Discovering patient groups in sequential electronic healthcare data using unsupervised representation learning.

Journal: BMC medical informatics and decision making
PMID:

Abstract

INTRODUCTION: Unsupervised feature learning methods inspired by natural language processing (NLP) models are capable of constructing patient-specific features from longitudinal Electronic Health Records (EHR).

Authors

  • Jingteng Li
    Great Ormond Street Institute of Child Health, University College London, London, UK.
  • Kimberley R Zakka
    Great Ormond Street Institute of Child Health, University College London, London, UK.
  • John Booth
    Great Ormond Street Hospital, Great Ormond Street Hospital Institute of Child Health and NIHR GOSH BRC, London, UK.
  • Louise Rigny
    Data Research Innovation and Virtual Environment, Great Ormond Street Hospital for Children, London, UK.
  • Samiran Ray
    Great Ormond Street Institute of Child Health, University College London, London, UK.
  • Mario Cortina-Borja
    Great Ormond Street Institute of Child Health, University College London, London, UK.
  • Payam Barnaghi
    Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, United Kingdom.
  • Neil Sebire
    Health Data Research UK, London, UK.