Actively Recruiting
Artificial Intelligence-assisted Colonoscopy in the Detection and Characterization of Colorectal Lesions: Randomized Controlled Clinical Trial
Led by Instituto do Cancer do Estado de São Paulo · Updated on 2025-07-16
1000
Participants Needed
1
Research Sites
43 weeks
Total Duration
On this page
AI-Summary
What this Trial Is About
Researchers are evaluating how well artificial intelligence (AI)-assisted colonoscopy works compared to standard colonoscopy in detecting adenomas and accurately characterizing colorectal lesions. This study is important because colorectal cancer is a common and deadly disease worldwide, and improving detection rates may help reduce mortality. The trial focuses on adults undergoing elective colonoscopy in a developing country setting, addressing gaps in current research and differences in results seen in other populations. The study is a randomized controlled clinical trial involving 100 adult patients in Brazil. Participants will be divided into two groups: one receiving AI-assisted colonoscopy and the other receiving standard high-definition colonoscopy without AI. Patients are stratified by age into three groups (18-44, 45-75, and 76+ years). All detected lesions will be removed and analyzed histologically. The AI system called CAD EYE will provide diagnostic data in the AI group. During the study, participants will undergo colonoscopy with sedation, and all findings will be recorded and analyzed. Researchers will measure the number of patients with at least one adenoma detected confirmed by histopathology, and the accuracy of the AI system in classifying lesions as neoplastic or non-neoplastic. Follow-up includes histopathological report availability about seven days after colonoscopy. The total study duration covers 12 months with assessments focused on detection rates and diagnostic accuracy.
CONDITIONS
Brief Title
Artificial Intelligence-assisted Colonoscopy in the Detection and Characterization of Colorectal Lesions
Who Can Participate
Eligibility Criteria
You may qualify if you...
- Patients aged 18 years or older
- Elective indication for colonoscopy
- Signed informed consent form agreeing to participate
You will not qualify if you...
- History of inflammatory bowel disease
- History of colorectal cancer
- Personal history of colorectal surgery
- Contraindication to endoscopic biopsies
- History of intestinal polyposis syndromes
- Urgent or emergency colonoscopy cases
- Severe, decompensated comorbidities or ASA score 3 or higher
- Incomplete colonoscopy that does not reach the cecum
- Inadequate bowel preparation with Boston Bowel Preparation Scale score lower than 6
- Refusal to participate or not signing the informed consent form
AI-Screening
AI-Powered Screening
Complete this quick 3-step screening to check your eligibility
Your Study Journey
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
1 visit (in-person)
Duration - 1 day
Participants undergo colonoscopy with or without artificial intelligence assistance to detect and characterize colorectal lesions. All detected lesions will be resected and analyzed histologically.
1 procedure visit (in-person)
Duration - 7 days after colonoscopy
Participants receive results from histopathological analysis to confirm adenoma detection and characterize lesions following the colonoscopy.
1 follow-up visit (in-person or remote)
Trial Site Locations
Total: 1 location
1
Hospital das Clínicas da Faculdade de Medicina da USP
São Paulo, São Paulo, Brazil, 05403-010
Actively Recruiting
Research Team
M
Márcio Roberto Facanali Júnior
A
Adriana Vaz Safatle Ribeiro, PhD
How is the study designed?
Study Type
INTERVENTIONAL
Masking
SINGLE
Allocation
RANDOMIZED
Model
PARALLEL
Primary Purpose
DIAGNOSTIC
Number of Arms
2
Similar Trials
Frequently Asked Questions
Have more questions? Get in touch with our team for quick support
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here