UMIN-CTR Clinical Trial

Basic information
Public title	Creation of an automatic diagnosis system for endoscopic images of esophageal disease using artificial intelligence
Acronym	Creation of an automatic diagnosis system for endoscopic images of esophageal disease using artificial intelligence
Scientific Title	Creation of an automatic diagnosis system for endoscopic images of esophageal disease using AI
Scientific Title:Acronym	Creation of an automatic diagnosis system for endoscopic images of esophageal disease using AI
Region	Japan

Condition
Condition	Esophageal diseases (such as esophageal malignant tumors, leiomyomas, neuroendocrine tumors, granuloma, reflux esophagitis, and eosinophilic esophagitis) and normal esophagus
Classification by specialty	Hepato-biliary-pancreatic medicine
Classification by malignancy	Malignancy
Genomic information	NO

Objectives
Narrative objectives1	To create an automatic diagnosis system for endoscopic images of esophageal disease using artificial intelligence (AI)
Basic objectives2	Efficacy
Basic objectives -Others
Trial characteristics_1
Trial characteristics_2
Developmental phase

Assessment
Primary outcomes	Diagnosis accuracy of various esophageal diseases using AI diagnostic system
Key secondary outcomes	Diagnosis sensitivity, specificity, positive predictive value, negative predictive value of various esophageal diseases using AI diagnostic system. Time required for diagnosis. Doctor's diagnostic accuracy, sensitivity, specificity, positive predictive value, negative predictive value

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	20 years-old <=
Age-upper limit	Not applicable
Gender	Male and Female
Key inclusion criteria	Esophageal diseases (such as esophageal malignant tumors, leiomyomas, neuroendocrine tumors, granuloma, reflux esophagitis, and eosinophilic esophagitis) and endoscopic images of normal esophagus (images / movies)
Key exclusion criteria	When the patient reject to use existing information through an information disclosure document published on the homepage of the facility.
Target sample size	5000

Research contact person
Name of lead principal investigator	1st name Ryu Middle name Last name Ishihara
Organization	Osaka International Cancer Institute.
Division name	Gastrointestinal Oncology
Zip code	541-8567
Address	1-69 Otemae 3-chome, Chuo-ku, Osaka541-8567, Japan
TEL	06-6945-1181
Email	ryu1486@gmail.com

Public contact
Name of contact person	1st name Kotaro Middle name Last name Waki
Organization	Osaka International Cancer Institute
Division name	Gastrointestinal Oncology
Zip code	541-8567
Address	1-69 Otemae 3-chome, Chuo-ku, Osaka541-8567, Japan
TEL	06-6945-1181
Homepage URL
Email	waki-ko@mc.pref.osaka.jp

Sponsor
Institute	Osaka International Cancer Institute Gastrointestinal Oncology
Institute
Department

Funding Source
Organization	Tada Tomohiro AI Endoscopic Diagnostic System Verification Fund
Organization
Division
Category of Funding Organization	Profit organization
Nationality of Funding Organization	Japan

Other related organizations
Co-sponsor	Tada Tomohiro Institute of Gastroenterology and Proctology Nigata University Graduate School of medical and Dental Science Department of Gastroenterology, Fukuoka University hospital AI Medical Service Inc. Department of Gastroenterology and Hepatology, Kumamoto University Hospital Department of Gastroenterology and Hepatology, Kumamoto chuo hospital Department of Gastroenterology and Hepatology,Keio University Hospital Department of Endoscopic Medicine, Mie University Hospital Department of Gastroenterology and Hepatology, Okayama University Graduate School of Medicine
Name of secondary funder(s)

IRB Contact (For public release)
Organization	Osaka International Cancer Institute, Ethics Committee
Address	1-69 Otemae 3-chome, Chuo-ku, Osaka541-8567, Japan
Tel	06-6945-1181
Email	rinri01@opho.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	2020 Year 03 Month 30 Day

Related information
URL releasing protocol
Publication of results	Published

Result
URL related to results and publications	https://onlinelibrary.wiley.com/doi/10.1111/den.13934
Number of participants that the trial has enrolled	21
Results	We prepared 100 video datasets, including 50 superficial ESCCs, 22 noncancerous lesions, and 28 normal esophagi. The AI system had sensitivity of 85.7% (54 of 63 ESCCs) and specificity of 40%. Initial evaluation by endoscopists conducted with plain video (without AI support) had average sensitivity of 75.0% (47.3 of 63 ESCC) and specificity of 91.4%.
Results date posted	2021 Year 03 Month 01 Day
Results Delayed
Results Delay Reason
Date of the first journal publication of results	2021 Year 01 Month 27 Day
Baseline Characteristics
Participant flow
Adverse events
Outcome measures
Plan to share IPD
IPD sharing Plan description

Progress
Recruitment status	Completed
Date of protocol fixation	2018 Year 12 Month 18 Day
Date of IRB	2018 Year 12 Month 18 Day
Anticipated trial start date	2018 Year 12 Month 18 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

Design: Multicenter observational study From the electronic medical record system and the endoscopic image server, the diagnosis information, the treatment information, and the endoscopic images of the patient having the esophageal disease are extracted after the anonymization processing. Similarly, it is extracted after the anonymization processing of the diagnosis information of the patient having the normal esophagus and the endoscopic images. Upload the extracted information and images to the server of AI medical service, which is responsible for developing the AI diagnostic system. AI medical service educates AI about 90% of the images classified by diagnosis name, and uses the remaining 10% of the images as verification images to evaluate the diagnostic accuracy of the AI diagnosis system for esophageal disease. We have the doctors who actually work in endoscopic practice diagnose the images and videos collected in our hospital after anonymization processing and compare them with the diagnostic accuracy of AI.

Management information
Registered date	2020 Year 02 Month 29 Day
Last modified on	2021 Year 03 Month 01 Day

Link to view the page
URL(English)	https://upload.umin.ac.jp/cgi-open-bin/icdr_e/ctr_view.cgi?recptno=R000045218