Artificial Intelligence in Colonoscopy

NCT06621225 | Completed FDA Device

• 1 other identifier: Pro00069956
• Study Type: interventional
• Target: 264
• Locations: 1 country
• Sites: 1

Brief Summary

N = 264 patients (50% female) aged 75 years and above undergoing colonoscopy were enrolled. Patients were randomly assigned into one of the three intervention groups: the primary intervention arm (CADe in combination with the MED), the second group with MED alone, and the control group with WLE. All detected lesions were removed and sent to histopathology for diagnosis. The primary outcome was the adenoma detection rate. Secondary outcomes were adenoma detection in the left colon in our cohort of patients.

Conditions

Colorectal Carcinoma

Keywords

Colonoscopy; Mucosal Exposure Device; Artificial Intelligence

Outcome Measures

Primary Outcomes (1)

• Primary Outcome Measure

  The primary outcome of interest was adenoma detection rate (ADR), defined as the percentage of patients in whom at least one histologically proven adenoma or carcinoma was identified during colonoscopy.

  181 days

Secondary Outcomes (1)

• Secondary Outcome Measure

  181 days

Study Arms (3)

Primary Intervention Arm

EXPERIMENTAL

In this arm, colonoscopy was performed using Computer Aided detection in combination with a Mucosal Exposure Device, which is FDA approved.

Device: Artificial Intelligence; Device: Mucosal Exposure Device

Secondary Intervention Arm

EXPERIMENTAL

In this arm, participants underwent colonoscopy solely with an FDA approved Mucosal Exposure Device

Device: Mucosal Exposure Device

Control group

NO INTERVENTION

In this arm, the participants underwent standard white light endoscopy without any intervention.

Interventions

Artificial Intelligence DEVICE

Medtronic GI Genius is an advanced AI-powered platform designed to assist gastroenterologists during colonoscopies. Utilizing deep learning algorithms, it analyzes real-time endoscopic images to detect and highlight polyps and other abnormalities, enhancing the detection rate and accuracy. The system provides visual cues to guide physicians in identifying potentially problematic areas that might be missed by the human eye alone. This technology aims to improve diagnostic precision, reduce missed detections, and ultimately enhance patient outcomes by facilitating earlier and more accurate interventions. GI Genius integrates seamlessly with existing endoscopy equipment, offering a valuable tool in the fight against colorectal cancer.

Primary Intervention Arm

Mucosal Exposure Device DEVICE

The Olympus Endocuff is an innovative device designed to enhance the effectiveness of colonoscopy procedures. It is a soft, flexible cuff that attaches to the end of the colonoscope and features multiple protruding \"fingers\" that help to improve mucosal exposure. By providing better visibility and maneuverability, the Endocuff helps gastroenterologists navigate and inspect the colon more thoroughly. It aids in the detection of polyps and other abnormalities by flattening folds and improving the overall view of the colon lining. This enhanced visualization contributes to more accurate diagnoses and can potentially reduce the miss rate of significant lesions, ultimately leading to better patient outcomes.

Primary Intervention Arm; Secondary Intervention Arm

Eligibility Criteria

• Age: 75 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Older Adult (65+)

You may qualify if:

• Patients aged 75 years and older.
• Patients who were able to provide informed consent or had a legally authorized representative who can consent on their behalf.
• Patients who were deemed fit for colonoscopy based on a pre-procedure evaluation.

You may not qualify if:

• Patients with acute gastrointestinal conditions such as active colitis, acute diverticulitis, or bowel obstruction.
• Patients with a history of major colorectal surgery that might alter normal colon anatomy (e.g., colectomy).
• Patients with severe comorbid conditions that would contraindicate colonoscopy, such as severe cardiopulmonary disease or advanced liver disease.
• Patients with uncorrected coagulopathies or those on anticoagulation therapy that cannot be safely managed around the time of the procedure.
• Patients who are unable to adequately prepare the bowel for colonoscopy.
• Patients who refuse to participate in the study or have a legally authorized representative who refuses consent.

Sponsors & Collaborators

• Pankaj Patel: lead

Study Sites (1)

The Surgery and Endoscopy Center of Sebring

Sebring, Florida, 33870, United States

Location

Related Publications (2)

• Pohl H, Robertson DJ. Colorectal cancers detected after colonoscopy frequently result from missed lesions. Clin Gastroenterol Hepatol. 2010 Oct;8(10):858-64. doi: 10.1016/j.cgh.2010.06.028. Epub 2010 Jul 22.

  PMID: 20655393 BACKGROUND

• Dekker E, Tanis PJ, Vleugels JLA, Kasi PM, Wallace MB. Colorectal cancer. Lancet. 2019 Oct 19;394(10207):1467-1480. doi: 10.1016/S0140-6736(19)32319-0.

  PMID: 31631858 BACKGROUND

MeSH Terms

Conditions

Colorectal Neoplasms

Condition Hierarchy (Ancestors)

Intestinal Neoplasms; Gastrointestinal Neoplasms; Digestive System Neoplasms; Neoplasms by Site; Neoplasms; Digestive System Diseases; Gastrointestinal Diseases; Colonic Diseases; Intestinal Diseases; Rectal Diseases

Study Officials

• Pankaj J Patel, MD

  The Surgery and Endoscopy Center of Sebring

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: TRIPLE
• Who Masked: PARTICIPANT, CARE PROVIDER, INVESTIGATOR
• Purpose: SCREENING
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Gastroenterologist and Medical Director of The Surgery and Endoscopy Center

Model Details: Patients were randomly allocated into one of three study groups: the primary intervention arm, where colonoscopy was performed using the CADe in combination with the MED; the second group underwent colonoscopy solely with the MED, while the control group underwent colonoscopy solely with the WLE. Randomization was executed by a scheduler responsible for patient appointments at the practice, ensuring impartial allocation, with the investigators maintaining no involvement in subject assignment to study arms. We used a Convolutional Neural Network-based CADe system, GI Genius, acquired for licensed use from Medtronic Inc., Minneapolis, MN. The MED employed was the EndoCuff Vision (ECV) developed by Olympus America, Center Valley, PA, which constitutes part of the standard equipment available. All detected lesions were identified and excised throughout the colonoscopy procedures, and specimens were promptly sent for histopathological analysis.

Study Record Dates

• First Submitted: September 7, 2024
• First Posted: October 1, 2024
• Study Start: November 22, 2022
• Primary Completion: May 31, 2023
• Study Completion: June 30, 2023
• Last Updated: October 1, 2024

Record last verified: 2024-09

Locations

US (1)