Pathology Artificial-Intelligence Clinical Evaluation Study (PACES)

  • Research type

    Research Study

  • Full title

    A clinical utility study investigating the integration of machine learning algorithms into the colorectal cancer care pathway, from histopathology to the clinical multidisciplinary team.

  • IRAS ID

    333259

  • Contact name

    University of Oxford Research Governance, Ethics and Ass

  • Contact email

    rgea.sponsor@admin.ox.ac.uk

  • Sponsor organisation

    University of Oxford / Research Governance, Ethics and Assurance

  • Clinicaltrials.gov Identifier

    N/A, N/A

  • Duration of Study in the UK

    2 years, 0 months, 1 days

  • Research summary

    PACES aims to assess if algorithms may predict, support, influence or change decisions made between patients and their doctors on treatment options for bowel cancer. No patient’s treatment plan will change as a result of participation in PACES.
    Adults with suspected or confirmed bowel who are scheduled for further examinations or treatments can participate. Potential participants will be invited to join the study before or during standard of care appointments via invitation letters containing a website link. Online, potential participants can view all study information, and ask any questions they may have. Consent and registration will be completed online.
    During bowel cancer diagnosis and treatment, doctors routinely take samples to be analysed in a laboratory, to help inform decisions on treatment. Importantly, no additional samples will be taken from patients wanting to take part in PACES. For participants, some samples will be sent from the hospital to laboratories based in Oxford after NHS processing. Here, images of the samples will be scanned into a computer so algorithms can analyse them.
    Teams of doctors and cancer specialists regularly meet to discuss treatment options for patients. This is known as a multidisciplinary team meeting and will take place without feedback from the algorithms. The patient’s doctor will then discuss the patient’s options during a follow-up appointment, and together they will decide on a treatment plan, as would normally happen.
    Only when a treatment plan has been made will algorithm results be sent to the participant’s doctor. The doctor will then complete a questionnaire assessing if their treatment recommendation would have changed, had algorithm results been provided earlier. Participants will also be asked to complete a questionnaire, investigating opinions on the use of AI in cancer treatment and diagnosis. Clinicians and pathologists involved in the case will also be invited to complete questionnaires.

  • REC name

    South Central - Oxford C Research Ethics Committee

  • REC reference

    24/SC/0165

  • Date of REC Opinion

    16 Jul 2024

  • REC opinion

    Further Information Favourable Opinion