MétaCan
Menu
Back to cohort
Record W4410382902 · doi:10.1136/gutjnl-2025-335091

Large language models for detecting colorectal polyps in endoscopic images

2025· article· en· W4410382902 on OpenAlexaff
Davide Massimi, Yuichi Mori, Giulio Antonelli, Tommy Rizkala, Marco Spadaccini, Chiara Lena, Sravanthi Parasa, Raf Bisschops, Daniel von Renteln, Susanne O'Reilly, Prateek Sharma, Douglas K. Rex, Michael Bretthauer, Alessandro Repici, Elena Demomi, Cesare Hassan

Bibliographic record

VenueGut · 2025
Typearticle
Languageen
FieldMedicine
TopicColorectal Cancer Screening and Detection
Canadian institutionsUniversité de Montréal
FundersNorges ForskningsrådEuropean Commission
KeywordsColorectal PolypMedicineComputer scienceColonoscopyRectal PolypRadiologyArtificial intelligenceNatural language processingColorectal cancerRectumInternal medicineCancer

Abstract

fetched live from OpenAlex

sponsorship: Cesare Hassan and Alessandro Repici are supported by the European Commission (Horizon Europe 101057099). The Associazione Italiana per la Ricerca sul Cancro (AIRC): IG 2022 - ID. 27843 project / (AIRC) IG 2023 - ID. 29220 project. And Bando PNRR- MCNT2- 2023- 12377041. Yuichi Mori is supported by the European Commission (Horizon Europe: 101057099). Luca Carlini is supported by the National Plan for NRRP Complementary Investments (PNC, established with the decree- law 6 May 2021, n. 59, converted by law n. 101 of 2021) in the call for the funding of research initiatives for technologies and innovative trajectories in the health and care sectors (Directorial Decree n. 931 of 06- 06- 2022) - project n. PNC0000003 - AdvaNced Technologies for Human- centrEd Medicine (project acronym: ANTHEM). This work reflects only the authors' views and opinions; neither the Ministry for University and Research nor the European Commission can be considered responsible for them. Michael Bretthauer is supported by the European Commission (Horizon Europe No. 101057099), Norwegian National Clinical Trial Mechanism (grant 36935), and Norwegian Research Council (grant 315410). Raf Bisschops is supported by a grant of research foundation Flanders (G072621N) and FKO of KU Leuven. Chiara Lena is supported by Multilayered Urban Sustainability Action (MUSA) project (ECS00000037), funded by the European Union - NextGenerationEU, under the National Recovery and Resilience Plan (NRRP) (European Commission|101057099, The Associazione Italiana per la Ricerca sul Cancro (AIRC)|27843, The Associazione Italiana per la Ricerca sul Cancro (AIRC)|29220, The Associazione Italiana per la Ricerca sul Cancro (AIRC)|12377041, National Plan for NRRP Complementary Investments|59, National Plan for NRRP Complementary Investments|101, National Plan for NRRP Complementary Investments|931, National Plan for NRRP Complementary Investments|PNC0000003, Norwegian National Clinical Trial Mechanism|36935, Norwegian Research Council|315410, Research foundation Flanders|G072621N, FKO of KU Leuven, Multilayered Urban Sustainability Action (MUSA) project -European Union - NextGenerationEU, under the National Recovery and Resilience Plan (NRRP)|ECS00000037)

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.008
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.021
Threshold uncertainty score0.043

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.008
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0020.003
Bibliometrics0.0030.002
Science and technology studies0.0010.001
Scholarly communication0.0020.002
Open science0.0020.002
Research integrity0.0030.003
Insufficient payload (model declined to judge)0.0060.006

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.013
GPT teacher head0.301
Teacher spread0.288 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations8
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueGutSame topicColorectal Cancer Screening and DetectionFrench-language works237,207