Systems and methods utilizing natural language medical records

• US 20040243545A1
• Filed: 05/29/2003
• Published: 12/02/2004
• Est. Priority Date: 05/29/2003
• Status: Abandoned Application

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Dictaphone Corporation (Microsoft Corporation)
• Inventors: Titemore, Robert G., Boone, Keith W., Carus, Alwin B., Hopkins, Jeffrey G., Ogrinc, Harry J., Reggie, Susan, DePlonty, Thomas J. III
• Application Number:
  US10/447,290
• Publication Number:
  US 20040243545A1
• Time in Patent Office: Days
• US Class Current: 707/2
• CPC Class Codes: G06F 16/313 Selection or weighting of terms for indexing
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

The invention involves systems and methods for generating, manipulating, summarizing, storing, reusing, and searching electronic medical records. Structured input of medical information by medical personnel based on templates may optionally be used to facilitate analysis of records, while allowing less restrictive text input than systems of the prior art. Data extraction of relevant medical data from the input text may optionally be facilitated by the structured format of the medical records. Extracted medical data is optionally validated and linked or associated with the text from which it was extracted. The extracted medical data is normalized to allow easier searching than available in systems of the prior art. Medical and document metadata is incorporated into the extracted medical data. Particularly pertinent medical information may be extracted and summarized from a patient'"'"'s medical history for use by a medical professional at the point of care.

Claims

1. A system for managing information, the system comprising:

a means for capturing text from a document source;

a means for determining the structure of the captured text;

a means for extracting elements of data from the captured text;

a means for categorizing the extracted elements of data;

a means for normalizing the extracted elements of data;

a means for adding metadata relating to the captured text;

a means for validating the extracted elements of data and the metadata, wherein the means for validating further includes validating at least one of the normalized extracted elements of data and the categorized extracted elements of data;

a storage means for storing an electronic document including the categorized, normalized and validated extracted elements of data and metadata in a storage means, wherein the categorized, normalized and validated extracted elements of data and metadata are stored in association with the captured text; and

a means for retrieving the electronic document from the storage means.

2. The system according to claim 1, further comprising a means for displaying the retrieved electronic records.

3. The system according to claim 2, further comprising a means for displaying the metadata.

4. The system according to claim 3, further comprising a means for displaying the captured text.

5. The system according to claim 1, further comprising a means for determining the structure of the format of the captured text.

6. The system according to claim 5, further comprising a means for determining the structure of the content of the captured text.

7. The system according to claim 6, wherein the content of the captured includes one of terms, words and phrases.

8. The system according to claim 1, further comprising a means for determining the overall classification of the content of the captured text.

9. The system according to claim 5, further comprising a means for reusing the extracted elements of data.

10. The system according to claim 5, further comprising a means for reusing the metadata.

11. The system according to claim 5, further comprising a means for reusing the captured text.

12. The system according to claim 1, further comprising a means for tracking which sections of the captured text have been completed.

13. The system according to claim 1, wherein the document source originates from an archive of legacy documents.

14. The system according to claim 13, wherein the document source includes at least one new document created from a predetermined document template.

15. The system according to claim 14, further comprising a means for entering text in the new document created from the predetermined document template.

16. The system according to claim 15, wherein the means for entering text in the new document created from a predetermined document template includes one of a keyboard attached to a computer, a microphone attached to a computer, a telephone, or a PDA.

17. The system according to claim 1, wherein the storage means for storing the electronic document is a computer hard drive.

18. The system according to claim 1, wherein the means for extracting elements of data from the text is a data extraction engine.

19. The system according to claim 1, wherein the means for validating extracted elements of data is a software program with access to the storage means for storing an electronic record.

20. The system according to claim 1, wherein the means for retrieving is accomplished by reference to at least one of the extracted elements of data, the metadata or the captured text.

21. The system according to claim 20, wherein the means for retrieving an electronic document from the storage means is a software program with access to the storage means for storing an electronic record.

22. The system according to claim 21, wherein information about the location of the extracted elements of data within the captured text is used to retrieve a section of the electronic document corresponding to the location of the extracted elements of data.

23. The system according to claim 22, wherein the means for adding metadata is a software program with access to the storage means for storing an electronic document.

24. The system according to claim 1, wherein the means for categorizing includes canonicalizing the extracted of elements of data.

25. The system according to claim 24, wherein the means for categorizing includes classifying headings contained in the extracted elements of data.

26. A method for managing information, the method comprising the steps of:

capturing text from a document source;

determining the structure of the captured text;

extracting elements of data from the captured text;

categorizing the extracted elements of data;

normalizing the extracted elements of data;

adding metadata relating to the captured text;

validating the extracted elements of data and the metadata, wherein validating further includes validating at least one of the normalized extracted elements of data and the categorized extracted elements of data;

storing an electronic document including the categorized, normalized and validated extracted elements of data and metadata in a storage means, wherein the categorized, normalized and validated extracted elements of data and metadata are stored in association with the captured text; and

retrieving the electronic document from the storage means.

