MétaCan
Menu
Back to cohort
Record W4407285889 · doi:10.1093/jcag/gwae059.125

A125 DOES AI INFLUENCE ADENOMA DETECTION RATES IN FIT-POSITIVE PATIENTS

2025· article· en· W4407285889 on OpenAlexaffabout
Brendan McGrath, Mark Borgaonkar, Gerona McGrath

Bibliographic record

VenueJournal of the Canadian Association of Gastroenterology · 2025
Typearticle
Languageen
FieldMedicine
TopicCancer Diagnosis and Treatment
Canadian institutionsMemorial University of Newfoundland
Fundersnot available
KeywordsAdenomaMedicinePsychologyInternal medicineArtificial intelligenceComputer science

Abstract

fetched live from OpenAlex

Abstract Background The Fecal Immunochemical Test (FIT) is a screening tool that identifies patients more likely to harbor adenomas or colorectal cancer (CRC). Rates of adenoma detection during colonoscopy can vary significantly among endoscopists. Artificial Intelligence (AI) has been shown to improve adenoma detection during colonoscopy. Aims To assess if AI assistance during colonoscopy can improve adenoma detection in FIT-positive patients. Methods In October and November of 2023, AI was utilized during colonoscopy for FIT-positive patients at Eastern Health, Newfoundland. The 61 FIT-positive patients who had colonoscopy with AI assistance were compared to 61 FIT-positive age, gender, and endoscopist-matched controls who had colonoscopies performed without AI assistance during the preceding 6 months. Demographic data were collected on all patients as well as colonoscopy findings, including CRC detection, polyp detection, and histology. The primary outcome was the proportion of patients with adenomas in the two groups. Secondary outcomes included advanced adenoma detection rate and sessile serrated lesion detection rate. Sample size was one of convenience as only 61 FIT-positive patients had colonoscopies with AI assistance while AI was temporarily available at our institution. Data were entered in SPSS version 17 for analysis. A chi-squared test was used to compare proportions. The study received approval from the local Health Research Ethics Board. Results 122 colonoscopies performed by 13 endoscopists (7 General Surgeons, 6 Gastroenterologists) were included. Sixty-eight patients (55.7%) were female and fifty-four patients (44.3%) were male with an average age of 64 (SD = 6.729). Of the patients who underwent AI-assisted colonoscopies, 73.8% had adenomas. Of the patients who underwent colonoscopy without AI assistance, 63.9% had adenomas. There was a non-significant trend toward higher adenoma detection in the patients who had a colonoscopy with AI (x^2=5.165, p=0.076). AI-assisted colonoscopies found advanced adenomas in 44.3% of patients compared to 29.5% in the no AI group (x^2=3,020, p=0.221). In the AI group, 8.2% of patients had sessile serrated lesions (SSL), compared to 1.6% in the standard procedure group (x^2=2.805, p=0.094). Conclusions This study showed a trend toward higher adenoma, advanced adenoma, and SSL detection with AI assistance in FIT-positive patients. Repeating this study with a larger sample size might clarify the effect of AI assistance during colonoscopy in FIT-positive patients Funding Agencies None

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.633
Threshold uncertainty score0.993

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.004
GPT teacher head0.241
Teacher spread0.238 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
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

Citations0
Published2025
Admission routes2
Has abstractyes

Explore more

Same venueJournal of the Canadian Association of GastroenterologySame topicCancer Diagnosis and TreatmentFrench-language works237,207