Automating the Classification of Medical Record Documents

Scanning and indexing medical records is a time consuming task exacerbated by the sheer number of document types that exist in a healthcare facility, and the requirement to classify each document to its specified type to a patient’s chart.  Several technologies exist to automate this process and eliminate the manual assignment of document types.

Content Recognition Software

Content recognition is an emerging technology used successfully for medical record document indexing and classification.  This technology mines the entire typed content on the document opposed to using specific field extraction, template forms, form IDs, or bar codes to identify and classify the document type.


The Benefits of Content Recognition Software

  • Content is consistent for document types regardless of their source (i.e. a lab result will contain the same relative content whether it is coming from Lab ABC or Lab XYZ)
  • There is no requirement to change any of the existing document forms; the technology works with all existing forms
  • The technology can be “trained” to identify and classify new document types based on the content contained which works well for outside documents received from new sources
  • The content recognition technology quickly adapts to new forms for new facilities, which makes it a perfect solution to use in a centralized scanning center that supports multiple healthcare facilities

In part two of this article, learn about the advantages and disadvantages of two other methods of automating document classification.

Request More Information

Back to top