68/100

Moderate evidence

Trace: a gain and a problemPublished recordHealthThe Trace

Guardrail-Based Radiology Protocolling with Large Language Models: Balancing Automation and Oversight

Truvace record
TRV-2026-2896raw data (JSON)
Version
v1Published
First published
Evidence type
Controlled or validated comparison
Sources
1 sourcePeer-reviewed
sha256
c07df58a8f63…check it

Safe clinical deployment of large language models (LLMs) for radiology protocolling requires knowing when not to automate. We evaluated a "guardrail-first" workflow that defers incomplete or safety-critical CT and MRI requests to radiologists before assignment. In this single-center retrospective study, 537 body imaging requests were temporally split into prompt development (n = 109) and validation (n = 428) cohorts. An expert radiologist classified requests as protocol-eligible or requiring review. Six LLM pipe…

57Gain side

How the two sides scoreClose call

58Problem side

The gain

In a single-center retrospective study of 428 CT and MRI requests, Gemini 3.1 Pro assigned an exact or equivalent protocol 12.7 percentage points more often than human protocolers (83.6%) and flagged all 38 safety-critical or major-missing-information requests for radiologist review.

The problem

In the same 428-request radiology protocolling study, models sent protocol-eligible requests to radiologists unnecessarily 1.3% to 34.0% of the time, and GPT-5.2 reached only 65.0% clinically appropriate assignment end to end.

A fixed formula sets both scores from the evidence and its sources. Reader votes don’t move them.

What the scores mean

G is the gain side, out of 100. It goes up when the gain is specific, when it measurably helped people and when the sources behind it are strong.

P is the problem side, out of 100. It goes up when the problem is specific, when it measurably hurt people and when the sources behind it are strong.

What this doesn’t fix

The work was a single-center retrospective study, and the authors say the findings support further prospective evaluation before clinical use.

Sources

1 on file
  1. Journal of Imaging Informatics in Medicinedoi:10.1007/s10278-026-02496-9
    Peer-reviewed2026-11-12

Cite this record

v1

Truvace Impact Record TRV-2026-2896, v1: “Guardrail-Based Radiology Protocolling with Large Language Models: Balancing Automation and Oversight.” Truvace, 2026-11-13. /record/TRV-2026-2896 (accessed on the day you copy it). sha256 c07df58a8f634d6f…

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. Publishedv1c07df58a8f63…

    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-2026-2896 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.