AI in COVID-19 [COVID-19]

  • Research type

    Research Study

  • Full title

    AI-assisted diagnosis and prognostication in COVID-19

  • IRAS ID

    282705

  • Contact name

    Evis Sala

  • Contact email

    es220@cam.ac.uk

  • Sponsor organisation

    Cambridge University Hospitals NHS Foundation Trust and The University of Cambridge

  • Duration of Study in the UK

    4 years, 11 months, 30 days

  • Research summary

    In December 2019 the first cases of a novel coronavirus infection in humans causing pneumonia were recorded in the Chinese city of Wuhan (1). Since then, the virus has been renamed SARS-CoV-2 (Severe Acute Respiratory Syndrome- Coronavirus 2) and its point of entry into the cell, the Angiotensin Converting Enzyme 2 (ACE2) receptor identified (2). Air travel from Wuhan has accelerated the worldwide spread of SARS-CoV 2 infections (Coronavirus Disease 2019 (COVID-19)), leading to an exponential growth in case numbers.\nCT is a widely available, cost-effective, and safe imaging tool, and plays a vital role in the diagnosis of viral pneumonia and recently in the diagnosis of COVID19. Recently, research into computer-assisted image analysis such as machine learning has highlighted the potential of objective image analysis beyond visual assessment in lung imaging\n\nIn this study we plan to retrospectively evaluate pseudo-anonymised imaging (x-ray and CT) of patients admitted for diagnostic workup of suspected respiratory infection.\nWe believe that, machine learning-assisted assessment of integrated imaging, clinical and laboratory data enables improved multi-parametric -based diagnostic and risk stratification accuracy in patients with respiratory infection/COVID-19. \nThis study will last for three years. [Study relying on COPI notice]

  • REC name

    London - Brent Research Ethics Committee

  • REC reference

    20/HRA/2504

  • Date of REC Opinion

    5 Jun 2020

  • REC opinion

    Further Information Favourable Opinion