Methods and apparatus for generating clinical reports

• US 10,199,124 B2
• Filed: 10/09/2017
• Issued: 02/05/2019
• Est. Priority Date: 03/08/2012
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Casella dos Santos, Mariana
• Primary Examiner(s): Armstrong, Angela A
• Application Number:
  US15/728,352
• Publication Number:
  US 20180032702A1
• Time in Patent Office: 484 Days
• Field of Search: None
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• 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 40/63 for local operation
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Techniques for documenting a clinical procedure involve transcribing audio data comprising audio of one or more clinical personnel speaking while performing the clinical procedure. Examples of applicable clinical procedures include sterile procedures such as surgical procedures, as well as non-sterile procedures such as those conventionally involving a core code reporter. The transcribed audio data may be analyzed to identify relevant information for documenting the clinical procedure, and a text report including the relevant information documenting the clinical procedure may be automatically generated.

Claims

1. A method comprising:

transcribing audio data comprising audio of one or more clinical personnel speaking while performing a clinical procedure, the audio data comprising audio of a clinician speaking while performing the clinical procedure, wherein transcribing the audio data comprises performing automatic speech recognition (ASR) on the audio data

analyzing the transcribed audio data, including the transcribed audio of the clinician speaking while performing the clinical procedure, using at least one processor, to identify relevant information for documenting the clinical procedure; and

automatically generating a text report including the identified relevant information documenting the clinical procedure;

wherein identifying the relevant information comprises detecting within the transcribed audio data a present-tense narration by the clinician that the clinician is performing a particular step of the clinical procedure;

wherein automatically generating the text report comprises automatically transforming the present-tense narration into a non-present-tense text portion in the report, stating that the particular step of the clinical procedure was performed.

2. The method of claim 1, wherein the audio data comprises audio of the one or more clinical personnel orally identifying an instrument used in performing the clinical procedure, wherein the analyzing comprises automatically determining from the transcribed audio data a step of the clinical procedure performed using the instrument, and wherein generating the text report comprises automatically generating text stating that the determined step of the clinical procedure was performed.

3. The method of claim 1, wherein the audio data comprises audio of the one or more clinical personnel orally identifying an action being performed during the clinical procedure, wherein the analyzing comprises automatically determining whether the action is part of a step of the clinical procedure that is relevant for documenting the clinical procedure, and wherein generating the text report comprises, in response to determining that the action is part of a step of the clinical procedure that is relevant for documenting the clinical procedure, automatically generating text stating that the relevant step was performed.

4. The method of claim 1, wherein the audio data comprises audio of the one or more clinical personnel orally identifying an event occurring during the clinical procedure, wherein the analyzing comprises automatically determining whether the event indicates that a patient suffered a complication of the clinical procedure, and wherein generating the text report comprises, in response to determining that the event indicates that the patient suffered a complication of the clinical procedure, automatically generating text stating that the event occurred as a complication.

5. The method of claim 1, wherein the clinical procedure is performed on a patient, wherein the audio data comprises audio of the one or more clinical personnel orally identifying one or more observations of a condition of the patient during the clinical procedure, wherein the analyzing comprises automatically determining whether the observed condition of the patient indicates that the patient suffered a complication of the clinical procedure, and wherein generating the text report comprises, in response to determining that the observed condition indicates that the patient suffered a complication of the clinical procedure, automatically generating text stating that the condition was observed as a complication.

6. The method of claim 1, wherein the clinical procedure is performed on a patient, wherein the audio data comprises audio of the one or more clinical personnel orally identifying one or more substances administered to the patient in connection with the clinical procedure, and wherein generating the text report comprises automatically generating text stating that the one or more substances were administered.

7. Apparatus comprising:

at least one processor; and

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

transcribing audio data comprising audio of one or more clinical personnel speaking while performing a clinical procedure, the audio data comprising audio of a first clinician speaking to one or more other clinical personnel while performing the clinical procedure, wherein transcribing the audio data comprises performing automatic speech recognition (ASR) on the audio data using a speech recognition model trained to recognize speech of the first clinician;

analyzing the transcribed audio data, including the transcribed audio of the first clinician speaking to the one or more other clinical personnel while performing the clinical procedure, to identify relevant Information for documenting the clinical procedure; and

automatically generating a text report including the identified relevant information documenting the clinical procedure;

wherein identifying the relevant information comprises detecting within the transcribed audio data a present-tense narration by the first clinician stating to the other clinical personnel that the first clinician is currently performing a particular step of the clinical procedure;

wherein automatically generating the text report comprises automatically transforming the present-tense narration into a non-present-tense text portion in the report, stating that the particular step of the clinical procedure was performed.

8. The apparatus of claim 7, wherein the audio data comprises audio of the one or more clinical personnel orally identifying an instrument used in performing the clinical procedure, wherein the analyzing comprises automatically determining from the transcribed audio data a step of the clinical procedure performed using the instrument, and wherein generating the text report comprises automatically generating text stating that the determined step of the clinical procedure was performed.

