The application of unsupervised deep learning in predictive models using electronic health records.

Journal: BMC medical research methodology
Published Date:

Abstract

BACKGROUND: The main goal of this study is to explore the use of features representing patient-level electronic health record (EHR) data, generated by the unsupervised deep learning algorithm autoencoder, in predictive modeling. Since autoencoder features are unsupervised, this paper focuses on their general lower-dimensional representation of EHR information in a wide variety of predictive tasks.

Authors

  • Lei Wang
    Department of Nursing, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, China.
  • Liping Tong
    Advocate Aurora Health, 3075 Highland Parkway, Downers Grove, IL, 60515, USA. liping.tong@advocatehealth.com.
  • Darcy Davis
    Advocate Aurora Health, 3075 Highland Parkway, Downers Grove, IL, 60515, USA.
  • Tim Arnold
    Cerner Corporation, 2800 Rockcreek Parkway, North Kansas City, MO, 64117, USA.
  • Tina Esposito
    Advocate Aurora Health, 3075 Highland Parkway, Downers Grove, IL, 60515, USA.