MétaCan
Menu
Back to cohort
Record W4323352962 · doi:10.1093/jcag/gwac036.116

A116 OPTIMIZING CROHN’S DISEASE ENDOSCOPIC SCORING OPERATING CHARACTERISTICS TO ASSIST WITH THE ADVENT OF ARTIFICIAL INTELLIGENCE

2023· article· en· W4323352962 on OpenAlexaff
C Galts, N Narula, Emily C L Wong, Walter Reinisch

Bibliographic record

VenueJournal of the Canadian Association of Gastroenterology · 2023
Typearticle
Languageen
FieldMedicine
TopicGastric Cancer Management and Outcomes
Canadian institutionsMcMaster University
Fundersnot available
KeywordsMedicineCrohn's diseaseInternal medicineColonoscopyInfliximabGastroenterologyClinical trialDiseaseInflammatory bowel diseaseSurgeryColorectal cancerCancer

Abstract

fetched live from OpenAlex

Abstract Background To date, no studies have used Artificial Intelligence (AI) to produce standard endoscopic scores for Crohn’s Disease (CD). These scores are essential to clinical practice and have a major cost in clinical trials. Purpose We aimed to re-examine the components of the Simple Endoscopic Score for Crohn’s Disease (SES-CD) and Modified Multiplier (MM-SES-CD) to see if scoring of individual colonic segments could be combined while maintaining predictive value accuracy, thus simplifying scoring for AI. Method Data from 279 participants in the UNITI and EXTEND trials as well as an infliximab biosimilar trial (NCT02096861) were used in this retrospective study. The primary outcome was endoscopic remission (ER-1) of the colon, defined as absence of ulcers. Secondary outcomes included alternative definitions of colonic endoscopic remission including SES-CD score of 0 (ER-2), SES-CD <3 (ER-3), and SES-CD reduction by 50% or greater from baseline (colonic endoscopic response). Result(s) The mean baseline SES-CD score was 13.7 (SD 7.7) and the mean MM-SES-CD score was 22.8 (SD 12.4). Among all possible colonic segment combinations, the combination of Right + Rectum + worst of Left or Transverse performed best for prediction of one-year ER-1, with fair accuracy (AUC 0.71, 95% CI 0.65-0.78, p < 0.0001). Accuracy of prediction of one-year ER-2 was poor (AUC 0.68, 95% CI 0.62-0.75, p < 0.0001), ER-3 was fair (AUC 0.71, 95% CI 0.65-0.77, p < 0.0001), and prediction of endoscopic response was poor (AUC 0.64, 95% CI 0.56-0.72, p > 0.01). These results were very similar to conventional scoring (without combining any “worst of” segments) with all of the colonic MM-SES-CD scores, with AUCs of 0.70, 0.69, 0.71, and 0.61 for the respective outcomes. Assessing only for the presence of ulcers was as accurate as the full assessment and exclusion of scoring stenosis had minimal impact on scores. Image Conclusion(s) By combining assessment of colonic segments accuracy was maintained compared with currently used endoscopic scoring. Assessing for features other than ulceration had no significant impact on overall scores. By combining colonic segments and limiting assessment to ulceration, it may be simpler to develop AI algorithms reliably scoring endoscopic severity of CD for clinical practice and trials. Please acknowledge all funding agencies by checking the applicable boxes below None Disclosure of Interest None Declared

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)0.016
metaresearch head score (Gemma)0.034
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: Empirical
Teacher disagreement score0.016
Threshold uncertainty score0.087

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0160.034
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.002
Science and technology studies0.0000.000
Scholarly communication0.0020.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.001

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 head0.020
GPT teacher head0.261
Teacher spread0.242 · 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

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueJournal of the Canadian Association of GastroenterologySame topicGastric Cancer Management and OutcomesFrench-language works237,207