Predicting one-year outcome in first episode psychosis using machine learning.

Journal: PloS one
PMID: 30845268

Abstract

BACKGROUND: Early illness course correlates with long-term outcome in psychosis. Accurate prediction could allow more focused intervention. Earlier intervention corresponds to significantly better symptomatic and functional outcomes. Our study objective is to use routinely collected baseline demographic and clinical characteristics to predict employment, education or training (EET) status, and symptom remission in patients with first episode psychosis (FEP) at one-year.

Authors

  • Samuel P Leighton
    Institute of Health and Wellbeing, University of Glasgow, Glasgow, United Kingdom.
  • Rajeev Krishnadas
    Institute of Neuroscience and Psychology, University of Glasgow, Glasgow, United Kingdom.
  • Kelly Chung
    Institute of Health and Wellbeing, University of Glasgow, Glasgow, United Kingdom.
  • Alison Blair
    ESTEEM First Episode Psychosis Service, NHS Greater Glasgow and Clyde, Glasgow, United Kingdom.
  • Susie Brown
    ESTEEM First Episode Psychosis Service, NHS Greater Glasgow and Clyde, Glasgow, United Kingdom.
  • Suzy Clark
    ESTEEM First Episode Psychosis Service, NHS Greater Glasgow and Clyde, Glasgow, United Kingdom.
  • Kathryn Sowerbutts
    ESTEEM First Episode Psychosis Service, NHS Greater Glasgow and Clyde, Glasgow, United Kingdom.
  • Matthias Schwannauer
    Department of Clinical & Health Psychology, University of Edinburgh, Edinburgh, United Kingdom.
  • Jonathan Cavanagh
    Institute of Health and Wellbeing, University of Glasgow, Glasgow, United Kingdom.
  • Andrew I Gumley
    Institute of Health and Wellbeing, University of Glasgow, Glasgow, United Kingdom.

Keywords

External Resources

Popular Topics
Recent Journals