9. The apparatus of claim 7, wherein the audio data comprises audio of the one or more clinical personnel orally identifying an action being performed during the clinical procedure, wherein the analyzing comprises automatically determining whether the action is part of a step of the clinical procedure that is relevant for documenting the clinical procedure, and wherein generating the text report comprises, in response to determining that the action is part of a step of the clinical procedure that is relevant for documenting the clinical procedure, automatically generating text stating that the relevant step was performed.

10. The apparatus of claim 7, wherein the audio data comprises audio of the one or more clinical personnel orally identifying an event occurring during the clinical procedure, wherein the analyzing comprises automatically determining whether the event indicates that a patient suffered a complication of the clinical procedure, and wherein generating the text report comprises, in response to determining that the event indicates that the patient suffered a complication of the clinical procedure, automatically generating text stating that the event occurred as a complication.

11. The apparatus of claim 7, wherein the clinical procedure is performed on a patient, wherein the audio data comprises audio of the one or more clinical personnel orally identifying one or more observations of a condition of the patient during the clinical procedure, wherein the analyzing comprises automatically determining whether the observed condition of the patient indicates that the patient suffered a complication of the clinical procedure, and wherein generating the text report comprises, in response to determining that the observed condition indicates that the patient suffered a complication of the clinical procedure, automatically generating text stating that the condition was observed as a complication.

12. The apparatus of claim 7, wherein the clinical procedure is performed on a patient, wherein the audio data comprises audio oldie one or more clinical personnel orally identifying one or more substances administered to the patient in connection with the clinical procedure, and wherein generating the text report comprises automatically generating text stating that the one or more substances were administered.

13. The apparatus of claim 7, wherein the analyzing comprises identifying the relevant information based at least in part on patient monitoring data recorded using monitoring equipment during the clinical procedure.

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

transcribing audio data comprising audio of one or more clinical personnel speaking while performing a clinical procedure, the audio data comprising audio of a first clinician speaking to one or more other clinical personnel while performing the clinical procedure, wherein transcribing the audio data comprises performing automatic speech recognition (ASR) on the audio data using a speech recognition model trained to recognize speech of the first clinician;

analyzing the transcribed audio data, including the transcribed audio of the first clinician speaking to the one or more other clinical personnel while performing the clinical procedure, to identify relevant information for documenting the clinical procedure; and

automatically generating a text report including the identified relevant information documenting the clinical procedure;

wherein identifying the relevant information comprises detecting within the transcribed audio data a present-tense narration by the first clinician stating to the other clinical personnel that the first clinician is currently performing a particular step of the clinical procedure;

wherein automatically generating the text report comprises automatically transforming the present-tense narration into a non-present-tense text portion in the report, stating that the particular step of the clinical procedure was performed.

15. The at least one non-transitory computer-readable storage medium of claim 14, wherein the audio data comprises audio of the one or more clinical personnel orally identifying an instrument used in performing the clinical procedure, wherein the analyzing comprises automatically determining from the transcribed audio data a step of the clinical procedure performed using the instrument, and wherein generating the text report comprises automatically generating text stating that the determined step of the clinical procedure was performed.

16. The at least one non-transitory computer-readable storage medium of claim 14, wherein the audio data comprises audio of the one or more clinical personnel orally identifying an action being performed during the clinical procedure, wherein the analyzing comprises automatically determining whether the action is part of a step of the clinical procedure that is relevant for documenting the clinical procedure, and wherein generating the text report comprises, in response to determining that the action is part of a step of the clinical procedure that is relevant for documenting the clinical procedure, automatically generating text stating that the relevant step was performed.

17. The at least one non-transitory computer-readable storage medium of claim 14, wherein the audio data comprises audio of the one or more clinical personnel orally identifying an event occurring during the clinical procedure, wherein the analyzing comprises automatically determining whether the event indicates that a patient suffered a complication of the clinical procedure, and wherein generating the text report comprises, in response to determining that the event indicates that the patient suffered a complication of the clinical procedure, automatically generating text stating that the event occurred as a complication.

18. The at least one non-transitory computer-readable storage medium of claim 14, wherein the clinical procedure is performed on a patient, wherein the audio data comprises audio of the one or more clinical personnel orally identifying one or more observations of a condition of the patient during the clinical procedure, wherein the analyzing comprises automatically determining whether the observed condition of the patient indicates that the patient suffered a complication of the clinical procedure, and wherein generating the text report comprises, in response to determining that the observed condition indicates that the patient suffered a complication of the clinical procedure, automatically generating text stating that the condition was observed as a complication.

19. The at least one non-transitory computer-readable storage medium of claim 14, wherein the clinical procedure is performed on a patient, wherein the audio data comprises audio of the one or more clinical personnel orally identifying one or more substances administered to the patient in connection with the clinical procedure, and wherein generating the text report comprises automatically generating text stating that the one or more substances were administered.

20. The at least one non-transitory computer-readable storage medium of claim 14, wherein the analyzing comprises identifying the relevant information based at least in part on patient monitoring data recorded using monitoring equipment during the clinical procedure.