Moderate evidence
Published recordHealthGood Space
More
GPT-4-Assisted Versus Human Detection of Intraoperative Adverse Events From Spine Surgery Operative Reports
- Truvace record
- TRV-2026-3080raw data (JSON)
- Version
- v1Published
- First published
- Evidence type
- Controlled or validated comparison
- Sources
- 1 sourcePeer-reviewed
- sha256
- 3aee6ec81ece…check it
Background and objectives: Manual chart review remains the primary method of clinical data collection in spine surgery research but is time intensive and prone to human error. Large language models may enable automated extraction of clinically meaningful events from unstructured operative text. We evaluated the performance of generative pre-trained transformer 4 (GPT-4) in detecting intraoperative adverse events from spine surgery operative notes compared with trained human reviewers. Methods: A retrospective co…
The gain
In a retrospective study of 1,454 laminectomy operative notes, GPT-4 detected 100% of incidental durotomies versus 89.8% for human reviewers and 90.5% of other adverse events versus 57.1%, in about 2 hours versus 35.
What this doesn’t fix
The data came from a single academic institution and one procedure type, and GPT-4's lower positive predictive value (88.0% vs 100.0%) means it flagged some events that were not true adverse events.
Sources
1 on file- Neurosurgery Practicedoi:10.1227/neuprac.0000000000000333
Cite this record
v1Truvace Impact Record TRV-2026-3080, v1: “GPT-4-Assisted Versus Human Detection of Intraoperative Adverse Events From Spine Surgery Operative Reports.” Truvace, 2026-11-20. /record/TRV-2026-3080 (accessed on the day you copy it). sha256 3aee6ec81ece2a3a…
Change history
1 versionEvery change made to this record since it was first published, and why. Nothing has changed since it went up.
Certified into the record
Check this record hasn’t been altered
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-3080 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.
ace