MétaCan
Menu
Back to cohort
Record W4323351007 · doi:10.1093/jcag/gwac036.114

A114 UNIFIED MAGNIFYING ENDOSCOPIC CLASSIFICATION (UMEC) FOR GASTROINTESTINAL LESIONS: A NORTH AMERICAN EDUCATION STUDY

2023· article· en· W4323351007 on OpenAlexaff
Mary Raina Angeli Fujiyoshi, Y Fujiyoshi, Nikko Gimpaya, Robert Bechara, Thurarshen Jeyalingam, Natalia Causada Calo, Nauzer Forbes, Rishad Khan, Michael Atalla, Akiko Toshimori, Yuto Shimamura, Mayo Tanabe, Jeffrey D. Mosko, Hiroyasu Inoue, Samir C. Grover

Bibliographic record

VenueJournal of the Canadian Association of Gastroenterology · 2023
Typearticle
Languageen
FieldMedicine
TopicEsophageal Cancer Research and Treatment
Canadian institutionsUniversity of OttawaQueen's UniversityUniversity of CalgaryHotel Dieu HospitalUniversity Health NetworkUniversity of TorontoKingston General HospitalSt. Michael's Hospital
Fundersnot available
KeywordsMedicineGastroenterologyEsophagusStomachInternal medicineEndoscopyGold standard (test)

Abstract

fetched live from OpenAlex

Abstract Background Magnification endoscopy and magnification narrow-band imaging are image enhanced endoscopy technologies that may allow for the diagnosis of advanced neoplasia in the GI tract on the basis of imaging characteristics. Recently, the Unified Magnifying Endoscopic Classification (UMEC) has been developed, which unified the criteria for the esophagus, stomach, and colon. UMEC divides optical diagnosis into one of the three categories: non-neoplastic, intramucosal neoplasia, and deep submucosal invasive cancer. Purpose The objective of this study is to educate North American endoscopists on the use of the UMEC schema, and to ascertain performance of the UMEC framework among North American endoscopists. Method Using UMEC, five North American endoscopists (>1000 procedures) without prior training in magnifying endoscopy independently diagnosed previously collected endoscopic image set of the esophagus, stomach, and colon. The endoscopists were trained on the use of UMEC via an eleven-minute training video with exemplars of each element of UMEC from esophagus, stomach, and colon. All endoscopists were blinded to white-light and non-magnifying NBI findings as well as histopathological diagnosis. The diagnostic performance of UMEC was assessed while using the gold standard histopathology as a reference. Result(s) A total of 299 gastrointestinal lesions (77 esophagus, 92 stomach, and 130 colon) were assessed using UMEC. For esophageal squamous cell carcinoma, the sensitivity, specificity, and accuracy for all 5 endoscopists ranged from 65.2% (95% CI: 50.9–77.9) to 87.0% (95% CI: 75.3–94.6), 77.4% (95% CI: 60.9–89.6) to 96.8% (95% CI: 86.8–99.8), and 75.3% to 87.0%, respectively. For gastric adenocarcinoma, the sensitivity, specificity, and accuracy for all 5 endoscopists ranged from 94.9% (95% CI: 85.0–99.1) to 100%, 52.9% (95% CI: 39.4–66.2) to 92.2% (95% CI: 82.7–97.5), and 73.3% to 93.3%, respectively. For colorectal adenocarcinoma, the sensitivity, specificity, and accuracy for all 5 endoscopists ranged from 76.2% (95% CI: 62.0–87.3) to 83.3% (95% CI: 70.3–92.5), 89.7% (95% CI: 82.1–94.9) to 97.7% (95% CI: 93.1–99.6), and 86.8% to 90.7%, respectively. Image Conclusion(s) UMEC is a simple and practical classification that can be used to introduce and educate endoscopists to magnification narrow-band imaging and optical diagnosis. Please acknowledge all funding agencies by checking the applicable boxes below CAG Disclosure of Interest M. R. A. Fujiyoshi Grant / Research support from: 2022 CAG/AbbVie Education Research Grant, Y. Fujiyoshi: None Declared, N. Gimpaya: None Declared, R. Bechara: None Declared, T. Jeyalingam: None Declared, N. Calo: None Declared, N. Forbes: None Declared, R. Khan: None Declared, M. Atalla: None Declared, A. Toshimori: None Declared, Y. Shimamura: None Declared, M. Tanabe: None Declared, J. Mosko: None Declared, H. Inoue: None Declared, S. Grover: 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)0.002
metaresearch head score (Gemma)0.006
Version: metacan-v3-hybrid-931329e0061cValidation 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 score0.014
Threshold uncertainty score0.028

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.006
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0000.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0030.001

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 head0.038
GPT teacher head0.329
Teacher spread0.291 · 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 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
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueJournal of the Canadian Association of GastroenterologySame topicEsophageal Cancer Research and TreatmentFrench-language works237,207