Background:

Colonoscopy is accepted to be the gold standard for screening of colorectal cancer (CRC). Most CRCs develop from adenomatous polyps, with colonoscopy accepted to be the gold standard for screening of CRC. An endoscopist's ability to detect polyps is assessed in the form of an Adenoma Detection Rate (ADR). Each 1.0% increase in ADR is associated with a 3.0% decrease in the risk of the patient developing an interval CRC. There remains a wide variation in endoscopist ADR.

More recently, the use of artificial intelligence (AI) and computer aided diagnosis in endoscopy has been gaining increasing attention for its role in automated lesion detection and characterisation. AI can potentially improve ADR, but previous AI related work has largely focused on retrospectively assessing still endoscopic images and selected video sequences which may be subject to bias and lack clinical utility. There are only limited clinical studies evaluating the effect of AI in improving ADR.

The CADDIE device uses convolutional neural networks developed for computer assisted detection and computer assisted diagnosis of polyps.

Primary objective: To determine whether the CADDIE artificial intelligence system improves endoscopic detection of adenomas during colonoscopy.

Primary endpoint: The difference in adenoma detection rate (ADR) between the intervention (supported with the CADDIE system) and non-intervention arm

Study design: Multi-Centre, open-label, randomised, prospective trial to assess efficacy and safety of the CADDIE artificial intelligence system for improving endoscopic detection of colonic polyps in real-time.

Inclusion Criteria:

• Patient's scheduled to undergo a surveillance or symptomatic colonoscopy with an endoscopist participating in the study phase of the trial.
• Male and female participants aged 18 years or older at the time of informed consent.
• Patient's able to comprehend, sign and date the written informed consent document to participate in the study.

Exclusion Criteria:

• Emergency colonoscopies and/or inpatient colonoscopies.

• Patients with inflammatory bowel disease (IBD)

• Patients with Colorectal Cancer (CRC)

• Patients with previous CRC

• Patients with previous colonic resection

• Patients returning for a planned elective therapeutic colonoscopy.

• Polyposis syndromes

• Current or relevant history of a physical or psychiatric illness or any medical condition that in the opinion of the investigator could affect the patient's safety or interfere with the study assessments

• Patients with a contraindication for biopsy or polypectomy. These include:

  • Patients who have not withheld medications pre-disposing to bleeding at time of colonoscopy as per local site /national guidelines 30.
  • Patients with a history of haemostasis disorders (Haemostasis disorders will include but will not be limited to: patients with haemophilia or other congenitally acquired clotting factor deficiencies, patients with cirrhosis with coagulopathy, patients known to have thrombocytopenia (<80,000 platelet/ul) and individuals with Von Willebrand's disease or other known platelet malfunction disorders).

• Patients is enrolled in another research study with an investigational medicinal product (IMP) or non-IMP that pre-disposes them to bleeding

Study population will include patient's scheduled to undergo a surveillance or symptomatic colonoscopy at the participating sites.

Patients will be asked informed consent with the possibility to share the data

Data will be made available from 1 year after the trial findings are published. This is available for up to 5 years after study completion.

We will make provision for and consider data sharing requests from bona fide researchers who must abide by the following principles: data will be collected with an high level of quality assurance, data will be held securely with appropriate documentation, data will not be put into the public domain or otherwise shared without explicit ethical review or legal obligation, and they will aim to use any data generated to the maximum public good. These datasets are governed by data usage policies specified by the data controller (UCL). If a conflict exists that severely restricts the analyses that can be undertaken, we would endeavour to support outside researchers by hosting them as visiting workers in our team so that they can access the data. We are committed to complying with the Wellcome Trust Data Sharing Policy. Applications are subject to review by Prof Lovat and Rawen Kader and should be emailed to l.lovat@ucl.ac.uk

Adverse events were recorded for 30 days post-procedure