Methods and apparatus for analyzing specificity in clinical documentation

• US 8,799,021 B2
• Filed: 02/18/2011
• Issued: 08/05/2014
• Est. Priority Date: 02/18/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Flanagan, James R., Montyne, Frank, Decraene, David, Casella dos Santos, Mariana, Holvoet, Marnix, Doyle, Karen Anne, Manoukian, Roubik, Elcocks, Anthony J., Shelton, Matthew R., Abrutyn, Scott, Habboush, Isam
• Primary Examiner(s): Sereboff, Neal
• Assistant Examiner(s): KANAAN, MAROUN P
• Application Number:
  US13/030,974
• Publication Number:
  US 20120215558A1
• Time in Patent Office: 1,264 Days
• Field of Search: 705/2, 705/3
• US Class Current: 705/3
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G16H 10/40 for data related to laboratory analysis, e.g. patient specimen analysis
• 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: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A set of one or more clinical facts may be collected from a clinician'"'"'s encounter with a patient. From the set of facts, it may be determined that an additional fact that provides additional specificity to the set of facts may possibly be ascertained from the patient encounter. A user may be alerted that the additional fact may possibly be ascertained from the patient encounter.

Claims

1. A method comprising:

extracting a set of one or more clinical facts from a text documenting a clinician'"'"'s encounter with a patient, the extracting comprising

analyzing the text to identify a set of one or more features of at least a portion of the text,

correlating the set of features to one or more abstract semantic concepts, and

generating computer-readable data that expresses the one or more abstract semantic concepts as the one or more clinical facts extracted from the text;

analyzing the set of facts, using at least one processor, to identify that at least one fact of the set of facts indicates a potential opportunity for providing additional specificity to the set of facts for documenting the patient encounter;

generating one or more hypotheses for an additional fact not documented in the text, that provides the additional specificity indicated by the at least one fact; and

alerting a user to at least one of the one or more hypotheses.

2. The method of claim 1, wherein the text comprises a free-form narration of the patient encounter provided by the clinician.

3. The method of claim 1, wherein the analyzing the set of facts comprises analyzing at least one fact received as a discrete structured data item from the user, in addition to the one or more clinical facts extracted from the text.

4. The method of claim 1, wherein the analyzing the set of facts comprises analyzing at least one fact received from an electronic medical record of the patient, in addition to the one or more clinical facts extracted from the text.

5. The method of claim 1, wherein the additional fact comprises a more specific version of a first fact of the set of facts.

6. The method of claim 5, wherein the first fact corresponds to at least one standard code.

7. The method of claim 6, wherein the at least one standard code comprises at least one code selected from the group consisting of an ICD code, a CPT code, a MedDRA code, a SNOMED code, a LOINC code, an RxNorm code, an NDC code and a RadLex code.

8. The method of claim 5, wherein the first fact corresponds to a code in a hierarchical coding system, wherein the additional fact corresponds to at least one code in the hierarchical coding system that is a more specific version of the code corresponding to the first fact.

9. The method of claim 1, wherein the additional fact is implied by two or more facts of the set of facts in combination.

10. The method of claim 1, wherein the generating comprises determining whether the patient'"'"'s history previous to the patient encounter includes information that provides the additional specificity to the set of facts, and wherein the alerting is performed in response to determining that the patient'"'"'s history does not include such information.

11. The method of claim 1, further comprising:

in response to determining that the patient'"'"'s history includes a second additional fact that provides additional specificity to the set of facts, suppressing an alert that would otherwise be generated relating to the second additional fact.

12. The method of claim 1, wherein the alerting comprises displaying a visual alert to the user.

13. The method of claim 1, wherein the alerting comprises providing an audio alert to the user.

14. The method of claim 1, wherein the alerting comprises presenting one or more options corresponding to the one or more hypotheses, and allowing the user to choose among the one or more options.

15. The method of claim 14, further comprising:

deriving the additional fact from the option chosen by the user; and

storing the additional fact as a discrete structured data item.

16. The method of claim 14, further comprising editing the text in accordance with the option chosen by the user.

17. The method of claim 1, wherein the user is the clinician.

18. The method of claim 1, wherein the user is a person other than the clinician, wherein the alerting comprises prompting the user to provide information corresponding to the additional fact, and wherein the method further comprises prompting the clinician to approve the information provided by the user.

19. The method of claim 2, further comprising simultaneously displaying to the user the set of facts and one or more portions of the free-form narration from which the set of facts was extracted.

