ANICAD

  • Research type

    Research Study

  • Full title

    Automated Non-Invasive Coronary Artery Disease detection using Artificial Intelligence - ANICAD.

  • IRAS ID

    276543

  • Contact name

    Amedeo Chiribiri

  • Contact email

    amedeo.chiribiri@kcl.ac.uk

  • Sponsor organisation

    King's College London

  • Duration of Study in the UK

    0 years, 11 months, 30 days

  • Research summary

    Cardiac magnetic resonance imaging (CMR) is recognised as one of the imaging methods of choice to investigate the heart. A technique called stress perfusion CMR, which involves giving patients a medication to increase the blood flow to their heart muscle, is used to identify the diagnosis of chest pain. This allows the identification of coronary artery disease (CAD), as well as the narrowing of smaller blood vessels called microvascular disease (MVD). Stress perfusion CMR differentiates these diagnoses form other causes of chest pain such as structural changes of the heart (called cardiomyopathy) or inflammation of the heart muscle (called myocarditis).

    A dedicated team at King's College London and Guy's & St Thomas' NHS Foundation Trust have been involved in improving the diagnostic ability of stress perfusion CMR for the past decade. This research study is an extension of this work, in a bid to improve comparability of data between different scanners, repeatability of methods and accuracy of emerging techniques in stress perfusion CMR.

    This study invites patients who are already being investigated for suspected coronary artery disease via stress CMR to have a second comparable scan. This could be done in exactly the same way, or on a different scanner or with methods not previously used during clinical scanning. Overall, this would allow robust repeatability assessment of emerging techniques, as well as testing and validation of new techniques against existing methods used in clinical practice. The information from assessing these variables would form a cohort assessment of a wide variety of patients referred for stress perfusion CMR. This would be used to train a neural network and build towards a robust, automated, artificially-intelligent analysis tool for assessment of myocardial blood flow.

    Participation in the study is purely voluntary and all study data would be processed and stored anonymously to maintain patient confidentiality.

  • REC name

    North West - Haydock Research Ethics Committee

  • REC reference

    22/NW/0309

  • Date of REC Opinion

    16 Sep 2022

  • REC opinion

    Favourable Opinion