Confirm that cOlon Neoplasm Finely can be IDENTIfied by AI without overLooking; CONFIDENTIAL study

Confirm that cOlon Neoplasm Finely can be IDENTIfied by AI without overLooking; CONFIDENTIAL study - CONFIDENTIAL study

Status

Active, not recruiting

Phases

Unknown

Study type

Observational

Source

JPRN

Registry ID

JPRN-UMIN000045456

Enrollment

100

Registered

2021-09-11

Start date

2021-09-11

Completion date

Unknown

Last updated

2026-06-29

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Suspected colorectal tumor (including colorectal adenoma)

Interventions

None listed

Eligibility

Sex/Gender

All

Inclusion criteria

Inclusion criteria: (1) Patients who undergo colonoscopy without a history of colonoscopy for more than 3 years at the research facility (2) Patients who can perform preparation as usual

Exclusion criteria

Exclusion criteria: (1) Emergency endoscopy case (2) Patients with a history of colectomy or severe adhesions of colon are known in advance (3) Patients with chronic bowel disease such as inflammatory bowel disease (4) Patients with poor preparation (5) Patients judged inappropriate by the doctor in charge of this study

Design outcomes

Primary

Measure	Time frame
Comparison of overall adenoma lesion detection rate (ADR) between endoscopists and Artificial Intelligence	—

Secondary

Measure	Time frame
(1) Comparison of the number of adenomas per case (adenomas / number of cases) between endoscopists and Artificial Intelligence (2) Comparison of ADR between specialists and non-specialists (including residents) (3) Comparison of the number of adenomas per case between specialists and non-specialists (including residents)	—

Countries

Japan

Contacts

Public ContactKazuhiro Mizukami

Oita University, Faculty of medicine Department of Gastroenterology

mizkaz0809@oita-u.ac.jp097-586-6193

Outcome results