Method for extracting pre-defined data items from medical service records generated by health care providers

• US 5,664,109 A
• Filed: 06/07/1995
• Issued: 09/02/1997
• Est. Priority Date: 06/07/1995
• Status: Expired due to Fees

• Current Assignee: Raytheon Company (Rtx Corporation)
• Original Assignee: E-Systems Incorporated (Rtx Corporation)
• Inventors: Campbell, Kelly Scott, Johnson, Gary Duane
• Primary Examiner(s): Black, Thomas G.
• Assistant Examiner(s): HOMERE, JEAN RAYMOND
• Application Number:
  US08/483,469
• Time in Patent Office: 818 Days
• Field of Search: 395/603, 395/202, 395/203, 395/204, 395/924, 395/610, 395/602, 395/791, 395/54, 364/DIG. 1
• US Class Current: 705/2
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/20 for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
• CPC Class Codes: G16H 70/60 relating to pathologies
• CPC Class Codes: Y10S 706/924 Medical
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99939 Privileged access

Abstract

A central medical record repository for a managed health care organization accepts and stores medical record documents in any format from medical service providers. The repository then identifies the document using information automatically extracted from the document and stores the extracted data in a document database. The repository links the document to a patient by extracting from the document demographic data identifying the patient and matching it to data stored in a patient database. Data is extracted automatically from medical records containing "unstructured" or free-form text by identifying conventional organization components in the text and is organized by executing rules that extract data with the aid of such information. Documents for a patient are retrieved by identifying the patient using demographic data.

Claims

1. A method of extracting a pre-defined data item from unstructured medical service records stored in a central data processing system and generated by a plurality of service providers, comprising the steps of:

storing the unstructured medical service records in a database of the central data processing system for a plurality of individuals having previously sought or received services from at least one of a plurality of service providers, each unstructured medical service record contains a plurality of spatially-organized groupings of unfielded and free form text;

identifying each spatially-organized grouping as one of a plurality of structural element designations using a rules-based application predicated at least in part on the structural element designations and a document type associated with a particular service provider; and

extracting the pre-defined data item from one of the plurality of spatially-organized groupings by executing the rules-based application.

2. The method of claim 1 wherein the step of identifying the spatially-organized groupings further includes identifying one of the plurality of generic structural element designations from the group header, title, subject, footer and a plurality of body sections.

3. The method of claim 1 wherein the step of extracting the pre-defined data item includes identifying medically relevant data, demographic information and a medical record number associated with the individual.

4. The method of claim 1 wherein the step of extracting the pre-defined data item further includes developing rules utilized by the rule-based application from information provided by the service providers or a previous unstructured medical service record.

5. The method of claim 1 further comprising the step of forming a TAG file including:

developing generic terms indicative of the structural element designations;

inserting the extracted pre-defined data items adjacent to the generic terms associated therewith; and

linking the TAG file to the medical service record.

6. The method of claim 5 wherein the step of extracting the pre-defined data item further includes:

obtaining rules from the rules-based application for extraction of the pre-defined data item from the unstructured medical service record;

executing the rules to obtain the pre-defined data item;

storing the acceptable pre-defined data item in the TAG file; and

linking the TAG file to the medical service record.

7. The method of claim 1 wherein the step of identifying each spatially-organized grouping includes the steps of:

removing stop words from the medical service record such that keywords remain in the medical service record;

storing the keywords in a keyword file; and

associating the keyword file to the medical service record.

8. The method of claim 1 wherein the step of identifying each of the spatially-organized groupings includes identifying the document type by utilizing the structural element designations.

9. The method of claim 1 further comprising:

creating a new medical service record associated with the medical service record in the database, said new medical service record includes a plurality of data fields;

populating the data fields of the new medical service record with the extracted pre-defined data; and

storing the new medical service record in a document repository using a document handle.

10. A method of extracting medically related information and demographic information from unstructured medical service records stored in a central data processing system and generated by a plurality of service providers, comprising the steps of:

storing the unstructured medical service records in a database of the central data processing system for a plurality of individuals having previously sought or received services from at least one of a plurality of service providers, each unstructured medical service record contains a plurality of spatially-organized groupings of unfielded and free form text;

identifying each spatially-organized grouping as one of a plurality of structural element designations using a rules-based application predicated at least in part on the structural element designations and a document type associated with a particular service provider;

developing rules utilized by the rule-based application from information provided by the service providers or a previous unstructured medical service record;

extracting the medically relevant information and demographic information from one of the plurality of spatially-organized groupings by executing the rules-based application;

creating a new medical service record associated with the medical service record in the database, said new medical service record includes a plurality of data fields;

populating the data fields of the new medical service record with the extracted pre-defined data; and

storing the new medical service record in a document repository using a document handle.

11. A method of extracting pre-defined data items from unstructured medical service records stored in a central data processing system and generated by a plurality of service providers, comprising the steps of:

storing the unstructured medical service records in a database of the central data processing system for a plurality of individuals having previously sought or received services from at least one of a plurality of service providers, each unstructured medical service record contains a plurality of spatially-organized groupings including a header, title, subject, footer and a plurality of body sections;

identifying each spatially-organized grouping as one of a plurality of structural element designations using a rules-based application predicated at least in part on the structural element designations and a document type associated with a particular service provider;

developing rules utilized by the rule-based application from information provided by the service providers or a previous unstructured medical service record; and

extracting the pre-defined data item from one of the plurality of spatially-organized groupings by executing the rules-based application.