Using AI to predict polyp pathology during colonoscopy

Artificial Intelligence Predicts the Pathology and Endoscopic Classification of Colorectal Polyps During Colonoscopy

This study is testing whether a new AI tool can help doctors better identify and classify polyps during colonoscopy to improve patient care and reduce unnecessary procedures.

Quick facts

• Study type: Observational
• Enrollment: 400 (estimated)
• Ages: 18 Years and up
• Sex: All
• Sponsor: Peking Union Medical College Hospital (other)
• Locations: 1 site (Beijing)
• Trial ID: NCT06773832 on ClinicalTrials.gov

What this trial studies

This observational study aims to evaluate the effectiveness of a real-time artificial intelligence model in diagnosing colorectal polyp pathology and classifying polyps during colonoscopy. By utilizing various endoscopic classification methods, the study seeks to improve the accuracy of optical diagnosis, potentially reducing unnecessary procedures and the economic burden on patients. The study will involve outpatients and inpatients undergoing routine colonoscopy screening at multiple centers, focusing on enhancing the training and application of endoscopic techniques. The goal is to streamline the diagnostic process and improve patient outcomes.

Who should consider this trial

Good fit: Ideal candidates include adults aged 18 and older who are undergoing routine colonoscopy screening.

Not a fit: Patients with severe gastrointestinal conditions, significant psychiatric illnesses, or those who have undergone colorectal surgery may not benefit from this study.

Why it matters

Potential benefit: If successful, this approach could lead to more accurate diagnoses of colorectal polyps, reducing unnecessary treatments and improving patient care.

How similar studies have performed: While the use of AI in medical diagnostics is a growing field, this specific application in colorectal polyp pathology is relatively novel and has not been extensively tested in prior studies.

Eligibility criteria

Inclusion Criteria:

1. Outpatients or inpatients undergoing routine colonoscopy screening at the endoscopy centers of multicenter hospitals;
2. Aged 18 years or older;
3. Have understanding of the study content and have signed the informed consent form.

Exclusion Criteria:

1. Gastroparesis or gastric outlet obstruction;
2. Known or suspected intestinal obstruction or perforation;
3. Severe chronic renal failure (creatinine clearance less than 30 mL/minute);
4. Severe congestive heart failure (New York Heart Association Class III or IV);
5. Currently pregnant or breastfeeding;
6. Toxic colitis or megacolon;
7. Poorly controlled hypertension (systolic blood pressure greater than 180 mmHg and/or diastolic blood pressure greater than 100 mmHg);
8. Moderate or massive active gastrointestinal bleeding (\>100 mL/day);
9. Significant psychiatric or psychological illness;
10. Allergy to medications used for bowel preparation;
11. Patients who have undergone colorectal surgery.

Where this trial is running

Beijing

• Peking Union Medical College Hospital — Beijing, China (RECRUITING)

Study contacts

• Principal investigator: Dong Wu, MD — Peking Union Medical College Hospital
• Study coordinator: Wenmo Hu, MD

Conditions: Colorectal Polyps, Colonoscopy, Artificial Intelligence, Optical Diagnosis, Sessile Serrated Adenoma, Adenoma