NCT06345105

Prospective Evalulation of Artificial Intelligence-assisted Monitoring of Effective Withdrawal Time Versus Standard Withdrawal Time on Adenoma Detected Per Colonoscopy

• Status: Completed
• Phase: —
• Study type: Observational
• Enrollment: 198 (actual)
• Sponsor: The University of Hong Kong · Academic / Other
• Sex: All
• Age: 40 Years
• Healthy volunteers: Accepted

Summary

The goal of this observational study is to assess the correlation between the artificial intelligence (AI) derived effective withdrawal time (EWT) during colonoscopy and endoscopists' adenoma per colonoscopy (APC), polyp per colonoscopy(PPC), adenoma detection rate (ADR), polyp detection rate (PDR) and during colonoscopy for each endoscopists. The association between the AI derived EWT with all colonoscopy outcomes during the prospective colonoscopy series would also be determined. The colonoscopy video of participants will be monitored by the AI. The result will be compared with standard withdrawal time (SWT).

Detailed description

This is a prospective colonoscopy trial using artificial intelligence (AI) real time effective mucosal examination monitor system (EndoScreener QC, Wision A.I. Shanghai \& Chengdu). Low residue diet will be taken by all patients two days before the scheduled colonoscopy. Oral polyethylene glycol lavage solution is used for bowel preparation as in usual hospital practice. All examination will be performed with high-definition endoscopes (EVIS-EXERA 290 video system, Olympus Optical, Tokyo, Japan) under white light by experienced endoscopists. In all colonoscopy examination, colonoscope will be first advanced to the cecum as confirmed by identification of the appendiceal orifice and ileocecal valve or by intubation of the ileum. After cecal intubation is performed, the colonoscopy is slowly withdrawn. All detected polyps will be removed during the withdrawal only. The size (measured with biopsy forceps), location and morphology of each polyp will be recorded by an independent observer. The withdrawal time (minus the polypectomy site) will be measured by a stopwatch and with a minimum of 6 minutes. The bowel preparation quality will be graded according to the Boston Bowel Preparation Scale. The AI derived (AI) real time effective mucosal examination monitor system (EndoScreen QC) will be initiated during scope withdrawal, starting from cecum to anus. The polypectomy or biopsy time will be removed as determination of standard withdrawal time. All endoscopists will be blinded to the results of AI real time monitoring of EWT. All polyp specimens removed will be clearly labelled and send for histological examination. All resected and biopsy specimens are fixed in 10% buffered formalin solution, and examined histologically by hematoxylin and eosin staining. The histopathological diagnosis is determined by experienced pathologists, who are blinded to the assigned endoscopic system, according to the World Health Organization (WHO) criteria. Advanced adenomas are defined as adenoma ≥10 mm in diameter or with villous histology in 25% or high-grade dysplasia (HGD), or carcinoma.The primary outcome of this study is to correlate the adenoma detection rates of the endoscopists with EWT.

Conditions

• Colon Polyp
• Colon Adenoma
• Artificial Intelligence

Interventions

Type	Name	Description
DEVICE	Endoscreener QC	Artificial intelligence monitoring of effective withdrawal time

Timeline

• Start date: 2023-11-01
• Primary completion: 2024-09-30
• Completion: 2025-01-31
• First posted: 2024-04-03
• Last updated: 2025-06-11

Locations

1 site across 1 country: Hong Kong