search
Back to results

Real Life AI in Polyp Detection (RELIANT)

Primary Purpose

Colonic Polyp

Status
Completed
Phase
Not Applicable
Locations
Germany
Study Type
Interventional
Intervention
AI-assisted colonoscopy
Sponsored by
Wuerzburg University Hospital
About
Eligibility
Locations
Arms
Outcomes
Full info

About this trial

This is an interventional diagnostic trial for Colonic Polyp focused on measuring Deep Learning, Polyp detection rate, CNN

Eligibility Criteria

18 Years - undefined (Adult, Older Adult)All SexesDoes not accept healthy volunteers

Inclusion Criteria:

  • Colonoscopies for Polyp detection

Exclusion Criteria:

  • Colonoscopies for Inflammatory Bowel Disease (IBD).
  • Colonoscopies for work up of an active bleeding

Sites / Locations

  • Universitätsklinikum Würzburg

Arms of the Study

Arm 1

Arm 2

Arm Type

Experimental

No Intervention

Arm Label

Colonoscopy with AI-assistance group

Standard Colonoscopy group

Arm Description

Colonoscopies were performed with AI-assistance.

Standard clinical procedure

Outcomes

Primary Outcome Measures

Polyp detection rate comparison
Number of polyps detected divided by number of colonoscopies
Mean withdrawal time comparison
Mean withdrawal time comparison

Secondary Outcome Measures

AI-Polyp bounding boxes - True Positive Evaluation
2 approaches: frame by frame analysis and temporal coherence analysis
AI-Polyp bounding boxes - False Positive Quantitative Evaluation
3 approaches depending on window-time detection
AI-Polyp bounding boxes - False Negative Evaluation
Number of by bounding box missed polyps
Reaction Time Analysis
Comparison time of polyp detection in a human vs machine approach

Full Information

First Posted
April 2, 2020
Last Updated
April 7, 2021
Sponsor
Wuerzburg University Hospital
search

1. Study Identification

Unique Protocol Identification Number
NCT04335318
Brief Title
Real Life AI in Polyp Detection
Acronym
RELIANT
Official Title
Real Life AI in Polyp Detection
Study Type
Interventional

2. Study Status

Record Verification Date
April 2021
Overall Recruitment Status
Completed
Study Start Date
May 1, 2020 (Actual)
Primary Completion Date
August 31, 2020 (Actual)
Study Completion Date
October 1, 2020 (Actual)

3. Sponsor/Collaborators

Responsible Party, by Official Title
Principal Investigator
Name of the Sponsor
Wuerzburg University Hospital

4. Oversight

Studies a U.S. FDA-regulated Drug Product
No
Studies a U.S. FDA-regulated Device Product
No
Data Monitoring Committee
No

5. Study Description

Brief Summary
The objective of this study is to compare the polyp detection rate (PDR) of endoscopists unaware of a commercially available artificial intelligence (AI) device for polyp detection during colonoscopy and the PDR of endoscopists with the aid of such a device. Moreover, an extensive characterization of the performance of this device will be done.
Detailed Description
Recently, there have been remarkable breakthroughs in the introduction of deep learning techniques, especially convolutional neural networks (CNNs), in assisting clinical diagnosis in different medical fields. One of these artificial intelligence (AI) devices to diagnose colon polyps during colonoscopy was launched in October 2019. Its intended use is to work as an adjunct to the endoscopist during a colonoscopy with the purpose of highlighting regions with visual characteristics consistent with different types of mucosal abnormalities. It is essential to know whether deep learning algorithms can really help endoscopists during colonoscopies. Several studies have already addressed this issue with different approaches and results. However, one common drawback of these type of Machine vs Human retrospective studies is endoscopist bias. It is usually generated because of human natural competitive spirit against machine or human relaxation because of AI-reliance. This can have an effect in the overall results. The investigators perfomed colonoscopies with the use of a commercially available AI system to detect colonic polyps and recorded them during clinical routine. Additionally from March 2019 - May 2019, 120 colonoscopy videos were performed and captured prospectively without the use of AI. In this study, the investigators plan to retrospectively compare those two video sets regarding the polyp detection rate, withdrawal time and polyp identification characteristics of the AI system.

6. Conditions and Keywords

Primary Disease or Condition Being Studied in the Trial, or the Focus of the Study
Colonic Polyp
Keywords
Deep Learning, Polyp detection rate, CNN

7. Study Design

Primary Purpose
Diagnostic
Study Phase
Not Applicable
Interventional Study Model
Parallel Assignment
Masking
None (Open Label)
Allocation
Non-Randomized
Enrollment
230 (Actual)

8. Arms, Groups, and Interventions

Arm Title
Colonoscopy with AI-assistance group
Arm Type
Experimental
Arm Description
Colonoscopies were performed with AI-assistance.
Arm Title
Standard Colonoscopy group
Arm Type
No Intervention
Arm Description
Standard clinical procedure
Intervention Type
Device
Intervention Name(s)
AI-assisted colonoscopy
Intervention Description
Colonoscopies performed with assistance of an AI tool that highlights the areas that are susceptible to be a polyp.
Primary Outcome Measure Information:
Title
Polyp detection rate comparison
Description
Number of polyps detected divided by number of colonoscopies
Time Frame
45 minutes
Title
Mean withdrawal time comparison
Description
Mean withdrawal time comparison
Time Frame
45 minutes
Secondary Outcome Measure Information:
Title
AI-Polyp bounding boxes - True Positive Evaluation
Description
2 approaches: frame by frame analysis and temporal coherence analysis
Time Frame
45 minutes
Title
AI-Polyp bounding boxes - False Positive Quantitative Evaluation
Description
3 approaches depending on window-time detection
Time Frame
45 minutes
Title
AI-Polyp bounding boxes - False Negative Evaluation
Description
Number of by bounding box missed polyps
Time Frame
45 minutes
Title
Reaction Time Analysis
Description
Comparison time of polyp detection in a human vs machine approach
Time Frame
45 minutes

10. Eligibility

Sex
All
Minimum Age & Unit of Time
18 Years
Accepts Healthy Volunteers
No
Eligibility Criteria
Inclusion Criteria: Colonoscopies for Polyp detection Exclusion Criteria: Colonoscopies for Inflammatory Bowel Disease (IBD). Colonoscopies for work up of an active bleeding
Overall Study Officials:
First Name & Middle Initial & Last Name & Degree
Alexander Hann, PD Dr. Med
Organizational Affiliation
Wuerzburg University Hospital
Official's Role
Principal Investigator
Facility Information:
Facility Name
Universitätsklinikum Würzburg
City
Würzburg
State/Province
Bayern
ZIP/Postal Code
97080
Country
Germany

12. IPD Sharing Statement

Plan to Share IPD
No

Learn more about this trial

Real Life AI in Polyp Detection

We'll reach out to this number within 24 hrs