70/100

Moderate evidence

GainPublished recordHealthGood Space

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
  1. Neurosurgery Practicedoi:10.1227/neuprac.0000000000000333
    Peer-reviewed2026-11-20

Cite this record

v1

Truvace 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 version

Every change made to this record since it was first published, and why. Nothing has changed since it went up.

  1. Publishedv13aee6ec81ece…

    Certified into the record

Check this record hasn’t been altered

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.