Improving Postpolypectomy Surveillance Decisions Using an Automated Analysis of Colonoscopy and Histopathology Reports: 2-Center Validation Study
Abstract
BackgroundPostpolypectomy 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. ObjectiveWe 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 auditable surveillance recommendations. MethodsWe extracted paired colonoscopy and histopathology reports from a National Health Service (NHS) trust and designed a 4-stage prompting pipeline using open-weight large language models to separate multispecimen histopathology reports into individual containers (“pots”), align endoscopic findings with specimens, and normalize each pot into a structured schema. The surveillance intervals were then computed by a deterministic rule engine encoding guideline rules. We evaluated extraction performance on 100 procedures (215 pots), assessed surveillance recommendation performance on a same-site cohort (n=100), and performed external validation on a cohort from a second trust (n=100). A separate retrospective audit compared automated recommendations and observed routine scheduling against a clinician-derived reference based on full electronic health record review in 127 patients. ResultsKey extraction fields showed end-to-end accuracy (specimen type=0.995; location=0.981; diagnosis=0.981; excision completeness=0.949), with mean report-level pot comprehensiveness of 0.968 (SD 0.112). Overall surveillance recommendation accuracy was 0.96 (95% CI 0.90-0.98) at Guy’s and St Thomas’ NHS Foundation Trust (GSTT) and 0.93 (95% CI 0.86-0.97) at Sandwell and West Birmingham NHS Trust (SWB) and showed strong class-level performance (F1F1F1F1 ConclusionsThis hybrid approach using open-weight large language models for structured extraction and guideline-encoded rules for decision-making can generate accurate, lightweight, and auditable postpolypectomy surveillance recommendations. Such a tool has the potential to improve safety netting and guideline adherence in NHS colonoscopy workflows.
Related
- Improving Data Quality, Model Transparency and Performance in Lung Histopathology with Explainable AI
- Risk of Advanced Colorectal Neoplasia among Patients Undergoing Repeated Colonoscopy Surveillance: A Two-Center Study.
- Colonoscopy surveillance after colorectal cancer surgery: meta-analysis
- Colonoscopy compliance matters more than time to colonoscopy after a positive FIT result
- Estimating sensitivity from tandem colonoscopy meta-analyses
BibTeX
@article{zecevic2026improving,
title = {{Improving Postpolypectomy Surveillance Decisions Using an Automated Analysis of Colonoscopy and Histopathology Reports: 2-Center Validation Study}},
author = {Agathe Zecevic and Sabina De Martino and Joshua Shan Chen Lee and Victoria To and Vedant Bhardwaj and Rhea Sibal and Nigel Trudgill and Shahd A Mohamed and Angus Roberts and Sebastian Zeki},
journal = {Journal of Medical Internet Research},
year = {2026},
month = oct,
doi = {10.2196/102789},
url = {https://doi.org/10.2196/102789},
note = {CC BY},
}
RIS
TY - JOUR
TI - Improving Postpolypectomy Surveillance Decisions Using an Automated Analysis of Colonoscopy and Histopathology Reports: 2-Center Validation Study
AU - Agathe Zecevic
AU - Sabina De Martino
AU - Joshua Shan Chen Lee
AU - Victoria To
AU - Vedant Bhardwaj
AU - Rhea Sibal
AU - Nigel Trudgill
AU - Shahd A Mohamed
AU - Angus Roberts
AU - Sebastian Zeki
PY - 2026
DA - 2026/10/23
JO - Journal of Medical Internet Research
DO - 10.2196/102789
UR - https://doi.org/10.2196/102789
AB - BackgroundPostpolypectomy 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. ObjectiveWe 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 auditable surveillance recommendations. MethodsWe extracted paired colonoscopy and histopathology reports from a National Health Service (NHS) trust and designed a 4-stage prompting pipeline using open-weight large language models to separate multispecimen histopathology reports into individual containers (“pots”), align endoscopic findings with specimens, and normalize each pot into a structured schema. The surveillance intervals were then computed by a deterministic rule engine encoding guideline rules. We evaluated extraction performance on 100 procedures (215 pots), assessed surveillance recommendation performance on a same-site cohort (n=100), and performed external validation on a cohort from a second trust (n=100). A separate retrospective audit compared automated recommendations and observed routine scheduling against a clinician-derived reference based on full electronic health record review in 127 patients. ResultsKey extraction fields showed end-to-end accuracy (specimen type=0.995; location=0.981; diagnosis=0.981; excision completeness=0.949), with mean report-level pot comprehensiveness of 0.968 (SD 0.112). Overall surveillance recommendation accuracy was 0.96 (95% CI 0.90-0.98) at Guy’s and St Thomas’ NHS Foundation Trust (GSTT) and 0.93 (95% CI 0.86-0.97) at Sandwell and West Birmingham NHS Trust (SWB) and showed strong class-level performance (F1F1F1F1 ConclusionsThis hybrid approach using open-weight large language models for structured extraction and guideline-encoded rules for decision-making can generate accurate, lightweight, and auditable postpolypectomy surveillance recommendations. Such a tool has the potential to improve safety netting and guideline adherence in NHS colonoscopy workflows.
SN - 1438-8871
ER -