CAP-AI

  • Research type

    Research Study

  • Full title

    Prediction of outcome in community acquired pneumonia admissions using artificial intelligence

  • IRAS ID

    266731

  • Contact name

    Cat Taylor

  • Contact email

    rgosponsor@le.ac.uk

  • Sponsor organisation

    University of Leicester

  • Duration of Study in the UK

    5 years, 0 months, 1 days

  • Research summary

    Pneumonia and flu caused 269,313 emergency hospital admissions in the UK in 2016/17 which cost the NHS an estimated £1 billion. Community acquired pneumonia (CAP) is the leading cause of death in NHS hospitals. Mortality associated with CAP admissions varies between 2% and 30% depending on disease severity, comorbities and age, and prompt interventions are associated with significantly improved outcome. Disease management according to agreed guidelines modifies outcome but it is unknown whether evaluation of other routinely collected parameters at the point of admission would improve treatment outcome further. Even small improvements in CAP outcome would potentially be of enormous benefit to large numbers of NHS patients. In Leicester between financial year 2011-2016 there were 13,496 CAP admissions, of which 16.6% died in-hospital.

    The CAP-AI project will use routinely collected health care data and apply modern artificial intelligence (AI) techniques to create models which could be used to help hospital staff deal with patients admitted with CAP. These techniques are showing great promise over more traditional statistical techniques and other mathematical modelling approaches.

    It is believed that the resultant AI models will provide better, and potentially more accurate and individualised prediction of outcomes.

  • REC name

    West Midlands - Solihull Research Ethics Committee

  • REC reference

    20/WM/0144

  • Date of REC Opinion

    4 May 2020

  • REC opinion

    Favourable Opinion