Water Exchange Colonoscopy With Artificial Intelligence-assisted Detection

Summary

The goal of this clinical trial is to compare the detected adenoma per colonoscopy (APC) in participants undergoing screening, surveillance, and positive fecal immunochemical test (FIT) or guaiac fecal occult blood test (gFOBT). There will be two arms in this study: WE water control and water plus artificial intelligence (AI). The main question it aims to answer is whether the addition of AI into water exchange (WE) colonoscopy increases APC than WE alone. The control method will use water instead of air inserted into the colon. The study method will use a commercially available AI system plus water during the procedure. Researchers will compare APCs to see if the addition of AI increases detection of adenomas during WE colonoscopy.

Conditions

• Colon Adenoma
• Colonoscopy
• Colon Polyp

Interventions

DEVICE

Water exchange alone

During the insertion phase of water exchange colonoscopy, the air pump will be turned off, while the colon will be irrigated with warm-to-touch water using a flushing pump. The water exchange approach involves the simultaneous infusion of water to facilitate luminal expansion and suction of unclean water during insertion. Upon reaching the cecum, where most of the water is suctioned to collapse the cecal lumen, the air pump will be opened. Withdrawal from the cecum will begin in the left lateral position. Similar withdrawal techniques with adequate luminal distention and comprehensive examination behind the folds will be emphasized. Any position change away from the original left lateral position in any colon segment during the withdrawal phase will be recorded. Tandem examination of specific colon segments, including the right colon, either in the standard modality or retroflexion, is prohibited.

DEVICE

Water exchange plus Artificial Intelligence (AI)

Similar water exchange technique as the active comparator will be employed during insertion. Similar withdrawal inspection techniques as the active comparator will be used. During withdrawal phase, commercially available AI system (CAD-EYE, Fujifilm, EU and Taiwan; Endo-AID, Olympus, EU and Taiwan) will be activated, providing a bounding box as output any time a lesion that is suspected to be a polyp is recognized by the AI device. False positive activation is defined as the identification by AI systems of an area during the withdrawal phase that is not deemed to be a colorectal lesion after re-examination by the colonoscopist. Real-time flagging of FP activation will be recorded by investigators and study staff.

Sponsors & Collaborators

• Digestive Endoscopy Unit, CTO Hospital, Iglesias, Italy

  collaborator UNKNOWN

• The Sepulveda Ambulatory Care Center, VAGLAHS, UCLA in the USA

  collaborator UNKNOWN

• Evergreen General Hospital, Taiwan

  lead OTHER

Principal Investigators

• Sergio Cadoni, MD · Endoscopy Digestive Unit, CTO Hospital, Iglesias, Italy

Study Design

Allocation

RANDOMIZED

Purpose

SCREENING

Masking

SINGLE

Model

PARALLEL

Eligibility

Min Age

45 Years

Max Age

75 Years

Sex

ALL

Healthy Volunteers

Yes

Timeline & Regulatory

Start

2023-12-18

Primary Completion

2024-12-05

Completion

2025-01-05

Countries

• Italy
• Taiwan

Study Locations