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

Impact of AI (Artificial Intelligence) on Adenoma Detection During Colonoscopy in FIT+ Patients: a Prospective Randomized Controlled Trial

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.

Study Overview

• Status: Completed
• Conditions: Polyp of Colon
• Intervention / Treatment: Device: Artificial Intelligence System (CAD EYE, Fujifilm Co.)

• Study Type: Interventional
• Enrollment (Actual): 750
• Phase: Not Applicable

Contacts and Locations

Study Locations

• Italy
  • Como, Italy, 22100
    • Gastroenterology Unit, Valduce Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 48 years to 72 years (Adult, Older Adult)
• Accepts Healthy Volunteers: No

Description

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

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Screening
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
No Intervention: 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.
Experimental: 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.	Device: 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.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
ADR	Adenoma Detection Rate: rate of participants with at least on adenoma detected during colonoscopy	10 months
APC	Adenoma per Colonoscopy: it is determined by dividing the total number of adenomas removed by the total number of colonoscopies performed	10 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Adv-ADR	Adv-ADR: rate of participants with at least on advanced adenoma detected during colonoscopy	10 months
SSL-DR:	SSL-ADR: the serrated lesions with neoplastic potential (sessile serrated lesions-SSA; traditional serrated adenomas - TSA) detection rate.	10 months

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Impact of Ai on endoscopist with different ADR	The variation in ADR will be stratified according the initial ADR of endoscopists participating in the present study	10 months

Collaborators and Investigators

• Sponsor: Valduce Hospital

Study record dates

Study Major Dates

• Study Start (Actual): December 20, 2020
• Primary Completion (Actual): October 31, 2021
• Study Completion (Actual): December 31, 2021

Study Registration Dates

• First Submitted: December 17, 2020
• First Submitted That Met QC Criteria: December 30, 2020
• First Posted (Actual): December 31, 2020

Study Record Updates

• Last Update Posted (Actual): March 26, 2024
• Last Update Submitted That Met QC Criteria: March 24, 2024
• Last Verified: March 1, 2024

More Information

Terms related to this study

• Keywords: adenoma detection
• Additional Relevant MeSH Terms: Neoplasms by Histologic Type; Neoplasms; Neoplasms, Glandular and Epithelial; Pathological Conditions, Anatomical; Polyps; Intestinal Polyps; Adenoma; Colonic Polyps
• Other Study ID Numbers: 598/2020

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No