Session ID: 

Identification of Rare Events in Narrative EHR Data

10:00am - 11:00am Thursday, February 14
Orlando - Orange County Convention Center


Even with near universal adoption of electronic medical records in the U.S., a large fraction of clinical data "locked”-in narrative electronic documents remains inaccessible for analysis and utilization in population management, quality improvement and clinical research. A number of different technologies, collectively known as natural language processing, have been developed for extraction of information from narrative data. However, it is not known how to choose between these technologies and under what circumstances one may work better than another. This speaker will describe a comparison between several widely used technologies for an important use case (identification of rare events in narrative EHR data) on the example of rejection of insulin therapy by patients with diabetes.

Learning Objectives: 

  • Explain importance of identification of rare clinical events in EMR data
  • Define different technologies that can be used to extract information from narrative electronic documents
  • Compare efficacy of natural language processing technologies for identification of rare clinical events
  • Discuss reasons for differences in performance between natural language processing technologies


Associate Professor of Medicine,
Brigham and Women's Hospital...


Clinical Informaticists
IT Professional
Population Health Management Professional