MétaCan
Menu
← Back to cohort
Record W4415668036 · doi:10.1093/jcag/gwaf026

Exploring a novel voice-guided artificial intelligence platform for real-time colonoscopy documentation: a pilot study

2025· article· en· W4415668036 on OpenAlexafffundabout
Mahsa Taghiakbari, Timothy Wong, Rohini Gaikar, Azar Azad, Robert Battat, Mickaël Bouin, Benoît Panzini, Roupen Djinbachian, David Armstrong, Daniel von Renteln

Bibliographic record

VenueJournal of the Canadian Association of Gastroenterology · 2025
Typearticle
Languageen
FieldMedicine
TopicColorectal Cancer Screening and Detection
Canadian institutionsVale (Canada)Université de MontréalCentre Hospitalier de l’Université de Montréal
FundersUniversité de Montréal
KeywordsColonoscopyDocumentationCompleteness (order theory)EndoscopyApplications of artificial intelligence

Abstract

fetched live from OpenAlex

Background: Accurate and consistent documentation during colonoscopy is essential for optimal patient care and therapeutic decisions. Traditional manual documentation is time-consuming and subject to variability. Artificial intelligence (AI)-assisted tools offer potential improvements by standardizing report generation in real-time. We developed a novel AI-driven, voice-guided reporting platform that uses natural language processing (NLP) and real-time image capture for endoscopy documentation. Methods: This prospective pilot study was conducted at the Centre Hospitalier de l'Université de Montréal between October 2023 and May 2024. A total of 95 patients undergoing elective endoscopy were recruited, with 57 procedures included in the final analysis. Endoscopists provided real-time verbal dictations during procedures, which the AI-assisted report generation tool transcribed and linked to captured images. The system's performance was evaluated based on documentation completeness, transcription accuracy, and user engagement. Results: The AI-assisted report generation tool successfully documented key procedural parameters when verbal annotations were provided, achieving an 87.5% detection rate for ileocecal valve identification, and 100% detection rate for procedure indication, Boston Bowel Preparation Score, withdrawal time, and polyp characterization. However, the transcription word error was 10.07%, with errors primarily in medical terminology. User engagement varied, with some procedures lacking dictated annotations. Conclusion: Our AI-assisted report generation tool demonstrates potential in standardizing colonoscopy documentation through AI-assisted, real-time NLP for generating reports. While effective, its performance depends on endoscopist engagement. Future improvements in NLP capabilities and structured reporting prompts can enhance completeness and usability, contributing to more efficient and accurate endoscopy documentation.

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)0.005
metaresearch head score (Gemma)0.012
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Non-randomized trial · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.005
Threshold uncertainty score0.028

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0050.012
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.000
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0040.001

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 head0.091
GPT teacher head0.325
Teacher spread0.233 · 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 designNon-randomized trial
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 routes3
Has abstractyes

Explore more

Same venueJournal of the Canadian Association of Gastroenterology→Same topicColorectal Cancer Screening and Detection→French-language works237,207→