Categorization of information using natural language processing and predefined templates

• US 8,185,553 B2
• Filed: 05/15/2008
• Issued: 05/22/2012
• Est. Priority Date: 03/31/2004
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Dictaphone Corporation (Microsoft Corporation)
• Inventors: Carus, Alwin B., Ogrinc, Harry J.
• Primary Examiner(s): Woo, Isaac M
• Application Number:
  US12/121,527
• Publication Number:
  US 20080255884A1
• Time in Patent Office: 1,468 Days
• Field of Search: 707600-831
• US Class Current: 707/791
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: Y10S 707/99942 Manipulating data structure, e.g. compression, compaction, compilation
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99944 Object-oriented database structure
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A computer implemented method for generating a report that includes latent information, comprising receiving an input data stream that includes latent information, performing one of normalization, validation, and extraction of the input data stream, processing the input data stream to identify latent information within the data stream that is required for generation of a particular report, wherein said processing of the input data stream to identify latent information comprises of identifying a relevant portion of the input data stream, bounding the relevant portion of the input data stream, classifying and normalizing the bounded data, activating a relevant report template based on said identified latent information, populating said template with template-specified data, and processing the template-specified data to generate a report.

Claims

1. At least one computer-readable storage medium having instructions encoded thereon which, when executed, perform a method comprising acts of:

receiving an input data stream comprising speech data documenting a physician'"'"'s encounter with a patient, the input data stream comprising latent information associated with a type of medical report appropriate for documenting the encounter with the patient;

processing the input data stream to identify the latent information;

based on the identified latent information, identifying the type of medical report appropriate for documenting the encounter with the patient;

activating a template specific to the identified type of medical report appropriate for documenting the encounter with the patient, wherein the template specifies at least a plurality of data fields required for documenting the encounter with the patient;

obtaining, from the input data stream, information corresponding to at least one of the data fields specified by the activated template; and

populating the template with the obtained information to generate a medical report that documents the encounter with the patient.

2. The at least one computer-readable storage medium of claim 1, wherein the report comprises an accreditation report or a billing report.

3. The at least one computer-readable storage medium of claim 1, wherein the latent information comprises information about at least one medical fact selected from the group consisting of a medical problem, an allergy, a medical treatment, a medication and a medical procedure.

4. The at least one computer-readable storage medium of claim 1, wherein the act of activating the template comprises selecting a template from a group of stored templates and activating the selected template.

5. The at least one computer-readable storage medium of claim 1, wherein the act of obtaining the information corresponding to at least one of the data fields specified by the activated template comprises prompting a user for the information.

6. The at least one computer-readable storage medium of claim 5, wherein the user is the physician.

7. The at least one computer-readable storage medium of claim 1, wherein the template is activated based on the latent information that does not specify the type of report to which the template relates.

8. A system comprising at least one processor programmed to:

receive an input data stream comprising speech data documenting a physician'"'"'s encounter with a patient, the input data stream comprising latent information associated with a type of medical report appropriate for documenting the encounter with the patient;

process the input data stream to identify the latent information;

based on the identified latent information, identify the type of medical report appropriate for documenting the encounter with the patient;

activate a template specific to the identified type of medical report appropriate for documenting the encounter with the patient, wherein the template specifies at least a plurality of data fields required for documenting the encounter with the patient;

obtain, from the input data stream, information corresponding to at least one of the data fields specified by the activated template; and

populate the template with the obtained information to generate a medical report that documents the encounter with the patient.

9. The system of claim 8, wherein the report comprises an accreditation report or a billing report.

10. The system of claim 8, wherein the latent information comprises information about at least one medical fact selected from the group consisting of a medical problem, an allergy, a medical treatment, a medication and a medical procedure.

11. The system of claim 8, further comprising at least one memory that stores a group of templates including the template, and wherein the at least one processor is programmed to activate the template by selecting the template from the stored group of templates and activating the selected template.

12. The system of claim 8, wherein the at least one processor is programmed to obtain the information corresponding to at least one of the data fields specified by the activated template at least in part by prompting a user to provide the information.

13. The system of claim 12, wherein the user is the physician.

14. The system of claim 8, wherein the at least one processor is programmed to activate the template based on the latent information that does not specify the type of report to which the template relates.