Machine learning model for early prediction of acute kidney injury (AKI) in pediatric critical care.

Journal: Critical care (London, England)
Published Date: Aug 10, 2021

Abstract

BACKGROUND: Acute kidney injury (AKI) in pediatric critical care patients is diagnosed using elevated serum creatinine, which occurs only after kidney impairment. There are no treatments other than supportive care for AKI once it has developed, so it is important to identify patients at risk to prevent injury. This study develops a machine learning model to learn pre-disease patterns of physiological measurements and predict pediatric AKI up to 48 h earlier than the currently established diagnostic guidelines.

Authors

  • Junzi Dong
    Hearing Research Center and Department of Biomedical Engineering, Boston University , Boston, Massachusetts 02215.
  • Ting Feng
    Connected Care and Personal Health Team, Philips Research North America, 222 Jacobs Street, Cambridge, MA, 02141, USA.
  • Binod Thapa-Chhetry
    Connected Care and Personal Health Team, Philips Research North America, 222 Jacobs Street, Cambridge, MA, 02141, USA.
  • Byung Gu Cho
    Connected Care and Personal Health Team, Philips Research North America, 222 Jacobs Street, Cambridge, MA, 02141, USA.
  • Tunu Shum
    Department of Information Technology, Phoenix Children's Hospital, Phoenix, AZ, USA.
  • David P Inwald
    Paediatric Intensive Care Unit, Addenbrooke's Hospital, Cambridge, UK.
  • Christopher J L Newth
    Department of Anesthesiology and Critical Care Medicine, Children's Hospital Los Angeles, Los Angeles, CA, USA.
  • Vinay U Vaidya
    Department of Information Technology, Phoenix Children's Hospital, Phoenix, AZ, USA.

Keywords

External Resources

Popular Topics
Recent Journals