Modelling outcomes after paediatric brain injury with admission laboratory values: a machine-learning approach.

Journal: Pediatric research
PMID: 31349360

Abstract

BACKGROUND: Severe traumatic brain injury (TBI) is a leading cause of mortality in children, but the accurate prediction of outcomes at the point of admission remains very challenging. Admission laboratory results are a promising potential source of prognostic data, but have not been widely explored in paediatric cohorts. Herein, we use machine-learning methods to analyse 14 different serum parameters together and develop a prognostic model to predict 6-month outcomes in children with severe TBI.

Authors

  • Saeed Kayhanian
    Department of Clinical Neurosciences, Division of Neurosurgery, Addenbrooke's Hospital, University of Cambridge, Cambridge, UK. sk776@cam.ac.uk.
  • Adam M H Young
    Department of Clinical Neurosciences, Division of Neurosurgery, Addenbrooke's Hospital, University of Cambridge, Cambridge, UK.
  • Chaitanya Mangla
    Fitzwilliam College, University of Cambridge, Cambridge, UK.
  • Ibrahim Jalloh
    Department of Clinical Neurosciences, Division of Neurosurgery, Addenbrooke's Hospital, University of Cambridge, Cambridge, UK.
  • Helen M Fernandes
    Department of Clinical Neurosciences, Division of Neurosurgery, Addenbrooke's Hospital, University of Cambridge, Cambridge, UK.
  • Matthew R Garnett
    Department of Clinical Neurosciences, Division of Neurosurgery, Addenbrooke's Hospital, University of Cambridge, Cambridge, UK.
  • Peter J Hutchinson
    NIHR Global Health Research Group on Acquired Brain and Spine Injury.
  • Shruti Agrawal
    Department of Paediatric Intensive Care, Addenbrooke's Hospital, University of Cambridge, Cambridge, UK.

Keywords

External Resources

Popular Topics
Recent Journals