Real-life Implementation of an AI-based Optical Diagnosis

Artificial Intelligence Clinical Trial

— AI-OD  

Official title:

Real-life Implementation of an Artificial Intelligence Based Optical Diagnosis Strategy for Diminutive Colorectal Polyps

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT06059378
• Other study ID #: 2024-11557
• Status: Recruiting
• Phase: N/A
• Start date: September 1, 2023
• Est. completion date: January 30, 2024

Study information

• Verified date: September 2023
• Source: Centre hospitalier de l'Université de Montréal (CHUM)
• Contact: n/a
• Is FDA regulated: No
• Study type: Interventional

Clinical Trial Summary

This is a prospective study that is the first to implement resect and discard and diagnose and leave strategies in real-time practice using stringent documentation and adjudication by 2 expert endoscopists as the gold standard. Therefore, this study mainly aims to evaluate the agreement between (CADx) assisted optical diagnosis and adjudication by two expert endoscopists in establishing surveillance intervals concordant with the European Society for Gastrointestinal Endoscopy (ESGE) and US Multisociety task force (USMSTF) guidelines.

Description:

All patients who meet the in/exclusion criteria can be enrolled.

Eligible patients will be informed about the study through a consent form that includes information on optical diagnosis (resect and discard, diagnose and leave) and AI/CADx systems. Subsequently, patients will be asked if they are willing to participate in the study, using AI-assisted optical diagnosis and the "resect and discard" and "diagnose and leave" strategy. If a patient declines to undergo optical diagnosis, they will be asked about the reason for their refusal to participate in the study. The options for their response include:

1. Concerns regarding undergoing an optical diagnosis.

2. Reluctance to participate in research projects in general.

3. Other reasons.

4. Preference not to answer the question. This data along with patient characteristics (age, sex) will be captured and kept to analyse reasons for non-participation. Patients who agree to participate in the study will undergo standard colonoscopy procedures with AI-assisted optical diagnosis for all diminutive colorectal polyps identified. High-definition colonoscopes with a joint computer-assisted classification (CADx) support (CAD-EYE software EW10-EC02) will be used. The endoscopists will also use the CAD-EYE blue light imaging (BLI) mode to enhance the visualization of polyp features. During the optical diagnosis using CADx, the most probable diagnosis (neoplastic or hyperplastic) will be displayed on the endoscopy screen. If the serrated pathology subtype is determined as the most probable histology, the endoscopists will make the final decision. They will also indicate whether their optical diagnosis was made with low or high confidence. When high-risk histology features are observed using BLI, the endoscopists will inform the research assistant for documentation, and the polyp will be sent for pathology examination in accordance with the ASGE PIVI guidelines recommendations. All polyps >5mm will be send for pathology evaluation as per standard of care. Polyp size will be measured using virtual scale technology integrated in the computer-assisted system (CAD) to ensure an accurate polyp sizing.

The surveillance intervals will be determined according to the most recent USMSTF and ESGE guidelines. Two independent endoscopists blinded to the initial optical diagnosis will review all video recordings and will independently perform the AI-assisted optical diagnosis for each 1-5mm polyp. For polyps >5mm, diagnosis will be evaluated through histology as per standard of care.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 102
• Est. completion date: January 30, 2024
• Est. primary completion date: December 1, 2023
• Accepts healthy volunteers: No
• Gender: All
• Age group: 45 Years to 80 Years

Eligibility

Inclusion Criteria:

• Age 45-80 years

• Undergoing an outpatient colonoscopy at the Centre Hospitalier de l'Université de Montréal (CHUM)

• Signed informed consent form

Exclusion Criteria:

• Inflammatory Bowel Disease;

• Active colitis;

• Hereditary CRC syndrome;

• Coagulopathy;

• American Society of Anesthesiologists (ASA) status >3

Related Conditions & MeSH terms

• Artificial Intelligence
• Disease

Intervention

Device:
• Artificial intelligence-assisted classification (CADx)
CADeye (Fujifilm, Japan) is a joint detection (CADe) and classification (CADx) AI-supported system, which has been developed utilising AI deep learning technology to support endoscopic lesion detection and characterisation in the colon.

Locations

Country	Name	City	State
Canada	Centre Hospitalier de l'Université de Montréal	Montréal	Quebec

Sponsors (1)

Lead Sponsor	Collaborator
Daniel Von Renteln

Country where clinical trial is conducted

Canada, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Agreement between (CADx) assisted optical diagnosis and adjudication by two expert endoscopists in establishing surveillance intervals	To calculate the proportion of surveillance intervals that are concordant with the European Society for Gastrointestinal Endoscopy (ESGE) and US Multisociety task force (USMSTF) guidelines when using adjudication by two expert endoscopists as the reference standard.	120 days
Secondary	Diagnostic characteristics of of (CADx) assisted optical diagnosis strategy using adjudication by two expert endoscopists as the reference standard	To calculate the accuracy, sensitivity, specificity, positive predictive value, negative predictive value of (CADx) assisted optical diagnosis (resect and discard) strategy using adjudication by two expert endoscopists as the reference standard.	120 days
Secondary	Negative predictive value for the diagnosis of rectosigmoid adenomas of an AI (CADx) assisted optical diagnosis (diagnose and leave) strategy using adjudication by two expert endoscopists as the reference standard	To calculate the negative predictive value for the diagnosis of rectosigmoid adenomas of an AI (CADx) assisted optical diagnosis strategy using adjudication by two expert endoscopists as the reference standard	120 days
Secondary	Assessing efficiency gains through AI-assisted optical diagnosis	To calculate the percentage of histopathologic analyses that could be avoided and the cost savings resulting from replacing pathology with AI-assisted optical diagnosis.	120 days
Secondary	Willingness of patients for undergoing AI-assisted optical diagnosis instead of pathology for diminutive polyps	To calculate the percentage of patients who agree to undergo resect and discard and diagnose and leave strategies	120 days
Secondary	Assessing cost savings through AI-assisted optical diagnosis	To calculate the cost savings associated with avoiding histologic analysis of resected specimen (estimated in 2023 Canadian Dollars).	120 days
Secondary	Assessing efficiency gains through same-day surveillance interval communication due to implementation of AI-based optical diagnosis	To calculate the percentage of patients who can receive surveillance interval assignment on the same day as the colonoscopy.	120 days