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-2026-2896 version: 1 kind: certified reason: Certified into the record timestamp: 2026-11-13T18:02:19.991677Z status: published lens: trace sector: health headline: Guardrail-Based Radiology Protocolling with Large Language Models: Balancing Automation and Oversight dek: 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… gain_title: 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. problem_title: 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. trace_subject: LLM-based protocolling of CT and MRI requests with radiologist-review guardrails gain_reading: 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. gain_evidence: Gemini 3.1 Pro achieved 100% sensitivity (38/38; 95% CI, 90.7-100) | exceeded by Gemini 3.1 Pro (+12.7 percentage points; 95% CI, 8.6-16.7) problem_reading: 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. problem_evidence: unnecessary escalation ranged from 1.3% (5/371) to 34.0% (126/371) | ranged from 65.0% (60.5-69.4) for GPT-5.2 quick_read: Researchers tested a workflow in which large language models first decide whether a CT or MRI request is safe to automate, and send incomplete or safety-critical ones to a radiologist. Using 537 body imaging requests from one center, they validated six AI pipelines on 428 requests against human protocolers. Gemini 3.1 Pro caught all 38 requests with safety-critical issues or major missing information and reached 96.3% clinically appropriate assignment. Humans achieved 83.6% exact or equivalent assignment, which four of the six pipelines exceeded by 8.6 to 12.7 percentage points. Performance varied widely. Unnecessary escalation of routine requests ranged from 1.3% to 34.0%, and GPT-5.2 managed 65.0% end-to-end appropriate assignment. The authors say the results support prospective evaluation rather than immediate deployment. limitation: The work was a single-center retrospective study, and the authors say the findings support further prospective evaluation before clinical use. tag: Dual reading key_points: The 537 requests were split by time into 109 for prompt development and 428 for validation. | An expert radiologist judged 57 of 428 requests (13.3%) as needing review: 15 safety-critical, 23 major missing information, 19 minor clarification. | Six pipelines were tested: Gemini 3.1 Pro, Claude Sonnet 4.6, GPT-5.2, GPT-5.2 high, DeepSeek V3.2 and DeepSeek V3.2 reasoner. | Sensitivity for the 38 highest-risk requests was 100% for Gemini 3.1 Pro and 94.7% to 97.4% for the others. | Among 371 protocol-eligible requests, unnecessary escalation was lowest for reasoning-enabled models. | Clinically appropriate assignment ranged from 65.0% to 96.3%; the top three pipelines did not differ significantly. rundown: The study was a single-center retrospective analysis of body imaging requests. Requests were split by time, with 109 used to develop prompts and 428 held for validation. An expert radiologist labelled each as protocol-eligible or requiring review. Each model ran in two stages: review triage, then protocol assignment. The primary outcome was clinically appropriate assignment, meaning an exact or equivalent protocol or a correct escalation to review, with bootstrapped 95% confidence intervals. Against a human benchmark of 83.6% exact or equivalent assignment, Gemini 3.1 Pro, Claude Sonnet 4.6, GPT-5.2 high and DeepSeek V3.2 reasoner scored higher by 12.7, 12.4, 11.6 and 8.6 percentage points. Sensitivity for the highest-risk requests was 94.7% to 100% across pipelines. sources: - peer_reviewed | Journal of Imaging Informatics in Medicine | https://doi.org/10.1007/s10278-026-02496-9 | 2026-11-12 prev: 0000000000000000000000000000000000000000000000000000000000000000
- SHA-256 hash
- c07df58a8f634d6f6f6d474ea3cc30d9ed3a0529f640fd3a38ca7bf1cc687663
- Previous version’s hash
- 0000000000000000000000000000000000000000000000000000000000000000
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.
ace