Trial Review

Technical difficulties have been reported by some users of the search function and is being investigated by technical staff. Thank you for your patience and apologies for any inconvenience caused.

The safety and scientific validity of this study is the responsibility of the study sponsor and investigators. Listing a study does not mean it has been endorsed by the ANZCTR. Before participating in a study, talk to your health care provider and refer to this information for consumers
Trial registered on ANZCTR


Registration number
ACTRN12622000866707
Ethics application status
Approved
Date submitted
7/05/2022
Date registered
17/06/2022
Date last updated
17/06/2022
Date data sharing statement initially provided
17/06/2022
Type of registration
Prospectively registered

Titles & IDs
Public title
Does Artificial Intelligence Improve Polyp Detection at Colonoscopy?
Scientific title
A randomised controlled trial to determine the impact of an artificial intelligence platform on adenoma detection rate during colonoscopy in adults
Secondary ID [1] 307073 0
Nil known
Universal Trial Number (UTN)
U1111-1278-0636
Trial acronym
Linked study record

Health condition
Health condition(s) or problem(s) studied:
Colonic Polyps 326230 0
Condition category
Condition code
Oral and Gastrointestinal 323532 323532 0 0
Other diseases of the mouth, teeth, oesophagus, digestive system including liver and colon
Cancer 323745 323745 0 0
Bowel - Back passage (rectum) or large bowel (colon)

Intervention/exposure
Study type
Interventional
Description of intervention(s) / exposure
Usual standard of care from the endoscopist doctor, with addition of Endo-AID (Olympus Corporation) AI module to be on during withdrawal phase of colonoscopy.

-Usual standard of care: single colonoscopy, which may take between 3-30 minutes. During withdrawal phase, which may take between 6 and 60 minutes, the AI module will be activated. It is not known if use of this module will increase the withdrawal time (compared to standard of care, without it).
-The nurses will advise the doctor of the randomisation (AI or standard of care), and turn on the AI device once withdrawal has commenced.
-The AI will analyse the video output from the scope to automatically detect suspected polyps in real-time during withdrawal. Polyps would then be further analysed and resected as per usual standard of care.
Intervention code [1] 323527 0
Diagnosis / Prognosis
Comparator / control treatment
Usual standard of care - colonoscopy withdrawal using doctor preference for polyp detection. This can take between 6-60 minutes. The artificial intelligence module will not be used to examine images taken during this procedure for the control participants.
Control group
Active

Outcomes
Primary outcome [1] 331290 0
ADR (Adenoma Detection Rate) - proportion of patients with at least one histologically proven adenoma or carcinoma. Histology will be assessed using standard procedure in the laboratory.
This data will be gathered from colonoscopy reports and lab reports of patients
Timepoint [1] 331290 0
At time of colonoscopy
Secondary outcome [1] 409435 0
PDR (Polyp Detection Rate): proportion of patients with at least one histologically proven polyp removed. This data will be gathered from colonoscopy reports and lab reports of patients.
Timepoint [1] 409435 0
At time of colonoscopy
Secondary outcome [2] 409436 0
Proximal ADR: proportion of patients with at least one histologically proven polyp removed proximal to the splenic flexture. This data will be gathered from colonoscopy reports and lab reports of patients.
Timepoint [2] 409436 0
At time of colonoscopy
Secondary outcome [3] 409437 0
Mean number of adenomas per colonoscopy (APC) - total number of adenomas divided by the number of colonoscopies performed. This will be comparing standard colonoscopy to AI assisted detection on colonoscopy.
This data will be gathered from colonoscopy reports and lab reports.
Timepoint [3] 409437 0
At time of colonsocopy
Secondary outcome [4] 409438 0
Sessile serrated detection rate (SSL): proportion of patients with at least one histologically proven sessile serrated lesion removed. This data will be gathered from colonoscopy reports and lab reports of patients.
Timepoint [4] 409438 0
At time of colonoscopy
Secondary outcome [5] 409439 0
Non-neoplastic resection rate – proportion of patients with polyps removed that are not histologically proven adenomas, SSLs, or colorectal cancers. This data will be gathered from colonoscopy reports and lab reports of patients.
Timepoint [5] 409439 0
At time of colonoscopy
Secondary outcome [6] 409440 0
Withdrawal time. This will be calculated using a timer (initiated by nursing staff) from the end of the colon (caecum) to withdrawal of the scope from the anus.
Timepoint [6] 409440 0
At time of colonoscopy (at the end)

Eligibility
Key inclusion criteria
• Aged 18 years old or above;
• They require elective colonoscopy for colorectal cancer screening, surveillance, or investigation of symptoms
• Written informed consent obtained.
Minimum age
18 Years
Maximum age
No limit
Sex
Both males and females
Can healthy volunteers participate?
No
Key exclusion criteria
• Contraindication or conditions precluding polyp resection (e.g. active gastrointestinal bleeding, significant bleeding tendency, uninterrupted anticoagulation)
• Scheduled staged procedure for polypectomy or biopsy
• Inflammatory Bowel Disease
• Previous bowel resection
• Unable to obtain informed consent

Study design
Purpose of the study
Diagnosis
Allocation to intervention
Randomised controlled trial
Procedure for enrolling a subject and allocating the treatment (allocation concealment procedures)
prior to colonoscopy initiation, an opaque envelope will be opened by nursing staff with instructions for use of AI or not. Envelopes will be created with instructions by an administrator not participating in study and shuffled.
Methods used to generate the sequence in which subjects will be randomised (sequence generation)
Participants will be allocated to the two intervention groups at a 1:1 ratio, and the computer-generated randomisation schedule will be pre-determined prior to participant recruitment.
Masking / blinding
Open (masking not used)
Who is / are masked / blinded?



