Impact of Artificial Intelligence (AI) on Adenoma Detection During Colonoscopy in FIT+ Patients.

NCT ID: NCT04691401

Last Updated: 2024-03-26

Basic Information

• Recruitment Status: COMPLETED
• Clinical Phase: NA
• Total Enrollment: 750 participants
• Study Classification: INTERVENTIONAL
• Study Start Date: 2020-12-20
• Study Completion Date: 2021-12-31

Brief Summary

The Italian screening program invites the resident population aged 50-74 for Fecal Immunochemical Test (FIT) every 2 years. Subjects who test positive are referred for colonoscopy. Maximizing adenoma detection during colonoscopy is of paramount importance in the framework of an organized screening program, in which colonoscopy represent the key examination. Initial studies consistently show that Artificial iIntelligence-based systems support the endoscopist in evaluating colonoscopy images potentially increasing the identification of colonic polyps. However, the studies on AI and polyp detection performed so far are mostly focused on technical issues, are based on still images analysis or recorded video segments and includes patients with different indications for colonoscopy. At the best of our knowledge, data on the impact on AI system in adenoma detection in a FIT-based screening program are lacking. The present prospective randomized controlled trial is aimed at evaluating whether the use of an AI system increases the ADR (per patient analysis) and/or the mean number of adenomas per colonoscopy in FIT-positive subjects undergoing screening colonoscopy. Therefore Patients fulfilling the inclusion criteria are randomized (1:1) in two arms: A) patients receive standard colonoscopy (with high definition-HD endoscopes) with white light (WL) in both insertion and withdrawal phase; all polyps identified are removed and sent for histopathology examination; B) patients receive colonoscopy examinations (with HD endoscopes) equipped with an AI system (in both insertion and withdrawal phase); all polyps identified are removed and sent for histopathology examination. In the present study histopathology represents the reference standard.

Conditions

Polyp of Colon

Study Design

• Allocation Method: RANDOMIZED
• Intervention Model: PARALLEL
• Primary Study Purpose: SCREENING
• Blinding Strategy: NONE

Study Groups

Standard WL (white light) colonoscopy

all patients receive standard colonoscopy (with high definition- HD- endoscopes) with white light (WL) in both insertion and withdrawal phase; all polyps identified are removed and sent for histopathology examination.

Group Type: NO_INTERVENTION

No interventions assigned to this group

Standard colonoscopy with assistance of Artificial Intelligence (CAD-EYE (Fujifilm Co, Tokyo, Japan)

all patients receive colonoscopy examinations (with HD endoscopes) equipped with an Ai system (CAD-EYE, Fujifilm Co, Tokyo, Japan) in both insertion and withdrawal phase). This system is a real-time computer-assisted image analysis that allows automatic polyp identification without modifications to the colonoscope or to the actual endoscopic procedure. When CAD EYE identifies a polyp, both a visual (a green blinking box surrounding the identified polyp, called the detection box) and an acoustic alarm pop up and attract the endoscopist attention. Around the endoscopic image a visual assist circle is shown and lights up in the direction where the suspicious polyp is detected.All polyps identified are removed and sent for histopathology examination.

Group Type: EXPERIMENTAL

Artificial Intelligence System (CAD EYE, Fujifilm Co.)

Intervention Type: DEVICE

A dedicated CNN-based AI system (CAD EYE, Fujifilm Co, Tokyo, Japan) has been recently developed. The Computer-aided diagnosis (CAD) CAD EYE system is a real-time computer-assisted image analysis that allows automatic polyp identification without modifications to the colonoscope or to the actual endoscopic procedure. When CAD EYE identifies a polyp, both a visual (a green blinking box surrounding the identified polyp, called the detection box) and an acoustic alarm pop up and attract the endoscopist attention. Around the endoscopic image a visual assist circle is shown and lights up in the direction where the suspicious polyp is detected.

Interventions

Artificial Intelligence System (CAD EYE, Fujifilm Co.)

A dedicated CNN-based AI system (CAD EYE, Fujifilm Co, Tokyo, Japan) has been recently developed. The Computer-aided diagnosis (CAD) CAD EYE system is a real-time computer-assisted image analysis that allows automatic polyp identification without modifications to the colonoscope or to the actual endoscopic procedure. When CAD EYE identifies a polyp, both a visual (a green blinking box surrounding the identified polyp, called the detection box) and an acoustic alarm pop up and attract the endoscopist attention. Around the endoscopic image a visual assist circle is shown and lights up in the direction where the suspicious polyp is detected.

Intervention Type: DEVICE

Eligibility Criteria

Inclusion Criteria

• Consecutive adult (50-74 yrs.) outpatients undergoing colonoscopy in the frame of the FIT-based screening program.

Exclusion Criteria

• patients with CRC history or hereditary polyposis syndromes or hereditary non-polyposis colorectal cancer
• patients with inadequate bowel preparation
• patients in which cecal intubation was not achieved or scheduled for partial examinations
• patients with gastrointestinal symptoms
• polyps could not be resected due to ongoing anticoagulation preventing resection and pathological assessment

• Minimum Eligible Age: 50 Years
• Maximum Eligible Age: 74 Years
• Eligible Sex: ALL
• Accepts Healthy Volunteers: No

Sponsors

Valduce Hospital

OTHER

Sponsor Role: lead

Responsible Party

Franco Radaelli

Head of Gastroenterology Unit

Responsibility Role: PRINCIPAL_INVESTIGATOR

Locations

Gastroenterology Unit, Valduce Hospital

Como, , Italy

Countries

Italy

Other Identifiers

598/2020

Identifier Type: -

Identifier Source: org_study_id