Methods and apparatus for analyzing specificity in clinical documentation

Patent metadata

Field	Value
Publication number	US-9898580-B2
Application number	US-201414302879-A
Country	US
Kind code	B2
Filing date	Jun 12, 2014
Priority date	Feb 18, 2011
Publication date	Feb 20, 2018
Grant date	Feb 20, 2018

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.

First claim

What is claimed is:

1. A method comprising:
extracting, from a text documenting a clinician's encounter with a single patient, a set of one or more clinical facts representing one or more abstract semantic concepts, wherein the extracting comprises
analyzing the text, via a natural language understanding engine, to identify a set of one or more features of at least a portion of the text, and
correlating the set of features to the one or more abstract semantic concepts;

wherein the one or more abstract semantic concepts comprise a first diagnosis that the clinician, in the text, indicated that the patient exhibited;
wherein the first diagnosis is a generic diagnosis representing a class of a plurality of more specific subdiagnoses of the first diagnosis;
wherein the method further comprises:
analyzing a history record comprising data indicative of the patient's history to determine an additional fact without needing to request input of the additional fact;
analyzing the set of one or more clinical facts and the additional fact, using at least one processor, to generate one or more hypotheses for a second diagnosis, exhibited by the patient and not documented in the text, the second diagnosis being a particular one of the plurality of more specific subdiagnoses of the first diagnosis that the clinician indicated that the patient exhibited; and
presenting, to a user, the generated 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 first diagnosis corresponds to a first code in a hierarchical coding system, and wherein the one or more hypotheses for the second diagnosis include at least one code in the hierarchical coding system that is a more specific version of the first code.

4. The method of claim 3 , wherein the first diagnosis that the clinician indicated that the patient exhibited corresponds to a first ICD code, and wherein the one or more hypotheses for the second diagnosis exhibited by the patient and not documented in the text include at least one child ICD code of the first ICD code in an ICD code hierarchy, wherein the first ICD code is a parent ICD code of the at least one child ICD code in the ICD code hierarchy.

5. The method of claim 1 , wherein analyzing the set of facts comprises determining that the second diagnosis is implied by two or more facts of the set of facts in combination.

6. 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.

7. 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, from a text documenting a clinician's encounter with a single patient, a set of one or more clinical facts representing one or more abstract semantic concepts, wherein the extracting comprises
analyzing the text, via a natural language understanding engine, to identify a set of one or more features of at least a portion of the text, and
correlating the set of features to the one or more abstract semantic concepts;

wherein the one or more abstract semantic concepts comprise a first diagnosis that the clinician, in the text, indicated that the patient exhibited;
wherein the first diagnosis is a generic diagnosis representing a class of a plurality of more specific subdiagnoses of the first diagnosis;
wherein the method further comprises:
analyzing a history record comprising data indicative of the patient's history to determine an additional fact without needing to request input of the additional fact;
analyzing the set of one or more clinical facts and the additional fact to generate one or more hypotheses for a second diagnosis, exhibited by the patient and not documented in the text, the second diagnosis being a particular one of the plurality of more specific subdiagnoses of the first diagnosis that the clinician indicated that the patient exhibited; and
presenting, to a user, the generated at least one of the one or more hypotheses.

8. The apparatus of claim 7 , wherein the text comprises a free-form narration of the patient encounter provided by the clinician.

9. The apparatus of claim 7 , wherein the first diagnosis corresponds to a first code in a hierarchical coding system, and wherein the one or more hypotheses for the second diagnosis include at least one code in the hierarchical coding system that is a more specific version of the first code.

10. The apparatus of claim 9 , wherein the first diagnosis that the clinician indicated that the patient exhibited corresponds to a first ICD code, and wherein the one or more hypotheses for the second diagnosis exhibited by the patient and not documented in the text include at least one child ICD code of the first ICD code in an ICD code hierarchy, wherein the first ICD code is a parent ICD code of the at least one child ICD code in the ICD code hierarchy.

11. The apparatus of claim 7 , wherein analyzing the set of facts comprises determining that the second diagnosis is implied by two or more facts of the set of facts in combination.

12. The apparatus of claim 7 , 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.

13. 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, from a text documenting a clinician's encounter with a single patient, a set of one or more clinical facts representing one or more abstract semantic concepts, wherein the extracting comprises
analyzing the text, via a natural language understanding engine, to identify a set of one or more features of at least a portion of the text, and
correlating the set of features to the one or more abstract semantic concepts;

wherein the one or more abstract semantic concepts comprise a first diagnosis that the clinician, in the text, indicated that the patient exhibited;
wherein the first diagnosis is a generic diagnosis representing a class of a plurality of more specific subdiagnoses of the first diagnosis;
wherein the method further comprises:
analyzing a history record comprising data indicative of the patient's history to determine an additional fact without needing to request input of the additional fact;
analyzing the set of one or more clinical facts and the additional fact to generate one or more hypotheses for a second diagnosis, exhibited by the patient and not documented in the text, the second diagnosis being a particular one of the plurality of more specific subdiagnoses of the first diagnosis that the clinician indicated that the patient exhibited; and
presenting, to a user, the generated at least one of the one or more hypotheses.

14. The at least one non-transitory computer-readable storage medium of claim 13 , wherein the text comprises a free-form narration of the patient encounter provided by the clinician.

15. The at least one non-transitory computer-readable storage medium of claim 13 , wherein the first diagnosis corresponds to a first code in a hierarchical coding system, and wherein the one or more hypotheses for second diagnosis include at least one code in the hierarchical coding system that is a more specific version of the first code.

16. The at l

Assignees

• Nuance Communications Inc

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

Classifications

• G16H50/70

  for mining of medical data, e.g. analysing previous cases of other patients · CPC title

• G06Q10/10

  Office automation; Time management · CPC title

• G16H10/40

  for data related to laboratory analysis, e.g. patient specimen analysis · CPC title

• G16H10/60 Primary

  for patient-specific data, e.g. for electronic patient records · CPC title

• G16H15/00

  ICT specially adapted for medical reports, e.g. generation or transmission thereof · CPC title