MétaCan
Menu
Back to cohort
Record W4391873606 · doi:10.1093/jcag/gwad061.125

A125 DIAGNOSTIC ACCURACY OF ARTIFICIAL INTELLIGENCE IN THE DIAGNOSIS OF INTESTINAL METAPLASIA AND DYSPLASIA IN PATIENTS WITH BARRETT'S ESOPHAGUS: A DIAGNOSTIC TEST ACCURACY META-ANALYSIS

2024· article· en· W4391873606 on OpenAlexaff
Kayla Dadgar, Laetitia Mais, Sivesh Sangar, Mohammad Yaghoobi

Bibliographic record

VenueJournal of the Canadian Association of Gastroenterology · 2024
Typearticle
Languageen
FieldMedicine
TopicEsophageal Cancer Research and Treatment
Canadian institutionsMcMaster University
Fundersnot available
KeywordsBarrett's esophagusDiagnostic accuracyIntestinal metaplasiaMedicineDysplasiaEsophagusMeta-analysisDiagnostic testRadiologyGastroenterologyInternal medicineAdenocarcinomaCancer

Abstract

fetched live from OpenAlex

Abstract Background Diagnosing dysplasia in patients with Barrett’s Esophagus is crucial in preventing esophageal cancer but challenging in clinical practice. Artificial Intelligence (AI) could potentially be utilized during endoscopy to provide better diagnostic accuracy. Aims The primary aim of this systematic review is to determine the diagnostic accuracy of AI in detecting intestinal metaplasia and dysplasia in adults with Barrett's esophagus using gastroscopy images. Methods A comprehensive electronic search was conducted of cross-sectional studies examining the accuracy of AI in diagnosing intestinal metaplasia or dysplasia using endoscopic images. Study selection, data extraction and quality assessment were completed by two authors independently. When a study used several models, the model with the highest sensitivity was used in meta-analysis. The Quality Assessment of Diagnostic Accuracy (QUADAS-2) tool was used to assess risk of bias and applicability. Meta-analysis was performed using a bivariate model to obtain summary estimates of sensitivity, specificity, and diagnostic odds ratio. Results Of the 1479 articles reviewed, 23 were included. The diagnosis of dysplasia by AI per endoscopic image obtained had a sensitivity of 0.92 (CI 0.85-0.96), specificity of 0.84 (CI 0.78-0.88) and diagnostic odds ratio (DOR) of 59 (CI 22-161). The diagnosis of dysplasia in volumetric laser endomicroscopy images interpreted by AI had an overall sensitivity of 0.83 (CI 0.70-0.91), specificity of 0.77 (0.67-0.85) and a DOR of 16 (CI 2-30). Subgroup analysis did not show a statistically significant difference when comparing studies conducted in Europe to those outside of Europe or studies published before 2020 to those published after 2020. A sensitivity analysis by removing the largest studies did not change the overall accuracy of AI. Conclusions AI algorithms seem to be accurate at detecting the presence of intestinal metaplasia and dysplasia. Further research into using artificial intelligence should be carried out to evaluate its use in combination with endoscopist’s opinion as a clinical decision-making tool to target areas of dysplasia for biopsies. 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 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)0.039
metaresearch head score (Gemma)0.118
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Meta-analysis · Consensus signal: Meta-analysis
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.039
Threshold uncertainty score0.204

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0390.118
Meta-epidemiology (narrow)0.0030.002
Meta-epidemiology (broad)0.0140.067
Bibliometrics0.0080.008
Science and technology studies0.0010.001
Scholarly communication0.0050.003
Open science0.0030.002
Research integrity0.0030.003
Insufficient payload (model declined to judge)0.0030.000

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 head0.025
GPT teacher head0.295
Teacher spread0.270 · 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 designMeta-analysis
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
Published2024
Admission routes1
Has abstractyes

Explore more

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