Locally Deployed Large Language Models for AI-Assisted Outpatient Prescription Review: Crossover Study
Zhengyue Liu, Yi Ding, Jingxia Chen, Ziqiang Yan, Xuxi Cheng, Wei Zhou, Peng Fu, Zhuo Wang · 2026
Read Locally Deployed Large Language Models for AI-Assisted Outpatient Prescription Review: Crossover Study by Zhengyue Liu, Yi Ding, Jingxia Chen, Ziqiang Yan, Xuxi Cheng, Wei Zhou, Peng Fu, Zhuo Wang (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/pmc-13620432.txt.
Description
Zhengyue Liu and co-authors test a locally run language model as a helper for pharmacists checking prescriptions, in a 2026 crossover study. Prescription review guards medication safety, but rising volumes squeeze the time per case. Cloud models risk leaking patient data, and fancy retrieval pipelines are hard for small hospital IT teams to run.
The team installed an open-source model on a hospital intranet server, backed by a knowledge base built from drug package inserts, matched by exact lookup. Two pharmacists each reviewed 213 outpatient prescriptions with and without the assistant, in a paired two-period design. The study judges whether this private, lightweight setup is feasible and useful for routine safety checks.
Catalog record
| CREATOR | Zhengyue Liu, Yi Ding, Jingxia Chen, Ziqiang Yan, Xuxi Cheng, Wei Zhou, Peng Fu, Zhuo Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |