Explainable machine learning model for in-hospital hypoglycemia risk in patients with latent autoimmune diabetes in adults
Qiang Zhang, Xinyi Liu, Yiting Ni, Haojie Zhou, Guniqing Zhu, Ying Wang, Ran Li, Yuan Zhao, Xiangfu Gu, Xiaoyu Cai, Xinmei Nie, Qian Tang, Ruonan Lin, Jianjun Zou, Xiaoli Zhu · 2026
Read Explainable machine learning model for in-hospital hypoglycemia risk in patients with latent autoimmune diabetes in adults by Qiang Zhang, Xinyi Liu, Yiting Ni, Haojie Zhou, Guniqing Zhu, Ying Wang, Ran Li, Yuan Zhao, Xiangfu Gu, Xiaoyu Cai, Xinmei Nie, Qian Tang, Ruonan Lin, Jianjun Zou, Xiaoli Zhu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13454309.txt.
Description
Qiang Zhang leads a fifteen-author team reporting a 2026 effort to predict low blood sugar during hospital stays for adults with a slow form of autoimmune diabetes. Such patients face sharp sugar swings, yet few risk tools target them. The team built three machine learning models from routine records at five hospitals in China, using one hospital as an outside check.
The study covered 752 patients treated between 2019 and 2025. Low sugar struck about 45 percent of patients in the main group and about 54 percent in the check group. Six factors carried most of the signal, led by the size of sugar swings and past low-sugar episodes. No model beat the others clearly in the outside check, and the authors add charts that show which factors drive each prediction.
Catalog record
| CREATOR | Qiang Zhang, Xinyi Liu, Yiting Ni, Haojie Zhou, Guniqing Zhu, Ying Wang, Ran Li, Yuan Zhao, Xiangfu Gu, Xiaoyu Cai, Xinmei Nie, Qian Tang, Ruonan Lin, Jianjun Zou, Xiaoli Zhu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 58 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |