Improving Polyp Detection Rate by Artificial Intelligence in Colonoscopy
Primary Purpose
Colonic Polyp
Status
Recruiting
Phase
Not Applicable
Locations
Norway
Study Type
Interventional
Intervention
GI Genius
Standard white light colonoscope
Sponsored by
About this trial
This is an interventional diagnostic trial for Colonic Polyp focused on measuring Colonoscopy, Artificial intelligence, Polyp detection
Eligibility Criteria
Inclusion Criteria:
- Patients coming to outpatient clinics to perform colonoscopies
Exclusion Criteria:
- Total colectomy
- Reservation against registration in Gastronet, the national quality register for colonoscopy in Norway
Sites / Locations
- Haraldsplass Deaconess HospitalRecruiting
- Haukeland University HospitalRecruiting
- Kanalspesialistene ASRecruiting
Arms of the Study
Arm 1
Arm 2
Arm Type
Active Comparator
Active Comparator
Arm Label
With artificial intelligence (AI)
Without artificial intelligence
Arm Description
Use of GI Genius artificial intelligence device during colonoscopy.
Use of standard colonoscopy equipment without GI Genius.
Outcomes
Primary Outcome Measures
Polyp detection rate (PDR) with and without artificial intelligence (AI)
Evaluate the PDR with and without the use of GI Genus artificial intelligence
PDR after the use of AI, is there a learning effect?
Evaluate if there is an improved PDR after the use of AI
Secondary Outcome Measures
Withdrawal time
To evaluate if the withdrawal time is influenced by the use of artificial intelligence
Complications
To evaluate if there are more registered complications with the use of AI
Full Information
NCT ID
NCT05322993
First Posted
April 4, 2022
Last Updated
April 19, 2022
Sponsor
Haraldsplass Deaconess Hospital
Collaborators
Haukeland University Hospital, European Society of Gastrointestinal Endoscopy, Kanalspesialistene AS
1. Study Identification
Unique Protocol Identification Number
NCT05322993
Brief Title
Improving Polyp Detection Rate by Artificial Intelligence in Colonoscopy
Official Title
Improving Polyp Detection Rate by Artificial Intelligence in Colonoscopy
Study Type
Interventional
2. Study Status
Record Verification Date
April 2022
Overall Recruitment Status
Recruiting
Study Start Date
November 19, 2021 (Actual)
Primary Completion Date
June 30, 2023 (Anticipated)
Study Completion Date
December 31, 2023 (Anticipated)
3. Sponsor/Collaborators
Responsible Party, by Official Title
Sponsor
Name of the Sponsor
Haraldsplass Deaconess Hospital
Collaborators
Haukeland University Hospital, European Society of Gastrointestinal Endoscopy, Kanalspesialistene AS
4. Oversight
Studies a U.S. FDA-regulated Drug Product
No
Studies a U.S. FDA-regulated Device Product
No
Product Manufactured in and Exported from the U.S.
No
Data Monitoring Committee
No
5. Study Description
Brief Summary
The aim of this study is to investigate if the use of artificial intelligence (AI) in colonoscopy improves the polyp detection rate, and if the use of AI has a learning effect.
Detailed Description
The endoscopists will use GI Genius from Medtronic, a device that uses artificial intelligence (AI) based on machine learning to detect polyps in the colon in real time during colonoscopy. The device interprets the endoscopy pictures and superimposes possible polyps with frames.
The patients will be included in regular outpatient clinics in Western Norway. The endoscopists will be divided into groups depending on their experience. The endoscopists will perform colonoscopies in three phases; (1) before the use of AI, (2) during the use of AI and (3) after the use of AI. The investigators will then evaluate the polyp detection rate (PDR) in the three phases to see if AI increases PDR, and if there is a learning effect on PDR after the use of AI. The investigators will also evaluate if there is a difference in the learning-effect from AI-use depending on if the endoscopist is experienced or inexperienced.
The PDR's are registered as part of Norway's national quality register of colonoscopy, Gastronet. The data registered in Gastronet can also help the investigators evaluate other outcomes such as withdrawal time, bowel preparation, patient reported pain, patient satisfaction and complications.
6. Conditions and Keywords
Primary Disease or Condition Being Studied in the Trial, or the Focus of the Study
Colonic Polyp
Keywords
Colonoscopy, Artificial intelligence, Polyp detection
7. Study Design
Primary Purpose
Diagnostic
Study Phase
Not Applicable
Interventional Study Model
Crossover Assignment
Model Description
Endoscopists will perform colonoscopies in three consecutive phases; 1. without artificial intelligence (AI), 2. with AI, 3. without (AI).
Masking
None (Open Label)
Allocation
Non-Randomized
Enrollment
4500 (Anticipated)
8. Arms, Groups, and Interventions
Arm Title
With artificial intelligence (AI)
Arm Type
Active Comparator
Arm Description
Use of GI Genius artificial intelligence device during colonoscopy.
Arm Title
Without artificial intelligence
Arm Type
Active Comparator
Arm Description
Use of standard colonoscopy equipment without GI Genius.
Intervention Type
Device
Intervention Name(s)
GI Genius
Intervention Description
The use of artificial intelligence during colonoscopy to improve polyp detection.
Intervention Type
Device
Intervention Name(s)
Standard white light colonoscope
Intervention Description
Standard colonoscopy.
Primary Outcome Measure Information:
Title
Polyp detection rate (PDR) with and without artificial intelligence (AI)
Description
Evaluate the PDR with and without the use of GI Genus artificial intelligence
Time Frame
18 months
Title
PDR after the use of AI, is there a learning effect?
Description
Evaluate if there is an improved PDR after the use of AI
Time Frame
18 months
Secondary Outcome Measure Information:
Title
Withdrawal time
Description
To evaluate if the withdrawal time is influenced by the use of artificial intelligence
Time Frame
18 months
Title
Complications
Description
To evaluate if there are more registered complications with the use of AI
Time Frame
24 months
10. Eligibility
Sex
All
Accepts Healthy Volunteers
Accepts Healthy Volunteers
Eligibility Criteria
Inclusion Criteria:
Patients coming to outpatient clinics to perform colonoscopies
Exclusion Criteria:
Total colectomy
Reservation against registration in Gastronet, the national quality register for colonoscopy in Norway
Central Contact Person:
First Name & Middle Initial & Last Name or Official Title & Degree
Tom André Pedersen, MD
Phone
95812371
Ext
+47
Email
tom_andre_pedersen@haraldsplass.no
First Name & Middle Initial & Last Name or Official Title & Degree
Roald F. Havre, Professor
Phone
90842938
Ext
+47
Email
roald.flesland.havre@helse-bergen.no
Overall Study Officials:
First Name & Middle Initial & Last Name & Degree
Roald F. Havre, Professor
Organizational Affiliation
Helse Bergen
Official's Role
Study Director
Facility Information:
Facility Name
Haraldsplass Deaconess Hospital
City
Bergen
State/Province
Vestland
ZIP/Postal Code
5009
Country
Norway
Individual Site Status
Recruiting
Facility Contact:
First Name & Middle Initial & Last Name & Degree
Tom André Pedersen, MD
Phone
95812371
Ext
+47
Email
tom.andre.pedersen@haraldsplass.no
First Name & Middle Initial & Last Name & Degree
Abid Aziz, MD
Phone
92049192
Ext
+47
Email
abid.aziz@haraldsplass.no
Facility Name
Haukeland University Hospital
City
Bergen
State/Province
Vestland
ZIP/Postal Code
5021
Country
Norway
Individual Site Status
Recruiting
Facility Contact:
First Name & Middle Initial & Last Name & Degree
Roald F. Havre, Professor
Phone
90842938
Ext
+47
Email
roald.flesland.havre@helse-bergen.no
First Name & Middle Initial & Last Name & Degree
Trond Engjom, PhD
Phone
92049852
Ext
+47
Email
trond.engjom@helse-bergen.no
Facility Name
Kanalspesialistene AS
City
Bergen
State/Province
Vestland
ZIP/Postal Code
5068
Country
Norway
Individual Site Status
Recruiting
Facility Contact:
First Name & Middle Initial & Last Name & Degree
Georg G. Dimcevski, Professor
Phone
46667907
Ext
+47
Email
georg.dimcevski@gmail.com
First Name & Middle Initial & Last Name & Degree
Skjalg Klomstad, MD
Phone
90167688
Ext
+47
Email
sklomstad@gmail.com
12. IPD Sharing Statement
Plan to Share IPD
No
IPD Sharing Plan Description
There is no specific plan to share IPD with other researchers.
Links:
URL
http://www.sthf.no/helsefaglig/gastronet
Description
Gastronet, the national quality register of colonoscopies
Learn more about this trial
Improving Polyp Detection Rate by Artificial Intelligence in Colonoscopy
We'll reach out to this number within 24 hrs