20. The method of claim 1, wherein the alerting is performed before the clinician finally approves the set of one or more clinical facts.

21. The method of claim 1, wherein the analyzing the set of facts, the generating, and the alerting are performed automatically.

22. The method of claim 17, further comprising:

receiving an indication from a human other than the clinician to issue an additional alert to the clinician; and

in response to the indication, issuing the additional alert to the clinician.

23. Apparatus comprising:

at least one processor; and

a memory storing processor-executable instructions that, when executed by the at least one processor, perform a method comprising;

extracting a set of one or more clinical facts from a text documenting a clinician'"'"'s encounter with a patient, the extracting comprising

analyzing the text to identify a set of one or more features of at least a portion of the text,

correlating the set of features to one or more abstract semantic concepts, and

generating computer-readable data that expresses the one or more abstract semantic concepts as the one or more clinical facts extracted from the text;

analyzing the set of facts to identify that at least one fact of the set of facts indicates a potential opportunity for providing additional specificity to the set of facts for documenting the patient encounter;

generating one or more hypotheses for an additional fact not documented in the text, that provides the additional specificity indicated by the at least one fact; and

alerting a user to at least one of the one or more hypotheses.

24. The apparatus of claim 23, wherein the text comprises a free-form narration of the patient encounter provided by the clinician.

25. The apparatus of claim 23, wherein the analyzing the set of facts comprises analyzing at least one fact received as a discrete structured data item from the user, in addition to the one or more clinical facts extracted from the text.

26. The apparatus of claim 23, wherein the analyzing the set of facts comprises analyzing at least one fact received from an electronic medical record of the patient, in addition to the one or more clinical facts extracted from the text.

27. The apparatus of claim 23, wherein the additional fact comprises a more specific version of a first fact of the set of facts.

28. The apparatus of claim 27, wherein the first fact corresponds to at least one standard code.

29. The apparatus of claim 28, wherein the at least one standard code comprises at least one code selected from the group consisting of an ICD code, a CPT code, a MedDRA code, a SNOMED code, a LOINC code, an RxNorm code, an NDC code and a RadLex code.

30. The apparatus of claim 27, wherein the first fact corresponds to a code in a hierarchical coding system, wherein the additional fact corresponds to at least one code in the hierarchical coding system that is a more specific version of the code corresponding to the first fact.

31. The apparatus of claim 23, wherein the additional fact is implied by two or more facts of the set of facts in combination.

32. The apparatus of claim 23, wherein the generating comprises determining whether the patient'"'"'s history previous to the patient encounter includes information that provides the additional specificity to the set of facts, and wherein the alerting is performed in response to determining that the patient'"'"'s history does not include such information.

33. The apparatus of claim 23, wherein the method further comprises:

in response to determining that the patient'"'"'s history includes a second additional fact that provides additional specificity to the set of facts, suppressing an alert that would otherwise be generated relating to the second additional fact.

34. The apparatus of claim 23, wherein the alerting comprises displaying a visual alert to the user.

35. The apparatus of claim 23, wherein the alerting comprises providing an audio alert to the user.

36. The apparatus of claim 23, wherein the alerting comprises presenting one or more options corresponding to the one or more hypotheses, and allowing the user to choose among the one or more options.

37. The apparatus of claim 36, wherein the method further comprises:

deriving the additional fact from the option chosen by the user; and

storing the additional fact as a discrete structured data item.

38. The apparatus of claim 36, wherein the method further comprises editing the text in accordance with the option chosen by the user.

39. The apparatus of claim 23, wherein the user is the clinician.

40. The apparatus of claim 23, wherein the user is a person other than the clinician, wherein the alerting comprises prompting the user to provide information corresponding to the additional fact, and wherein the method further comprises prompting the clinician to approve the information provided by the user.

41. The apparatus of claim 24, wherein the method further comprises simultaneously displaying to the user the set of facts and one or more portions of the free-form narration from which the set of facts was extracted.

42. The apparatus of claim 23, wherein the alerting is performed before the clinician finally approves the set of one or more clinical facts.

43. The apparatus of claim 23, wherein the analyzing the set of facts, the generating, and the alerting are performed automatically.

44. The apparatus of claim 39, wherein the method further comprises:

receiving an indication from a human other than the clinician to issue an additional alert to the clinician; and

in response to the indication, issuing the additional alert to the clinician.

