control, and diabetic very poor control. These classes, derived from Hemoglobin A1c (HbA1c) and blood sugar levels, provide healthcare professionals and patients with a more comprehensive understanding of the disease. Machine learning algorithms, including Logistic Regression, Random Forest, and Dense Neural Network (DNN) for binary classification, and Random Forest, Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), CatBoost, and DNN for six-class classification, were employed to compare accuracy rates. Risk factors such as Body Mass Index (BMI), age, blood sugar level, and HbA1c level were categorized, and their interaction effects were evaluated using conditional entropy and visualized with hierarchical clustering, dendrograms, and heatmaps. The findings reveal that multi-class diabetes prediction can achieve comparable accuracy to binary classification when HbA1c and fasting blood sugar levels are accurately measured. Moreover, the investigation into interaction effects yields valuable insights into the heightened risk associated with the combination of major risk factors.

Copyright

© 2023 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  - Shengyuan Zhang
PY  - 2023
DA  - 2023/11/27
TI  - Advancing Diabetes Prediction: A Nuanced Six-Class Classification System and Risk Factor Interactions Investigation
BT  - Proceedings of the 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023)
PB  - Atlantis Press
SP  - 677
EP  - 686
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-300-9_71
DO  - 10.2991/978-94-6463-300-9_71
ID  - Zhang2023
ER  -