×

Automated patient/document identification and categorization for medical data

  • US 8,751,495 B2
  • Filed: 09/28/2010
  • Issued: 06/10/2014
  • Est. Priority Date: 09/29/2009
  • Status: Active Grant
First Claim
Patent Images

1. A method, comprising:

  • receiving a data source selection from a user or software application, the data source including medical information of a plurality of patients;

    receiving, from the user or software application, a data pattern that is related to a concept to be explored in the data source;

    querying the data source to find information that approximately matches the data pattern; and

    receiving the information from the data source, wherein the information includes unstructured data, assigning a classification to individual parts of the information based on the part'"'"'s relationship to the data pattern; and

    outputting the classified information, including the unstructured data as a table including a classification label and a passage header columns, to the user or software application, the passage column being of the unstructured data separated into the individual parts, the unstructured data of the passage column comprising fragment passages that are one or more sentences, one or more clauses, or one or more sentences and clauses, which include a query term and surrounding text, and the classification label indicating positive or negative or not applicable to support of corresponding passages of the passage column andwherein the method is performed using a processor.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×