45. At least one non-transitory computer-readable storage medium encoded with a plurality of computer-executable instructions that, when executed, perform a method comprising:

extracting a set of one or more clinical facts from a text documenting a clinician'"'"'s encounter with a patient, the extracting comprising

analyzing the text to identify a set of one or more features of at least a portion of the text,

correlating the set of features to one or more abstract semantic concepts, and

generating computer-readable data that expresses the one or more abstract semantic concepts as the one or more clinical facts extracted from the text;

analyzing the set of facts to identify that at least one fact of the set of facts indicates a potential opportunity for providing additional specificity to the set of facts for documenting the patient encounter;

generating one or more hypotheses for an additional fact not documented in the text, that provides the additional specificity indicated by the at least one fact; and

alerting a user to at least one of the one or more hypotheses.

46. The at least one non-transitory computer-readable storage medium of claim 45, wherein the text comprises a free-form narration of the patient encounter provided by the clinician.

47. The at least one non-transitory computer-readable storage medium of claim 45, wherein the analyzing the set of facts comprises analyzing at least one fact received as a discrete structured data item from the user, in addition to the one or more clinical facts extracted from the text.

48. The at least one non-transitory computer-readable storage medium of claim 45, wherein the analyzing the set of facts comprises analyzing at least one fact received from an electronic medical record of the patient, in addition to the one or more clinical facts extracted from the text.

49. The at least one non-transitory computer-readable storage medium of claim 45, wherein the additional fact comprises a more specific version of a first fact of the set of facts.

50. The at least one non-transitory computer-readable storage medium of claim 49, wherein the first fact corresponds to at least one standard code.

51. The at least one non-transitory computer-readable storage medium of claim 50, wherein the at least one standard code comprises at least one code selected from the group consisting of an ICD code, a CPT code, a MedDRA code, a SNOMED code, a LOINC code, an RxNorm code, an NDC code and a RadLex code.

52. The at least one non-transitory computer-readable storage medium of claim 49, wherein the first fact corresponds to a code in a hierarchical coding system, wherein the additional fact corresponds to at least one code in the hierarchical coding system that is a more specific version of the code corresponding to the first fact.

53. The at least one non-transitory computer-readable storage medium of claim 45, wherein the additional fact is implied by two or more facts of the set of facts in combination.

54. The at least one non-transitory computer-readable storage medium of claim 45, wherein the generating comprises determining whether the patient'"'"'s history previous to the patient encounter includes information that provides the additional specificity to the set of facts, and wherein the alerting is performed in response to determining that the patient'"'"'s history does not include such information.

55. The at least one non-transitory computer-readable storage medium of claim 45, wherein the method further comprises:

in response to determining that the patient'"'"'s history includes a second additional fact that provides additional specificity to the set of facts, suppressing an alert that would otherwise be generated relating to the second additional fact.

56. The at least one non-transitory computer-readable storage medium of claim 45, wherein the alerting comprises displaying a visual alert to the user.

57. The at least one non-transitory computer-readable storage medium of claim 45, wherein the alerting comprises providing an audio alert to the user.

58. The at least one non-transitory computer-readable storage medium of claim 45, wherein the alerting comprises presenting one or more options corresponding to the one or more hypotheses, and allowing the user to choose among the one or more options.

59. The at least one non-transitory computer-readable storage medium of claim 58, wherein the method further comprises:

deriving the additional fact from the option chosen by the user; and

storing the additional fact as a discrete structured data item.

60. The at least one non-transitory computer-readable storage medium of claim 58, wherein the method further comprises editing the text in accordance with the option chosen by the user.

61. The at least one non-transitory computer-readable storage medium of claim 45, wherein the user is the clinician.

62. The at least one non-transitory computer-readable storage medium of claim 45, wherein the user is a person other than the clinician, wherein the alerting comprises prompting the user to provide information corresponding to the additional fact, and wherein the method further comprises prompting the clinician to approve the information provided by the user.

63. The at least one non-transitory computer-readable storage medium of claim 46, wherein the method further comprises simultaneously displaying to the user the set of facts and one or more portions of the free-form narration from which the set of facts was extracted.

64. The at least one non-transitory computer-readable storage medium of claim 45, wherein the alerting is performed before the clinician finally approves the set of one or more clinical facts.

65. The at least one non-transitory computer-readable storage medium of claim 45, wherein the analyzing the set of facts, the generating, and the alerting are performed automatically.

66. The at least one non-transitory computer-readable storage medium of claim 61, wherein the method further comprises:

receiving an indication from a human other than the clinician to issue an additional alert to the clinician; and

in response to the indication, issuing the additional alert to the clinician.