Artificial Intelligence Performance in Colonoscopy in Daily Practice


randomised, controlled single center, single investigator study mainly in colorectal screening population in daily practice with and without artificial intelliegence (AI) named DiscoveryTM from Pentax medical.Patient randomly are allocated to one of four groups: Pentax i10 colonoscopes without any additional divice, Pentax i 10 with DiscoveryTM (AI), Pentax i 10 with EndocuffTM and Pentax i10 with EndocuffTM and DiscoveryTM (AI). The different groups are compared in terms of the different parameters: e.g. time of endoscopy, polyps (PDR) and adenoma detected (ADR).

Full Title of Study: “Artificial Intelligence Performance in Colonoscopy in Daily Practice: Randomised, Comparative Study of Pentax i10 Colonoscopes With or Without Endocuff Combined With Discovery™ or Without”

Study Type

  • Study Type: Interventional
  • Study Design
    • Allocation: Randomized
    • Intervention Model: Single Group Assignment
    • Primary Purpose: Diagnostic
    • Masking: None (Open Label)
  • Study Primary Completion Date: July 31, 2022

Detailed Description

From August 2021 through August 2022 all patients undergoing a colonoscopy in a gastroenterologist's private practice are assigned using randomization tables to one or the other above mentioned groups. Time of the endoscopy (ascent, descent and intervention time), polyps detected and there histology are written down real time with a tablet computer anonymized with the patient number. Furthermore dosage of sedatives and over all satisfaction is traced. 1. endpoint is time gain of each phase of the colonoscopy 2. endpoint is adenoma detetcion rate (ADR)


  • Device: Discovery TM of Pentax medical on/off in colonoscopy
    • on the monitor artificial integlligence Discovery can be switched on or off.

Arms, Groups and Cohorts

  • No Intervention: Pentax i 10
    • Patient gets normal colonoscopy without Endocuff or activation of artifical intelligence
  • Active Comparator: Pentax i 10 with artificial intelligence Discovery TM
    • Normal Pentax i 10 colonoscope with on the specital monitor acitvated artificial intelligence
  • Other: Pentax i 10 with Endocuff TM
    • Normal Pentax i 10 instrument with Endocuff (cheap cap on the tip of the endosope) showed in former studies high performence with high ADR
  • Active Comparator: Pentax i 10 with Endocuff TM and artificial intelligence Discovery TM
    • Endocuff cap is mounted on the tip of the endoscope and artificial intelligence is activated on the monitor. hypothesis is that probabely artificial intelligence and Endocuff combined potentiate theire effect.

Clinical Trial Outcome Measures

Primary Measures

  • Endoscopy time
    • Time Frame: within 45 minutes of examination
    • measurement of ascent, descent and intervention time during colonoscopy

Secondary Measures

  • polyp and adenoma detetction rate PDR and ADR
    • Time Frame: within 45 minutes of examination
    • counts of polpypes and theier location in the colon and theire histology

Participating in This Clinical Trial

Inclusion Criteria

all patient referred and fit for an ambulant colonoscopy Exclusion Criteria:


Gender Eligibility: All

Minimum Age: 15 Years

Maximum Age: N/A

Are Healthy Volunteers Accepted: No

Investigator Details

  • Lead Sponsor
    • Gastroenterologie Baden-Wettingen
  • Collaborator
    • Dominik J. Leiner Ludwig-Maximilians-Universität München, Institut für Kommunikationswi
  • Provider of Information About this Clinical Study
    • Principal Investigator: Geyer Martin, Dr med. Geyer Martin, Principal investigator – Gastroenterologie Baden-Wettingen

Clinical trials entries are delivered from the US National Institutes of Health and are not reviewed separately by this site. Please see the identifier information above for retrieving further details from the government database.

At, we keep tabs on over 200,000 clinical trials in the US and abroad, using medical data supplied directly by the US National Institutes of Health. Please see the About and Contact page for details.