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

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.

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.

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.

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.