Methods and apparatus for formatting text for clinical fact extraction

• US 8,768,723 B2
• Filed: 02/18/2011
• Issued: 07/01/2014
• 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: Montyne, Frank, Decraene, David, Van der Vloet, Joeri, Raedemaeker, Johan, Coppens, Frederik, Deray, Tom, Flanagan, James R., Casella dos Santos, Mariana, Holvoet, Marnix, Hellman, David, Yegnanarayanan, Girija, Doyle, Karen Anne, Desimpel, Ignace, van Gurp, Maria
• Primary Examiner(s): Sereboff, Neal
• Assistant Examiner(s): KANAAN, MAROUN P
• Application Number:
  US13/030,959
• Publication Number:
  US 20120212337A1
• Time in Patent Office: 1,229 Days
• Field of Search: 705/2, 705/3
• US Class Current: 705/2
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof

Abstract

An original text that is a representation of a narration of a patient encounter provided by a clinician may be received and re-formatted to produce a formatted text. One or more clinical facts may be extracted from the formatted text. A first fact of the clinical facts may be extracted from a first portion of the formatted text, and the first portion of the formatted text may be a formatted version of a first portion of the original text. A linkage may be maintained between the first fact and the first portion of the original text.

Claims

1. A method comprising:

receiving an original free-form text narrative of a patient encounter provided by a clinician;

re-formatting the original free-form text narrative, using at least one processor, in a manner that facilitates clinical fact extraction performed by a fact extraction engine on a formatted text resulting from the re-formatting;

extracting one or more clinical facts from the formatted text using the fact extraction engine, wherein a first fact of the one or more clinical facts is extracted from a first portion of the formatted text, wherein the first portion of the formatted text is a formatted version of a first portion of the original free-form text narrative, the extracting comprising

analyzing the formatted text to identify a set of one or more features of at least the first portion of the formatted 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 formatted text; and

providing to a user an indicator that distinguishes the first portion of the original free-form text narrative that resulted in extraction of the first fact, from other portions of the original free-form text narrative that did not result in the extraction of the first fact.

2. The method of claim 1, wherein the re-formatting facilitates the clinical fact extraction at least in part by adding, removing or correcting at least one sentence boundary in the original free-form text narrative.

3. The method of claim 1, wherein the re-formatting facilitates the clinical fact extraction at least in part by identifying at least one section boundary in the original free-form text narrative, and adding, removing or correcting at least one section heading corresponding to the at least one section boundary.

4. The method of claim 1, wherein the re-formatting facilitates the clinical fact extraction at least in part by normalizing at least one section heading according to a standard for an institution associated with the patient encounter.

5. The method of claim 1, wherein receiving the original free-form text narrative comprises performing automatic speech recognition on a spoken free-form narration provided by the clinician.

6. The method of claim 5, wherein performing the automatic speech recognition comprises accessing a lexicon of terms linked to a clinical ontology.

7. The method of claim 6, wherein the clinical ontology is a language understanding ontology.

8. The method of claim 1, further comprising prompting a user to approve the formatted text.

9. The method of claim 1, wherein the indicator comprises a visual indicator.

10. The method of claim 1, wherein the indicator comprises an audio indicator.

11. The method of claim 1, wherein neither the original free-form text narrative nor the formatted text is edited by a human other than the clinician before the one or more clinical facts are extracted.

12. The method of claim 1, wherein the re-formatting and the extracting are performed automatically.

13. 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;

receiving an original free-form text narrative of a patient encounter provided by a clinician;

re-formatting the original free-form text narrative in a manner that facilitates clinical fact extraction performed by a fact extraction engine on a formatted text resulting from the re-formatting;

extracting one or more clinical facts from the formatted text using the fact extraction engine, wherein a first fact of the one or more clinical facts is extracted from a first portion of the formatted text, wherein the first portion of the formatted text is a formatted version of a first portion of the original free-form text narrative, the extracting comprising

analyzing the formatted text to identify a set of one or more features of at least the first portion of the formatted 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 formatted text; and

providing to a user an indicator that distinguishes the first portion of the original free-form text narrative that resulted in extraction of the first fact, from other portions of the original free-form text narrative that did not result in the extraction of the first fact.

