The SHARPn project on secondary use of Electronic Medical Record data: progress, plans, and possibilities. Academic Article uri icon


MeSH Major

  • Data Mining
  • Electronic Health Records
  • Natural Language Processing
  • Software


  • SHARPn is a collaboration among 16 academic and industry partners committed to the production and distribution of high-quality software artifacts that support the secondary use of EMR data. Areas of emphasis are data normalization, natural language processing, high-throughput phenotyping, and data quality metrics. Our work avails the industrial scalability afforded by the Unstructured Information Management Architecture (UIMA) from IBM Watson Research labs, the same framework which underpins the Watson Jeopardy demonstration. This descriptive paper outlines our present work and achievements, and presages our trajectory for the remainder of the funding period. The project is one of the four Strategic Health IT Advanced Research Projects (SHARP) projects funded by the Office of the National Coordinator in 2010.

publication date

  • December 2011



  • Academic Article



  • eng

PubMed Central ID

  • PMC3243296

PubMed ID

  • 22195076

Additional Document Info

start page

  • 248

end page

  • 56


  • 2011