HRRT: hierarchical reinforcement learning for renal replacement therapy decision support
Qianyi Xu, Feng Wu, Zi Yi Christopher Thong, Mark Sen Liang Goh, Pengpeng Chen, Jie Yang, Chen Huang, Zhongheng Zhang, Yucai Hong, Kay Choong See, Mengling Feng · 2026
Read HRRT: hierarchical reinforcement learning for renal replacement therapy decision support by Qianyi Xu, Feng Wu, Zi Yi Christopher Thong, Mark Sen Liang Goh, Pengpeng Chen, Jie Yang, Chen Huang, Zhongheng Zhang, Yucai Hong, Kay Choong See, Mengling Feng (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/PMC13645796.txt.
Description
Qianyi Xu and ten colleagues build an artificial intelligence system, published in 2026, to guide kidney replacement therapy for intensive care patients with acute kidney injury. Decisions about when to start this blood-cleaning treatment, how to run it, and when to stop vary widely between clinicians. The team trained a layered reinforcement learning system on 2,467 intensive care stays from a United States hospital. Outside checks used patient stays from the Netherlands and China.
Judged against what clinicians actually did, the system's recommended path came with an estimated death rate several points lower. The authors argue that a single system covering the whole treatment course can cut needless variation and tailor choices to each patient's course. Because the study is based on past records, the next step would be testing the tool in live care. The work shows how learning systems may support some of the hardest calls in intensive care.
Catalog record
| CREATOR | Qianyi Xu, Feng Wu, Zi Yi Christopher Thong, Mark Sen Liang Goh, Pengpeng Chen, Jie Yang, Chen Huang, Zhongheng Zhang, Yucai Hong, Kay Choong See, Mengling Feng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 67925 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |