Explainable deep learning framework incorporating medical knowledge for insulin titration in diabetes
We present an explainable deep learning framework that combines post-hoc XAI and expert domain knowledge to provide transparent and expert-aligned explanations for insulin titration in type 2 diabetes management. This framework enhances decision-making accuracy and confidence, especially for junior clinicians, and may facilitate broader clinical adoption of AI-assisted decision-making tools.
Authors
- Liming Wu (ORCID: https://orcid.org/0009-0006-1219-2195)
- Yanying Guo
- Biao Li (ORCID: https://orcid.org/0009-0009-5707-5314)
- Yujuan Fan
- Haowei He
- Jiaping Lu
- Hexu Zhao
- Yang Yuan (ORCID: https://orcid.org/0000-0002-0005-6093)
- Guangyu Wang
- Ping Wang
- Xiaoying Li
- Zhen Ying
- Ying Chen
Institutions
- Beijing University of Posts and Telecommunications (CN)
- Sun Yat-sen University (CN)
- Fudan University (CN)
- Shanghai Xuhui Central Hospital (CN)
- People's Hospital of Xinjiang Uygur Autonomous Region (CN)
- ShangHai JiAi Genetics & IVF Institute (CN)
- Zhongshan Hospital (CN)
- The First Affiliated Hospital, Sun Yat-sen University (CN)
- Center for Life Sciences (CN)
- Tsinghua University (CN)
Publication Details
- Journal
- Communications Medicine
- Published
- 2026-02-26
- DOI
- https://doi.org/10.1038/s43856-026-01449-1
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00