Artificial Intelligence in Image Recognition of Pouchoscopies in Patients With Restorative Proctocolectomy

NCT04864587 | Completed

• 1 other identifier: PouchVision1.0
• Study Type: observational
• Target: 500
• Locations: 1 country
• Sites: 1

Brief Summary

The application of artificial intelligence in pouchoscopy of patients with restorative proctocolectomy might improve the diagnosis of pouchitis and neoplasms. The aim of this pilot study is to develop a convolutional neural network algorithm for pouchoscopy

Conditions

Pouches, Ileoanal

Outcome Measures

Primary Outcomes (2)

• AI versus endoscopist

  Detection of pouchitis by AI versus assessment by endoscopist in pouchoscopy

  Immediately after application of AI algorithm or after assessment of the endoscopic image by the endoscopist

• AI versus pathologist

  Detection of pouchitis by AI versus pathologist in pouchoscopy

  Immediately after application of AI algorithm or after assessment of the microscopic image of the pouch biopsy by the pathologist

Study Arms (1)

Restorative colectomy with ileoanal pouch

Patients with restorative colectomy with ileoanal pouch who receive pouchoscopy for detection of pouchitis or neoplasm

Diagnostic Test: Artificial intelligence used for image recognition in pouchoscopy

Interventions

Artificial intelligence used for image recognition in pouchoscopy DIAGNOSTIC_TEST

The aim of this study is to develop an image recognition algorithm that reliably detects the different graduations of pouch inflammation and neoplasms in the pouch

Restorative colectomy with ileoanal pouch

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Adult patients with inflammatory bowel disease and status after restorative proctocolectomy with ileoanal pouch might develop pouchitis or neoplasia in the pouch.

You may qualify if:

• All patients aged ≥ 18 years with inflammatory bowel disease and status after restorative proctocolectomy with ileoanal pouch who had received a pouchoscopy

You may not qualify if:

• Very poor endoscopic image quality

Sponsors & Collaborators

• Theresienkrankenhaus und St. Hedwig-Klinik GmbH: lead
• Universitätsmedizin Mannheim: collaborator

Study Sites (1)

Theresienkrankenhaus und St. Hedwigkliniken GmbH

Mannheim, Baden-Wurttemberg, 68165, Germany

Location

Related Publications (1)

• van der Sommen F, de Groof J, Struyvenberg M, van der Putten J, Boers T, Fockens K, Schoon EJ, Curvers W, de With P, Mori Y, Byrne M, Bergman JJGHM. Machine learning in GI endoscopy: practical guidance in how to interpret a novel field. Gut. 2020 Nov;69(11):2035-2045. doi: 10.1136/gutjnl-2019-320466. Epub 2020 May 11.

  PMID: 32393540 BACKGROUND

Study Officials

• Daniel Schmitz, PhD

  Theresienkrankenhaus Mannheim, University of Heidelberg

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: April 21, 2021
• First Posted: April 29, 2021
• Study Start: June 1, 2021
• Primary Completion: June 1, 2023
• Study Completion: June 1, 2023
• Last Updated: August 29, 2023

Record last verified: 2023-08

Data Sharing

• IPD Sharing: Will not share

Locations

DE (1)