Methods and apparatus for formatting text for clinical fact extraction
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.
1. A method comprising:
receiving, using at least one processor, an original text that is a textual representation of a narration of a patient encounter provided by a clinician;
re-formatting the original text, using the at least one processor, to produce a formatted text;
determining, using the at least one processor and from at least one word or phrase of the formatted text, one or more clinical facts indicating one or more concepts expressed by the at least one word or phrase of the formatted text, wherein a first fact of the one or more clinical facts is determined 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 text, the determining the first fact from the first portion of the formatted text comprising identifying one or more features of one or more words or phrases of the first portion of the formatted text and identifying, based on the one or more features, a clinical fact expressed by the first portion of the formatted text; and
outputting, using the at least one processor, the one or more clinical facts determined from the formatted text and, for the first fact, an indication of a linkage between the first fact and the first portion of the original text.
2. The method of claim 1 , wherein the re-formatting comprises adding, removing or correcting at least one sentence boundary in the original text.
3. The method of claim 1 , wherein the re-formatting comprises identifying at least one section boundary in the original text, 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 comprises 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 the narration is provided by the clinician in spoken form, and wherein receiving the original text comprises performing automatic speech recognition on the spoken narration.
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 , wherein outputting the one or more clinical facts and the indication of the linkage between the first fact and the first portion of the original text comprises outputting, to at least one clinician, the one or more clinical facts and the indication of the linkage between the first fact and the first portion of the original text.
9. The method of claim 1 , wherein neither the original text nor the formatted text is edited by a human other than the clinician before the one or more clinical facts are determined.
10. The method of claim 1 , wherein the re-formatting and the determining are performed automatically.
11. 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 text that is a textual representation of a narration of a patient encounter provided by a clinician;
re-formatting the original text to produce a formatted text;
determining, from at least one word or phrase of the formatted text, one or more clinical facts indicating one or more concepts expressed by the at least one word or phrase of the formatted text, wherein a first fact of the one or more clinical facts is determined 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 text, the determining the first fact from the first portion of the formatted text comprising identifying one or more features of one or more words or phrases of the first portion of the formatted text and identifying, based on the one or more features, a clinical fact expressed by the first portion of the formatted text; and
outputting the one or more clinical facts determined from the formatted text and, for the first fact, an indication of a linkage between the first fact and the first portion of the original text.
12. The apparatus of claim 11 , wherein the re-formatting comprises adding, removing or correcting at least one sentence boundary in the original text.
13. The apparatus of claim 11 , wherein the re-formatting comprises identifying at least one section boundary in the original text, and adding, removing or correcting at least one section heading corresponding to the at least one section boundary.
14. The apparatus of claim 11 , wherein the re-formatting comprises normalizing at least one section heading according to a standard for an institution associated with the patient encounter.
15. The apparatus of claim 11 , wherein the narration is provided by the clinician in spoken form, and wherein receiving the original text comprises performing automatic speech recognition on the spoken narration.
16. The apparatus of claim 15 , wherein performing the automatic speech recognition comprises accessing a lexicon of terms linked to a clinical ontology.
17. The apparatus of claim 16 , wherein the clinical ontology is a language understanding ontology.
18. The apparatus of claim 11 , wherein the method further comprises prompting a user to approve the formatted text.
19. The apparatus of claim 11 , wherein outputting the one or more clinical facts and the indication of the linkage between the first fact and the first portion of the original text comprises outputting, to at least one clinician, the one or more clinical facts and the indication of the linkage between the first fact and the first portion of the original text.
20. The apparatus of claim 11 , wherein neither the original text nor the formatted text is edited by a human other than the clinician before the one or more clinical facts are determined.
21. At least one computer-readable storage medium encoded with a plurality of computer-executable instructions that, when executed, perform a method comprising:
receiving an original text that is a textual representation of a narration of a patient encounter provided by a clinician;
re-formatting the original text to produce a formatted text;
determining, from at least one word or phrase of the formatted text, one or more clinical facts indicating one or more concepts expressed by the at least one word or phrase of the formatted text, wherein a first fact of the one or more clinical facts is determined 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 text, the determining the first fact from the first portion of the formatted text comprising identifying one or more features of one or more words or phrases of the first portion of the formatted text and identifying, based on the one or more features, a clinical fact expressed by the first portion of the formatted text; and
outputting the one or more clinical facts determined from the formatted text and, for the first fact, an indication of a linkage between the first fact and the first portion of the original text.
22. The at least one computer-readable storage medium of claim 21 , wherein the re-formatting comprises adding, removing or correcting at least one sentence boundary in the original text.
23. The at least one computer-readable storage medium of claim 21 , wherein the re-formatting comprises identifying at least one section boundary in the original text, and adding, removing or correcting at least one section heading corresponding to the at least one section boundary.
24. The at least one computer-readable storage medium of claim 21 , wherein the re-formatting comprises normalizing at least one section heading according to a standard for an institution associated with the patient encounter.
25. The at least one computer-readable storage medium of claim 21 , wherein the narration is provided by the clinician in spoken form, and wherein receiving the original text comprises performing automatic speech recognition on the spoken narration.
26. The at least one computer-readable storage medium of claim 25 , wherein performing the automatic speech recognition comprises accessing a lexicon of terms linked to a clinical ontology.
27. The at least one computer-readable storage medium of claim 26 , wherein the clinical ontology is a language understanding ontology.
28. The at least one computer-readable storage medium of claim 21 , wherein the method further comprises prompting a user to approve the formatted text.
29. The at least one computer-readable storage medium of claim 21 , wherein outputting the one or more clinical facts and the indication of the linkage between the first fact and the first portion of the original text comprises outputting, to at least one clinician, the one or more clinical facts and the indication of the linkage between the first fact and the first portion of the original text.
30. The at least one computer-readable storage medium of claim 21 , wherein neither the original text nor the formatted text is edited by a human other than the clinician before the one or more clinical facts are determined.