Artificial Intelligence Aid Systems in Colorectal Adenoma Detection

Not Applicable

Completed

• Conditions: Adenoma Detection Rate
• Interventions: Device: Computed adenoma detection system (CADe); Behavioral: Control group (regular colonoscopy)

• Registration Number: NCT04945044
• Lead Sponsor: Hospital Universitario de Canarias

Brief Summary

The main purpose of the study to evaluate the usefulness of the Endo-AID artificial intelligence system in the detection of colorectal adenomas in consecutive patients for outpatient colonoscopy.

The secondary aims were:

* To evaluate the benefit of Endo-AID in adenoma detection rate by comparing endoscopists with high and low adenoma detection rate.

* To evaluate serrated detection rate, advanced adenoma detection rate, adenoma detection rate according to the size (\<= 5mm, 6-9mm,\> = 10mm) and number of adenomas by colonoscopy. Stratification by location and morphology.

Detailed Description

Priority guidelines have been established regarding IA applied to gastrointestinal endoscopy. Regarding the priority uses for their development, there are applications that improve vision, placing computer-assisted lesion detection (CADe) as one of the most necessary priorities, given the importance of colorectal cancer screening (CRC) and post-polypectomy surveillance. The evaluation of these systems in different clinical practices and patient groups has been recommend. In this regard, studies in the western population are limited and have been carried out by expert endoscopists. It has not been evaluated in endoscopists with different adenoma detection rates. In addition, there are no studies with the recent CADe Endo-AID system (Olympus Corp. Tokyo).

The main purpose of the study to evaluate the usefulness of the Endo-AID artificial intelligence system in the detection of colorectal adenomas in consecutive patients for outpatient colonoscopy. In addition, the benefit of the CADe system will be assessed according to the endoscopist ADR.

A randomized controlled trial will be carried out in consecutive outpatients meeting the inclusion criteria and none of the exclusion criteria. Patients with be randomized to one of the four groups: CADe system and high ADR endoscopist; CADe system and low ADR endoscopist; Control and high ADR endoscopist; Control and low ADR endoscopist.

For the sample size calculation a 14.4 of difference in favor of the CADe system was considered. Taking onto account an alpha error of 0.05 in a unilateral contrast, a power of 80% and a loss of 10%, 165 patients per group would be required.

Study Timeline

• Study First Submitted: 2021-06-22
• Study First Submitted QC: 2021-06-22
• Study First Posted: 2021-06-30
• Study Start: 2021-11-15
• Primary Completion: 2022-01-31
• Study Completion: 2022-01-31
• Status Verified: 2022-09
• Last Update Submitted: 2022-09-19
• Last Update Posted: 2022-09-21

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 370

Inclusion Criteria

• Age ≥ 18 years.
• Patients referred for outpatient colonoscopy

Exclusion Criteria

• Colonic resection
• Taking anticoagulants or antiagregants that contraindicate the performance of therapy
• Patients with a recent colonoscopy (<6 months) of good quality (e.g. cited for endoscopic therapy)
• Inflammatory bowel disease
• Patients with incomplete colonoscopy
• Patients with inadequate preparation using the Boston Colonic Preparation Scale (BBPS). A cleaning quality of less than 2 points in any of the 3 colonic sections will be considered inadequate.
• Patients with polyposis syndromes
• Refusal to participate in the study.

Study & Design

• Study Type: INTERVENTIONAL
• Study Design: PARALLEL

Arm && Interventions

Group	Intervention	Description
Computed adenoma detection system (CADe)	Computed adenoma detection system (CADe)	Tis system can detect in the screen suspicion areas of adenomatous polyps. This is an additional help for the endoscopist for the detection of lesions
Control group (absence of CADe)	Control group (regular colonoscopy)	This is the control group. As in the routine colonoscopy the endoscopist is in charge of the detection of the lesions.

Primary Outcome Measures

Name	Time	Method
Adenoma detection rate	[Time frame: 1 years][Designated as safety issue: No]	Number of colonoscopies with colorectal adenoma/Number of total colonoscopies

Secondary Outcome Measures

Name	Time	Method
Serrated detection rate	[Time Frame: 1 years][Designated as safety issue: No]	Number of colonoscopies with serrated adenoma/Number of total colonoscopies
Advanced adenoma detection rate	[Time Frame: 1 years][Designated as safety issue: No]	Number of colonoscopies with advanced adenoma/Number of total colonoscopies

Trial Locations

Locations (1)

Department of Gastroenterology; 🇪🇸 La Laguna, S/C De Tenerife, Spain