TRV-2026-3080Version 1 · Published

Saved · see the current record

Why this version exists

Certified into the record

The exact text we saved

This is the version exactly as it was saved, character for character. The SHA-256 hash below is a 64-character code worked out from that text. Run the same text through SHA-256 and you get the same code; change a single letter and the code comes out completely different. Each version also stores the previous version’s hash, which chains them together so no version can be swapped out quietly.

TRUVACE RECORD VERSION
record: TRV-2026-3080
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-11-20T18:02:11.933780Z
status: published
lens: g_space
sector: health
headline: GPT-4-Assisted Versus Human Detection of Intraoperative Adverse Events From Spine Surgery Operative Reports
dek: 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…
gain_title: 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.
problem_title: (none)
trace_subject: (none)
gain_reading: 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.
gain_evidence: GPT-4 achieved 100.0% sensitivity compared with 89.8% for human reviewers | GPT-4 demonstrated higher sensitivity than humans (90.5% vs 57.1%) | approximately 35 hours to review all notes, compared with approximately 2 hours for GPT-4
problem_reading: (none)
problem_evidence: (none)
quick_read: A retrospective study of 1,454 laminectomy cases at one academic institution, performed between 2016 and 2022, compared GPT-4 with four trained human reviewers at spotting intraoperative adverse events in operative notes. For incidental durotomy, which occurred in 88 cases (6.1%), GPT-4 found every one (100.0% sensitivity) while humans found 89.8%.

GPT-4 also did better on other adverse events (21 cases), with 90.5% sensitivity against 57.1% for humans. Human sensitivity fell on longer notes, whereas GPT-4 stayed stable across note-length quartiles.

Review took humans about 35 hours for all notes and GPT-4 about 2 hours, a cut of more than 90%. The authors describe the approach as a human-in-the-loop adjunct to chart review rather than a replacement.
limitation: 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.
tag: Evidence-backed gain
key_points: The study analysed 1,454 laminectomy cases from a single academic institution between 2016 and 2022. | Four trained human reviewers and GPT-4 independently read deidentified operative notes using standardized prompts. | A senior reviewer adjudicated discordant classifications to set the ground truth. | GPT-4 had 100.0% sensitivity for incidental durotomy versus 89.8% for humans, but positive predictive value of 88.0% versus 100.0%. | Specificity for durotomy was 99.1% for GPT-4 and 100.0% for humans. | For nondurotomy adverse events (21 cases), GPT-4 sensitivity was 90.5% versus 57.1% for humans, with equal 100.0% specificity. | Human sensitivity declined on longer notes while GPT-4 held steady across note-length quartiles. | Review time fell from about 35 hours to about 2 hours.
rundown: Manual chart review is the main way spine surgery researchers collect clinical data, but it is slow and prone to human error. The team tested whether GPT-4 could extract adverse events from unstructured operative notes.

Both humans and GPT-4 used standardized prompts on deidentified notes. Discordant calls went to a senior reviewer, and the team calculated sensitivity, specificity, predictive values and F1 score, and stratified results by note length.

GPT-4 flagged all 88 incidental durotomies but produced more false positives, with positive predictive value of 88.0% against 100.0% for humans. On the 21 other adverse events it found 90.5% against 57.1%.

The authors conclude that model-assisted review could make neurosurgical outcomes research more complete and efficient when paired with human oversight.
sources:
- peer_reviewed | Neurosurgery Practice | https://doi.org/10.1227/neuprac.0000000000000333 | 2026-11-20
prev: 0000000000000000000000000000000000000000000000000000000000000000
SHA-256 hash
3aee6ec81ece2a3a8e969d7b7747291e70a3fc818548d3176265ce66a935db83
Previous version’s hash
0000000000000000000000000000000000000000000000000000000000000000
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.