Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1640
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-17T01:09:34.246288Z
status: published
lens: g_space
sector: health
headline: Improving Postpolypectomy Surveillance Decisions Using an Automated Analysis of Colonoscopy and Histopathology Reports: 2-Center Validation Study
dek: Background: Postpolypectomy surveillance intervals derived from colonoscopy findings and histopathology should be guideline-based, yet these are frequently not adhered to, contributing to under- and oversurveillance. This motivates a more structured and automated approach to improve adherence.
Objective: We developed and evaluated an automated, implementable, guideline-aligned decision support tool that extracts colorectal polyp features from free-text colonoscopy and histopathology reports and produces auditabl…
gain_title: A hybrid pipeline of open-weight language models and a deterministic guideline rule engine reached 0.93 to 0.96 recommendation accuracy across two NHS trusts and would mainly reduce potential undersurveillance.
problem_title: (none)
trace_subject: (none)
gain_reading: A hybrid pipeline of open-weight language models and a deterministic guideline rule engine reached 0.93 to 0.96 recommendation accuracy across two NHS trusts and would mainly reduce potential undersurveillance.
gain_evidence: Overall surveillance recommendation accuracy was 0.96 (95% CI 0.90-0.98) | the tool would improve guideline adherence primarily by reducing potential undersurveillance
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers built a tool that reads free-text colonoscopy and histopathology reports from NHS trusts, pulls out structured polyp features using open-weight language models, and then applies encoded guideline rules to recommend follow-up intervals after polyp removal.

Guideline-based surveillance intervals are often not followed, leading to both too little and too much follow-up. A tool that is auditable and accurate could support safer scheduling, but the results come from retrospective samples of 100 cases per site, so real-world clinical impact is not yet shown.
limitation: The evaluation was retrospective and used small cohorts of 100 patients per site, and the authors describe only the potential to improve safety netting and adherence, not a demonstrated clinical effect.
tag: Evidence-backed gain
key_points: Extraction accuracy was 0.995 for specimen type, 0.981 for location and diagnosis, and 0.949 for excision completeness. | Recommendation accuracy was 0.96 at Guy's and St Thomas' and 0.93 at Sandwell and West Birmingham. | Cancer alert F1-score was 1.00 at both sites, while 3-year follow-up F1-scores were lower at 0.86 and 0.80. | A deterministic rule engine, not the language model, computes the surveillance interval, making outputs auditable.
rundown: The pipeline uses four prompting stages to split multispecimen histopathology reports into individual pots, align endoscopic findings with each specimen, and normalize each pot into a structured schema.

Extraction was tested on 100 procedures comprising 215 pots. Recommendation performance was tested on a same-site cohort of 100 patients and externally validated on 100 patients from a second trust.

A separate retrospective audit of 127 patients compared automated recommendations and observed routine scheduling with a clinician-derived reference based on full electronic health record review. The tool would improve adherence mainly by reducing potential undersurveillance.
sources:
- peer_reviewed | Journal of Medical Internet Research | https://doi.org/10.2196/102789 | 2026-10-16
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

86dfe5be2f287ba79e353fcf59987729a08f56f1f96d407f20691cfc2f5b522a

previous

0000000000000000000000000000000000000000000000000000000000000000