Intervention assignment
Parallel
Other design features
Phase
Not Applicable
Type of endpoint/s
Efficacy
Statistical methods / analysis
A sample size of 390 patients per arm is required based on the expected ADR of 35% for both arms, a non-inferiority margin of 10%, power of 90% and an alpha level of 5% (onesided). Non-inferiority was met for the primary endpoint if the lower 2-sided 90% confidence interval (CI) excluded a 10% or greater difference in favor of the control group. The 10% non-inferiority margin reflects a typical maximum clinically acceptable difference for comparative studies of this type. If non-inferiority was demonstrated for the primary endpoint, the endpoint was assessed for superiority (1 sided p value <0.05) using the Fisher exact test.

Recruitment
Recruitment status
Not yet recruiting
Date of first participant enrolment
Anticipated
4/07/2022
Actual
Date of last participant enrolment
Anticipated
22/12/2023
Actual
Date of last data collection
Anticipated
22/12/2023
Actual
Sample size
Target
780
Accrual to date
Final
Recruitment outside Australia
Country [1] 24753 0
New Zealand
State/province [1] 24753 0

Funding & Sponsors
Funding source category [1] 311384 0
Commercial sector/Industry
Name [1] 311384 0
Olympus
Country [1] 311384 0
New Zealand
Primary sponsor type
Hospital
Name
Waitakere Hospital
Address
55-75 Lincoln Road, Henderson, Auckland 0610
Country
New Zealand
Secondary sponsor category [1] 312775 0
None
Name [1] 312775 0
Address [1] 312775 0
Country [1] 312775 0

Ethics approval
Ethics application status
Approved
Ethics committee name [1] 310868 0
Northern B Health and Disability Ethics Committee
Ethics committee address [1] 310868 0
Ministry of Health
Health and Disability Ethics Committees
PO Box 5013
Wellington 6140
Ethics committee country [1] 310868 0
New Zealand
Date submitted for ethics approval [1] 310868 0
12/12/2021
Approval date [1] 310868 0
03/05/2022
Ethics approval number [1] 310868 0
Project ID: 11946

Summary
Brief summary
Computer-aided polyp detection tools (CADe), utilizing artificial intelligence (AI) may increase polyp detection in the bowel during colonoscopy. Polyps are the outgrowths in the bowel that may go on the turn to colon cancer. Detecting and removing polyps is the best known method to prevent colon cancer. The primary role of these tools is the automated detection of polyps, indicating the presence and location of lesions in real time. By drawing the endoscopist’s attention to AI-recognised polyps, the software provides visual support and an additional safety mechanism that may help reduce the frequency of overlooked polyps.

We aim to perform a true prospective randomised control trial to establish if AI assisted colonoscopy does increase detection as compared to our usual standard of care.
Trial website
Trial related presentations / publications
Public notes
Provisional approval NZ HDEC given 3/5/22. Awaiting complete final approval following submission of new documentation.

Contacts
Principal investigator
Name 119158 0
Dr Cameron Schauer
Address 119158 0
C/O Gastroenterology Department, Waitakere Hospital
55-75 Lincoln Road, Henderson, Auckland 0610
Country 119158 0
New Zealand
Phone 119158 0
+64210368637
Fax 119158 0
Email 119158 0
cameron.schauer@gmail.com
Contact person for public queries
Name 119159 0
Dr Cameron Schauer
Address 119159 0
C/O Gastroenterology Department, Waitakere Hospital
55-75 Lincoln Road, Henderson, Auckland 0610
Country 119159 0
New Zealand
Phone 119159 0
+64210368637
Fax 119159 0
Email 119159 0
cameron.schauer@gmail.com
Contact person for scientific queries
Name 119160 0
Dr Cameron Schauer
Address 119160 0
C/O Gastroenterology Department, Waitakere Hospital
55-75 Lincoln Road, Henderson, Auckland 0610
Country 119160 0
New Zealand
Phone 119160 0
+64210368637
Fax 119160 0
Email 119160 0
cameron.schauer@gmail.com

Data sharing statement
Will individual participant data (IPD) for this trial be available (including data dictionaries)?
No
No/undecided IPD sharing reason/comment
All data is de-identified once collected (see attached data management plan).

De-identified, raw, line-by-line data for each participant will NOT be made available.


What supporting documents are/will be available?




Results publications and other study-related documents

Documents added manually
No documents have been uploaded by study researchers.

Documents added automatically
No additional documents have been identified.