Autonomous Artificial Intelligence Versus AI Assisted Human Optical Diagnosis (CADx-Prosp)

Autonomous Artificial Intelligence Versus AI Assisted Human Optical Diagnosis of Colorectal Polyps

Computer-aided image-enhanced endoscopy can predict the nature of colorectal polyps with over 90% accuracy. This technology uses artificial intelligence (AI) to analyze video recordings of polyps, learning to make diagnoses in real-time. This means that doctors can get immediate predictions about small polyps during the procedure, reducing the need for separate pathology exams and saving costs, ultimately improving patient care.

Human and AI interactions are complex and a framework to reap synergistic effects CADx systems when used by humans to harness optimal performance needs to be established. AI solutions in medicine are usually developed to be used as assistive devices, however, then they rely on humans to correct AI errors. Optical polyp diagnosis is a complex task. Non experts usually achieve diagnostic accuracy in 70-80%. CADx systems have a similar diagnostic accuracy when used autonomously. Clinical evaluation of CADx systems showed that CADx assisted OD performs equally to the operator performance when using non CADx assisted OD. To harness a benefit of clinical CADx implementation we would have to find a way that synergies between human and CADx come into play to eliminate cases in which CADx assisted and/ or human OD results in low diagnostic accuracy and also addresses the problem of serrated polyp recognition.

Study Overview

• Status: Not yet recruiting
• Conditions: Colonic Polyp; Artificial Intelligence
• Intervention / Treatment: Other: CADx (AI) system

Detailed Description

Our study hypothesis is that for CADx implementation, instead of using the high/low confidence framework, identifying cases with suboptimal diagnostic accuracy could be facilitated through identifying cases in which CADx and endoscopist disagreed in their diagnosis. Eliminating such cases might separate out cases with low accuracy when using CADx assisted OD. Since endoscopists have a high sensitivity but low specificity for serrated polyp OD, this framework will also allow us to implement a strategy to adequately manage serrated polyps found in the cohort.

• Study Type: Interventional
• Enrollment (Estimated): 540
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Daniel von Renteln, MD; Phone Number: 30912 514 890-8000; Email: daniel.von.renteln.med@ssss.gouv.qc.ca

Study Locations

• Canada
  • Quebec
    • Montréal, Quebec, Canada
      • Ghislaine Ahoua
      • Contact: Daniel Von Renteln, MD

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Indication for full colonoscopy.

Exclusion Criteria:

• Known inflammatory bowel disease
• Active colitis
• coagulopathy
• familial polyposis syndrome
• poor general health, defined as an American Society of Anesthesiologists class >3
• emergency colonoscopy

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm

Intervention / Treatment

Other: All participants; The endoscopist will make an optical diagnosis (OD) prediction for all small polyps (up to 10 mm) in white light (WL). Then, the endoscopist will make another OD prediction using image enhanced endoscopy (IEE) modes. After that, CADx will be activated in the IEE mode and a CADx prediction will be documented. Finally, after seeing the CADx prediction, the endoscopist will make a final prediction, which can agree or disagree with the autonomous CADx one. Polyps will be resected and sent to a pathology lab, where a pathologic diagnosis (blinded to the endoscopist's predictions) will be rendered.

Other: CADx (AI) system; The CADx system will be used to predict the histopathology of the polyp detected.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Accuracy of optical diagnosis, for polyps 1-5mm, compared with an agreed upon CADx-assisted diagnosis	Accuracy of optical diagnosis, for polyps 1-5mm, compared with an agreed upon CADx-assisted diagnosis , when histopathology results are used as the reference	up to 100 weeks

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Test characteristics, including recall, specificity, positive and negative predictive values (PPV/NPV), and particularly the NPV of rectosigmoid neoplastic polyps.	A ≥90% NPV will be used as a quality benchmark for a strategy to not resect such diminutive polyps.	up to 100 weeks
Agreement of surveillance interval recommendations of AI-A and AI-H compared with the pathology-based recommendations	For surveillance interval assignment, the pathology results of concomitant polyps >5 mm (including multiple concomitant polyps of all sizes and histology) will be considered when calculating the surveillance interval recommendation. Surveillance recommendations will be based on the 2020 United States Multi Society Task Force Guidelines as is current standard of practice at our center.	up to 100 weeks
Proportion of patients for whom an immediate surveillance recommendation can be directly provided for each approach, and how often histopathology-based polyp examination would have been avoided.	The potential cost-effectiveness of OD (either approaches) will be evaluated using the measured described above.	up to 100 weeks
Variability of OD (AI-A and AI-H) across participating endoscopists.	Each participating endoscopist will conduct a similar number of optical diagnoses to assess endoscopist-related factors.	up to 100 weeks
Cost-effectiveness of OD ((AI-A and AI-H)	A cost-effectiveness model will be applied to better quantify costs and understand cost impact including key cost drivers when generalized to a broader screening population.	up to 100 weeks
Accuracy of optical diagnosis, for polyps 1-10mm, compared with an agreed upon CADx-assisted diagnosis	Accuracy of optical diagnosis, for polyps 1-10mm, compared with an agreed upon CADx-assisted diagnosis, when histopathology results are used as the reference	up to 100 weeks

Collaborators and Investigators

• Sponsor: Centre hospitalier de l'Université de Montréal (CHUM)
• Collaborators: Roupen Djinbachian, MD; Mahsa Taghiakbari, MD PHD
• Investigators: Principal Investigator: Daniel von Renteln, MD, University of Montreal Medical Center (CHUM)

Study record dates

Study Major Dates

• Study Start (Estimated): November 15, 2024
• Primary Completion (Estimated): November 15, 2024
• Study Completion (Estimated): November 15, 2024

Study Registration Dates

• First Submitted: July 30, 2024
• First Submitted That Met QC Criteria: August 5, 2024
• First Posted (Actual): August 9, 2024

Study Record Updates

• Last Update Posted (Actual): November 15, 2024
• Last Update Submitted That Met QC Criteria: November 13, 2024
• Last Verified: November 1, 2024

More Information

Terms related to this study

• Keywords: optical diagnosis, artificial intelligence
• Additional Relevant MeSH Terms: Pathological Conditions, Anatomical; Intestinal Polyps; Polyps; Colonic Polyps
• Other Study ID Numbers: 2025-12306

Drug and device information, study documents

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