Assessing stroke severity using electronic health record data: a machine learning approach.

Journal: BMC medical informatics and decision making
Published Date:

Abstract

BACKGROUND: Stroke severity is an important predictor of patient outcomes and is commonly measured with the National Institutes of Health Stroke Scale (NIHSS) scores. Because these scores are often recorded as free text in physician reports, structured real-world evidence databases seldom include the severity. The aim of this study was to use machine learning models to impute NIHSS scores for all patients with newly diagnosed stroke from multi-institution electronic health record (EHR) data.

Authors

  • Emily Kogan
    Janssen Research & Development, LLC, Raritan, NJ, USA. ekogan@its.jnj.com.
  • Kathryn Twyman
    Janssen Research & Development, LLC, Raritan, NJ, USA.
  • Jesse Heap
    Janssen Research & Development, LLC, Raritan, NJ, USA.
  • Dejan Milentijevic
    Janssen Scientific Affairs, LLC, Titusville, NJ, USA.
  • Jennifer H Lin
    Janssen Scientific Affairs, LLC, Titusville, NJ, USA.
  • Mark Alberts
    Hartford HealthCare, Hartford, CT, USA.