Graph autoencoder based causal discovery method for type 2 diabetes mellitus risk factors
PeerJ Computer Science · 31.07.2026 · 12 · e4030
DOI: 10.7717/peerj-cs.4030 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 31.07.2026. Verfasst von Bo Chen und 6 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Guangdong Province General Program Project, Science and Technology Planning Project of Shiyan City.
Themen: Diabetes mellitus
Abstract (Originalsprache)
The risk factors for type 2 diabetes mellitus (T2DM) encompass biochemical indicators (such as glycated hemoglobin, high-density lipoprotein, etc .) and physiological indicators (such as age, weight, etc .). The interactions among these indicators influence the risk and progression of T2DM. Uncovering their causal relationships is a crucial means for T2DM prevention and intervention. Addressing the issues of severe coupling among T2DM risk factors, small sample sizes, and the erroneous causal relationships arising from existing nonlinear causal discovery methods struggling to satisfy the acyclicity assumption, this article proposes a Graph Autoencoder (GAE)-based causal discovery method tailored for T2DM risk factors. Firstly, by integrating a data generation model with the Graph Autoencoder (GAE), a candidate space for the nonlinear causal structure of risk factors is constructed. Secondly, the problem of optimizing the causal structure is transformed into a task of minimizing the GAE reconstruction error. Utilizing the augmented Lagrangian method and innovatively introducing a bidirectional edge penalty term, a new scoring function is established to avoid generating cyclic causal graphs. Thirdly, the function parameters are iteratively optimized via gradient descent until converging to the optimal causal structure within the candidate space. Finally, validation experiments were designed using two types of datasets. The results show that on a dataset with a known true Directed Acyclic Graph (DAG), the proposed method achieves an accuracy of up to 80%, with optimal comprehensive metrics compared to other methods. On three diabetes datasets, the proposed method achieves an average plausibility rate of 82.8%, significantly outperforming comparative methods and enabling the discovery of more potential causal relationships. The method proposed in this article can provide a reliable information-assisted tool for research into the pathological mechanisms of T2DM.
Förderung
- Natural Science Foundation of Guangdong Province General Program Project
- Science and Technology Planning Project of Shiyan City
Zitieren
APA
Chen, B., Wang, Z., Chen, Y., Xie, W., Li, S., Gao, X., & Zhou, B. (2026). Graph autoencoder based causal discovery method for type 2 diabetes mellitus risk factors. PeerJ Computer Science, 12, e4030. https://doi.org/10.7717/peerj-cs.4030
Vancouver
Chen B, Wang Z, Chen Y, Xie W, Li S, Gao X, et al. Graph autoencoder based causal discovery method for type 2 diabetes mellitus risk factors. PeerJ Computer Science. 2026;12:e4030. doi:10.7717/peerj-cs.4030
BibTeX
@article{Chen2026,
author = {Chen, Bo and Wang, Zhenghao and Chen, Yufeng and Xie, Wenxue and Li, Sen and Gao, Xiue and Zhou, Boyang},
title = {Graph autoencoder based causal discovery method for type 2 diabetes mellitus risk factors},
journal = {PeerJ Computer Science},
year = {2026},
volume = {12},
pages = {e4030},
doi = {10.7717/peerj-cs.4030}
}
EUVIMED