UMIN-CTR Clinical Trial

Basic information
Public title	Clinical Evaluation of Diagnostic Support Software for Colonoscopy
Acronym	Evaluation of AI for colonoscopy
Scientific Title	Prospective Evaluation of a Computer-aided diagnosis for Narrow-Band Imaging of Colorectal Lesions
Scientific Title:Acronym	NBI-CAD study
Region	Japan

Condition
Condition	Colorectal neoplasms
Classification by specialty	Gastroenterology
Classification by malignancy	Malignancy
Genomic information	NO

Objectives
Narrative objectives1	To evaluate the diagnostic accuracy of AI for NBI images (NBI-CAD) for colorectal lesions.
Basic objectives2	Efficacy
Basic objectives -Others
Trial characteristics_1
Trial characteristics_2
Developmental phase

Assessment
Primary outcomes	To demonstrate that the lower limit of the confidence interval for the sensitivity of NBI-CAD to diminutive colorectal neoplasms exceeds 90%.
Key secondary outcomes	(1) Specificity, NPV, PPV,accuracy of NBI-CAD for diminutive neoplasms. (2) Sensitivity, specificity, NPV, PPV, and accuracy of NBI-CAD for tumors larger than 5 mm, SSA/P, and hyperplastic polyps. (3) Sensitivity, specificity, NPV, PPV, accuracy of NBI-CAD for neoplasms when the diagnostic result of NBI-CAD is high confidence (probability >90%). (4)The sensitivity, specificity, PPV, NPV, and accuracy of NBI-CAD for neoplastic lesions at high confidence (probability > 90%). (5) Adenoma detection rate (6) Advanced adenoma / neoplasia detection rate (7) Time from cecal arrival to endoscope witdrawal (8) Presence and type of adverse events (9) Surveillance interval concordance rate

Base
Study type	Observational

Study design
Basic design
Randomization
Randomization unit
Blinding
Control
Stratification
Dynamic allocation
Institution consideration
Blocking
Concealment

Intervention
No. of arms
Purpose of intervention
Type of intervention
Interventions/Control_1
Interventions/Control_2
Interventions/Control_3
Interventions/Control_4
Interventions/Control_5
Interventions/Control_6
Interventions/Control_7
Interventions/Control_8
Interventions/Control_9
Interventions/Control_10

Eligibility
Age-lower limit	40 years-old <=
Age-upper limit	Not applicable
Gender	Male and Female
Key inclusion criteria	(1) Patients who do not have any previous information regarding colorectal polyp and will undergo colonoscopy at the Digestive Disease Center, Showa University Northern Yokohama Hospital during the period from the approval by the IRB to December 31, 2021. 2) Patients who are 40 years old or older at the time of examination
Key exclusion criteria	(1) Patients with polyposis, such as familial adenomatous polyposis. (2) Patients with inflammatory bowel disease (3) Patients who have expressed their refusal for the use of the information (4) Patients whose pathological diagnosis has been made previously, such as biopsy at a previous doctor's office (5) Patients who are taking antiplatelet agents or anticoagulants and for whom resection of the lesion is inappropriate.
Target sample size	350

Research contact person
Name of lead principal investigator	1st name Masashi Middle name Last name Misawa
Organization	Showa University Northern Yokohama Hospital
Division name	Digestive Disease Center
Zip code	2248503
Address	Chigasaki-chuo 35-1, Tsuduki, Yokohama
TEL	045-949-7000
Email	mmisawa@med.showa-u.ac.jp

Public contact
Name of contact person	1st name Masashi Middle name Last name Misawa
Organization	Showa University Northern Yokohama Hospital
Division name	Digestive Disease Center
Zip code	2248503
Address	Chigasaki-chuo 35-1, Tsuduki, Yokohama
TEL	045-949-7000
Homepage URL
Email	mmisawa@med.showa-u.ac.jp

Sponsor
Institute	Showa University Northern Yokohama Hospital
Institute
Department

Funding Source
Organization	Japan Society for the Promotion of Science
Organization
Division
Category of Funding Organization	Japanese Governmental office
Nationality of Funding Organization

Other related organizations
Co-sponsor
Name of secondary funder(s)

IRB Contact (For public release)
Organization	Showa University Northern Yokohama Hospital
Address	Chigasaki-chuo 35-1, Tsuduki, Yokohama
Tel	045-949-7000
Email	irb02syh@ofc.showa-u.ac.jp

Secondary IDs
Secondary IDs	NO
Study ID_1
Org. issuing International ID_1
Study ID_2
Org. issuing International ID_2
IND to MHLW

Institutions
Institutions

Other administrative information
Date of disclosure of the study information	2021 Year 12 Month 25 Day

Related information
URL releasing protocol
Publication of results	Unpublished

Result
URL related to results and publications
Number of participants that the trial has enrolled
Results
Results date posted
Results Delayed
Results Delay Reason
Date of the first journal publication of results
Baseline Characteristics
Participant flow
Adverse events
Outcome measures
Plan to share IPD
IPD sharing Plan description

Progress
Recruitment status	Completed
Date of protocol fixation	2021 Year 05 Month 25 Day
Date of IRB	2021 Year 06 Month 30 Day
Anticipated trial start date	2021 Year 07 Month 01 Day
Last follow-up date	2022 Year 03 Month 31 Day
Date of closure to data entry
Date trial data considered complete
Date analysis concluded

Other

Other related information

Patients will undergo endoscopy using conventional endoscopy procedures. When the endoscopist finds a lesion, endoscopist uses WLI, NBI,and chromoendoscopy observation to diagnose the lesion. A still image is taken during NBI observation then the image is analyzed by the AI and output pathological prediction (adenoma, hyperplastic, and SSL) with percentage. It is recommended that the endoscopists take a minimum of five still images from a single lesion. The results will be stored and recorded by the endoscopits/medical stuff. Based on the endoscopist's diagnosis, the lesion will be resected on the same day or at a later date, and a pathological diagnosis will be made. If the results of the pathological diagnosis are inconsistent with the results of the endoscopic diagnosis made by the physician with a high degree of confidence, the physician should consult with the pathologist and consider re-cutting the pathological specimen. The outcomes will be calculated by comparing AI diagnosis and pathological diagnosis. After the examination, the physician will record the location, lesion diameter, morphology, endoscopic diagnosis, and AI results of the discovered lesion using our endoscopic filing system (Solemio Quev). Physicians participating in the study will be given a lecture on the use of NBI-CAD, and will be included in the study after performing at least five examinations using the system. Patients enrollment will be finished if the number of resected diminutive adenoma reached 241.

Management information
Registered date	2021 Year 05 Month 28 Day
Last modified on	2022 Year 11 Month 28 Day

Link to view the page
URL(English)	https://center6.umin.ac.jp/cgi-open-bin/icdr_e/ctr_view.cgi?recptno=R000050671