.png){kind=icon}
.png){kind=icon}
Return
Exploring a novel voice-guided artificial intelligence platform for real-time colonoscopy documentation: a pilot study
.png){kind=icon}
OA
AI
DOI：10.1093/jcag/gwaf026.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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'Universit & eacute; de Montr & eacute;al 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. Colonoscopy is a test that helps doctors find and prevent cancer in the large intestine. Doctors need to keep good records of what they see during this test to take care of their patients. But writing these reports by hand takes time, and some important information might be missed. AIDREA is a smart machine that helps doctors by turning their spoken words into a written report. It listens to what the doctor says and writes it down, along with pictures of what they find in the large intestine. In this study, we tested AIDREA in a hospital in Montreal. When doctors spoke about what they saw, AIDREA recorded it correctly. It saved details like whether the intestine was clean, if anything looked unusual, and how long the test lasted. But AIDREA had trouble understanding some words that doctors always use. In the future, we will make it better at understanding these words. We can say that AIDREA helps doctors write reports faster and more accurately. This means doctors can spend less time on paperwork and more time helping their patients.
Keywords:
artificial intelligence
documentation
colonoscopy
endoscopy
natural language processing
Journal
J
IF:
2.7
Papers:
43
Citations:
691