Does AI-assisted colonoscopy lower the risk of future advanced colon lesions?
Official title: The Long-term Effect of Artificial Intelligence-assisted Colonoscopy on Risk of Metachronous Advanced Colonic Lesion
Run by The University of Hong Kong · NCT07467928 · Data updated 2026-11-12
This study will test whether using artificial intelligence during colonoscopy lowers the chance of developing advanced colonic lesions later in people who previously had polyps.
Quick facts
| Study type | Interventional |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 404 (estimated) |
| Sponsor | The University of Hong Kong Academic / other |
| Locations | 1 site (Hong Kong) |
| Status | Recruiting |
| Started | July 1, 2025 |
| Main results expected | December 31, 2027 |
| Study ends | February 28, 2028 |
| Registry record updated | March 12, 2026 |
| Trial ID | NCT07467928 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Ideal candidates are people who completed the original randomized trial comparing AI-assisted versus conventional colonoscopy, are due for surveillance colonoscopy, and do not have IBD, prior colorectal cancer, or bowel resection.
✕Probably not a fit
Patients with inflammatory bowel disease, a history of colorectal cancer or bowel resection, those with new severe comorbidities making colonoscopy unsafe, or people who were not part of the original trial are unlikely to benefit from participation.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This is a prospective follow-up of patients who completed a randomized trial comparing AI-assisted and conventional colonoscopy, bringing them back for scheduled surveillance colonoscopy to detect metachronous advanced colonic lesions. Investigators will compare the prevalence of advanced lesions on surveillance exams between participants whose prior colonoscopy used AI and those whose prior exam was conventional. Patients with inflammatory bowel disease, prior colorectal cancer, bowel resection, or new severe comorbidities that make colonoscopy unsafe are excluded. The trial is conducted by The University of Hong Kong at Queen Mary Hospital using standard surveillance colonoscopy and polypectomy procedures to capture outcomes.
Why it matters
Potential benefit: If successful, AI-assisted colonoscopy could reduce the number of advanced colonic lesions found at later surveillance and potentially lower future colorectal cancer risk.
How similar studies have gone: Multiple randomized trials have shown that AI-assisted colonoscopy increases adenoma detection rates, but long-term evidence that it reduces metachronous advanced lesions remains limited.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Eligible participants are those who were previously enrolled and completed our randomized controlled trial comparing AI-assisted and conventional colonoscopy Exclusion Criteria: * In addition to the baseline exclusion criteria of the index trial, patients who were found to have inflammatory bowel disease, colorectal cancer and underwent bowel resection would be excluded. Similar to index trial, patients who have developed severe comorbid illnesses that make surveillance colonoscopy and polypectomy unsafe, or become unable to provide informed consent for trial participation would also be excluded Index trial: Lui TK, Lam CP, To EW, Ko MK, Tsui VWM, Liu KS, et al. Endocuff With or Without Artificial Intelligence-Assisted Colonoscopy in Detection of Colorectal Adenoma: A Randomized Colonoscopy Trial. Am J Gastroenterol. 2024;119(7):1318-25
Where it's running
-
Queen Mary Hospital
Hong Kong, Hong Kong Recruiting
Study contacts
- Study coordinator: Thomas KL Clinical Assoicate Professor, MD
- Email: tkllui@hku.kh
- Phone: 852 + 97360997
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
AI-assisted measurement of gummy smiles from photos
A computer program using artificial intelligence will try to identify and measure gummy smiles from patient photos to see if its measurements match those of expert dentists.
-
Benchmarking AI language models against tumor boards for oncology treatment decisions
This project tests whether frontier AI language models can match the treatment recommendations of multidisciplinary tumor boards for common cancers using standardized synthetic cases.
-
AI-assisted gender prediction from the jawbone using CBCT measurements
A retrospective study tests whether AI can predict a person’s gender from measurements of the mandible taken from existing CBCT scans.
-
A web-based tool to help predict submucosal invasive cancer in large non-pedunculated colorectal polyps
A web-based decision aid is being tested to see if it can help endoscopists predict cancer invasion in large non-pedunculated colorectal polyps during live colonoscopies.
-
Smartphone-based AI eye disease screening for anterior segment conditions
A smartphone-powered AI system tests whether it can identify 16 eye conditions from images captured on a phone, without needing internet access, in adults.
-
Detecting freezing of gait at home using AI and wearable sensors
This project tests whether an AI algorithm using wearable sensors can accurately detect freezing of gait in people with Parkinson's disease while they go about daily life at home.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.