Large Language Model Assistant for Emergency Department Discharge Documentation
Problem
Emergency department discharge documentation is time-consuming and often incomplete, burdening physicians and risking patient safety.
Why it matters
Documentation burden reduces physician efficiency and incomplete notes can compromise follow-up care.
What the AI did
A large language model assistant generates ED discharge note drafts that physicians edit; evaluated in a randomized sequential prospective validation with 6 emergency physicians and 300 note sets rated by 3 independent physicians.
Results
not stated in source (abstract truncated before outcome numbers).
Impact
Rigorous evaluation design described at a 2400-bed tertiary hospital; effectiveness not shown in provided evidence.
Record
| Venue | JAMA Network Open |
|---|---|
| Published | 2025 |
| Work type | article |
| Authors | Ji Woo Song, Junseong Park, Ji Hoon Kim, Seng Chan You |
| Citations | 33 (OpenAlex, at import time) |
| References | 21 |
| Model or method | LLM assistant (specific model not stated in source) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1001/jamanetworkopen.2025.38427 |
| Open access | gold |
| Keywords | large language model, discharge documentation, emergency department, clinical workflow |
Importance rating
real but narrower advance
Documentation burden and incomplete ED discharge notes affect physician efficiency and follow-up care; real but narrow workflow advance, validated at one 2400-bed hospital with no outcome numbers in abstract.