Exploring a novel voice-guided artificial intelligence platform for real-time colonoscopy documentation: a pilot study
Bibliographic record
Abstract
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".