Utilising routinely collected clinical data through time series deep learning to improve identification of bacterial bloodstream infections: a retrospective cohort study.

Journal: The Lancet. Digital health
PMID: 40015765

Abstract

BACKGROUND: Blood cultures are the gold standard for diagnosing bacterial bloodstream infections, but test results are only available 24-48 h after sampling. We aimed to develop and evaluate models using health-care data to predict bloodstream infections in patients admitted to hospital.

Authors

  • Damien K Ming
    Centre for Antimicrobial Optimisation, Imperial College London, England.
  • Vasin Vasikasin
    Centre for Antimicrobial Optimisation, Imperial College London, London, UK; Department of Internal Medicine, Phramongkutklao Hospital and College of Medicine, Bangkok, Thailand.
  • Timothy M Rawson
    National Institute for Health Research Health Protection Research Unit in Healthcare Associated Infections and Antimicrobial Resistance, Imperial College London, London, UK.
  • Pantelis Georgiou
  • Frances J Davies
    Healthcare Protection Research Unit in Healthcare Associated Infections, Imperial College London, London, UK; Imperial College Healthcare NHS Trust, London, UK.
  • Alison H Holmes
    Health Protection Unit in Healthcare Associated infections and Antimicrobial Resistance, Imperial College London, 8th floor Commonwealth Building, Hammersmith Hospital Campus, Acton, London, W12 0NN, UK.
  • Bernard Hernandez
    Centre for Bio-Inspired Technology, Department of Electrical and Electronic Engineering, Imperial College London, B422 Bessemer Building, South Kensington Campus, London, SW7 2AZ, UK. b.hernandez-perez@imperial.ac.uk.

Keywords

External Resources

Popular Topics
Recent Journals