27. The method according to claim 26, further comprising the step of displaying the retrieved electronic records.

28. The method according to claim 26, further comprising the step of displaying the metadata.

29. The method according to claim 28, further comprising the step of displaying the captured text.

30. The method according to claim 26, further comprising the step of determining the structure of the format of the captured text.

31. The method according to claim 30, further comprising the step of determining the structure of the content of the captured text.

32. The method according to claim 31, wherein the content of the captured includes one of terms, words and phrases.

33. The method according to claim 26, further comprising the step of determining the overall classification of the content of the captured text.

34. The method according to claim 30, further comprising the step of reusing the extracted elements of data.

35. The method according to claim 30, further comprising the step of reusing the metadata.

36. The method according to claim 30, further comprising the step of reusing the captured text.

37. The method according to claim 26, further comprising the step of tracking which sections of the captured text have been completed.

38. The method according to claim 26, wherein the document source originates from an archive of legacy documents.

39. The method according to claim 38, wherein the document source includes at least one new document created from a predetermined document template.

40. The method according to claim 39, further comprising the step of entering text in the new document created from the predetermined document template.

41. The method according to claim 40, wherein step of entering text in the new document created from a predetermined document template includes one of a keyboard attached to a computer, a microphone attached to a computer, a telephone, or a PDA.

42. The method according to claim 41, wherein the step of storing the electronic document is storing the electronic document on a computer hard drive.

43. The method according to claim 26, wherein the step of extracting elements of data from the text includes using a data extraction engine.

44. The method according to claim 26, wherein the step of validating extracted elements of data includes using a software program with access to the storage means for storing an electronic record.

45. The method according to claim 26, wherein the step of retrieving is accomplished by reference to at least one of the extracted elements of data, the metadata or the captured text.

46. The method according to claim 45, wherein the step of retrieving an electronic document includes using is a software program with access to the storage means for storing an electronic record.

47. The method according to claim 46, wherein information about the location of the extracted elements of data within the captured text is used to retrieve a section of the electronic document corresponding to the location of the extracted elements of data.

48. The method according to claim 47, wherein the step of adding metadata includes using a software program with access to the storage means.

49. The method according to claim 26, wherein step of categorizing includes canonicalizing the extracted of elements of data.

50. The method according to claim 49, wherein the step of categorizing includes classifying headings contained in the extracted elements of data.

51. A method, the method comprising the steps of:

entering information text in a predetermined record template, wherein text pertinent to a section of the template is entered in that section as natural language;

storing a completed medical record;

extracting elements of medical data from the text, wherein information about which section of the template the text was entered is used to extract elements of medical data from the text;

validating extracted data;

normalizing the extracted elements of medical data;

storing an electronic medical record as normalized extracted elements of medical data in association with the text from which they were extracted; and

retrieving electronic medical records from the storage means by natural language searching, wherein the retrieving is accomplished by reference to one or more extracted elements and the natural language is normalized.

52. The method according to claim 51, wherein the step of entering medical information text is performed using a microphone attached to a computer.

53. The method according to claim 51, wherein the step of entering medical information is performed using a telephone.

54. The method according to claim 51, wherein the step of entering medical information is performed using a PDA.

55. The method according to claim 51, wherein the step of storing a completed medical record and the step of storing an electronic medical record are performed on computer hard drives.

56. The method according to claim 55, wherein the step of storing a completed medical record and step of storing an electronic medical record are performed on database servers.

57. The method according to claim 51, wherein the step of extracting elements of medical data from the text is performed using a NLP and ML data extraction engine.

58. The method according to claim 51, wherein the step of validating extracted data is performed using a web browser software program with access to the stored electronic medical record.

59. The method according to claim 51, wherein the step of normalizing the extracted elements of medical data is performed using a software program running on a computer.

60. The method according to claim 51, wherein the step of retrieving electronic medical records is performed using a web browser software program with access to the stored electronic medical record.

61. The method according to claim 51, further comprising the step of creating a medical record template.

62. The method according to claim 51, further comprising providing a patient history summary.

63. The method according to claim 51, further comprising the step of adding medical metadata.

64. The method according to claim 63, wherein the additional medical metadata is stored on a computer hard drive.

65. The method according to claim 63, wherein the additional medical metadata is stored on a database server.

66. The method according to claim 63, wherein the step of adding medical metadata is performed using a software program running on a computer.

67. The method according to claim 63, wherein the step of adding medical metadata is performed using a web browser with access to the stored electronic medical record.