14. The apparatus of claim 13, wherein the re-formatting facilitates the clinical fact extraction at least in part by adding, removing or correcting at least one sentence boundary in the original free-form text narrative.

15. The apparatus of claim 13, wherein the re-formatting facilitates the clinical fact extraction at least in part by identifying at least one section boundary in the original free-form text narrative, and adding, removing or correcting at least one section heading corresponding to the at least one section boundary.

16. The apparatus of claim 13, wherein the re-formatting facilitates the clinical fact extraction at least in part by normalizing at least one section heading according to a standard for an institution associated with the patient encounter.

17. The apparatus of claim 13, wherein receiving the original free-form text narrative comprises performing automatic speech recognition on a spoken free-form narration provided by the clinician.

18. The apparatus of claim 17, wherein performing the automatic speech recognition comprises accessing a lexicon of terms linked to a clinical ontology.

19. The apparatus of claim 18, wherein the clinical ontology is a language understanding ontology.

20. The apparatus of claim 13, wherein the method further comprises prompting a user to approve the foimatted text.

21. The apparatus of claim 13, wherein the indicator comprises a visual indicator.

22. The apparatus of claim 13, wherein the indicator comprises an audio indicator.

23. The apparatus of claim 13, wherein neither the original free-form text narrative nor the formatted text is edited by a human other than the clinician before the one or more clinical facts are extracted.

24. The apparatus of claim 13, wherein the re-formatting and the extracting are performed automatically.

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

receiving an original free-form text narrative of a patient encounter provided by a clinician;

re-formatting the original free-form text narrative in a manner that facilitates clinical fact extraction performed by a fact extraction engine on a formatted text resulting from the re-formatting;

extracting one or more clinical facts from the formatted text using the fact extraction engine, wherein a first fact of the one or more clinical facts is extracted from a first portion of the formatted text, wherein the first portion of the formatted text is a formatted version of a first portion of the original free-form text narrative, the extracting comprising

analyzing the formatted text to identify a set of one or more features of at least the first portion of the formatted 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 formatted text; and

providing to a user an indicator that distinguishes the first portion of the original free-form text narrative that resulted in extraction of the first fact, from other portions of the original free-form text narrative that did not result in the extraction of the first fact.

26. The at least one non-transitory computer-readable storage medium of claim 25, wherein the re-formatting facilitates the clinical fact extraction at least in part by adding, removing or correcting at least one sentence boundary in the original free-form text narrative.

27. The at least one non-transitory computer-readable storage medium of claim 25, wherein the re-formatting facilitates the clinical fact extraction at least in part by identifying at least one section boundary in the original free-form text narrative, and adding, removing or correcting at least one section heading corresponding to the at least one section boundary.

28. The at least one non-transitory computer-readable storage medium of claim 25, wherein the re-formatting facilitates the clinical fact extraction at least in part by normalizing at least one section heading according to a standard for an institution associated with the patient encounter.

29. The at least one non-transitory computer-readable storage medium of claim 25, wherein receiving the original free-form text narrative comprises performing automatic speech recognition on a spoken free-form narration provided by the clinician.

30. The at least one non-transitory computer-readable storage medium of claim 29, wherein performing the automatic speech recognition comprises accessing a lexicon of terms linked to a clinical ontology.

31. The at least one non-transitory computer-readable storage medium of claim 30, wherein the clinical ontology is a language understanding ontology.

32. The at least one non-transitory computer-readable storage medium of claim 25, wherein the method further comprises prompting a user to approve the formatted text.

33. The at least one non-transitory computer-readable storage medium of claim 25, wherein the indicator comprises a visual indicator.

34. The at least one non-transitory computer-readable storage medium of claim 25, wherein the indicator comprises an audio indicator.

35. The at least one non-transitory computer-readable storage medium of claim 25, wherein neither the original free-form text narrative nor the formatted text is edited by a human other than the clinician before the one or more clinical facts are extracted.

36. The at least one non-transitory computer-readable storage medium of claim 25, wherein the re-formatting and the extracting are performed automatically.