Dynamically configurable interface for structured note dictation for multiple EHR systems

• US 10,650,808 B1
• Filed: 02/13/2018
• Issued: 05/12/2020
• Est. Priority Date: 02/14/2017
• Status: Active Grant

• Current Assignee: Aging of America Group, Inc.
• Original Assignee: NoteSwift, Inc. (Aging of America Group, Inc.)
• Inventors: Platt, Timothy, Stratton, Allan
• Primary Examiner(s): Abebe, Daniel
• Application Number:
  US15/895,361
• Time in Patent Office: 819 Days
• Field of Search: 704270
• CPC Class Codes: G06F 16/2468 Fuzzy queries
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• 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

Abstract

Systems and methods for providing a dynamically configurable interface for structured note dictation input for one or more electronic health record (EHR) systems generally comprise a dictation user interface, a dictation management subsystem, and at least one EHR system having a plurality of electronic medical records. The dictation management subsystem generally comprises a computing device configured to moderate the recognized text for a particular EHR system and particular electronic health record.

Claims

1. A system for dynamically-configurable SOAP (subjective, objective, assessment, and plan) note dictation, the system comprising:

a computing platform including computing hardware of at least one processor, a memory operably coupled to the at least one processor, and configured to store instructions invoked by the at least one processor;

instructions that, when executed on the computing platform, cause the computing platform to implement;

a dictation user interface including an abstraction layer for programmatic access to a speech-to-text recognition component and configured to receive user-dictated clinical document data as a SOAP note; and

a dictation management subsystem including;

a segmenter engine configured to receive as input the user-dictated clinical document data and segment the clinical document data into a plurality of lines and tokens and identify a plurality of section headers for the SOAP note;

a parser engine configured to receive the plurality of lines and tokens from the segmenter engine and access one or more databases limited by at least one characteristic of a particular section header for the SOAP note, the particular section header corresponding to a particular plurality of lines and tokens to match the plurality of lines and tokens to a plurality of meaningful medical phrases using fuzzy matching to create a plurality of exact match entries and at least one non-exact match entry, the fuzzy matching including at least one rule corresponding to the particular section header for the SOAP note;

a correction engine configured to determine possible ambiguities for the at least one non-exact match entry based on the fuzzy matching, and

a presentation engine configured to

present a correction window on a graphical user interface, the correction window including the at least one non-exact match entry and a list of potential corrections derived from the fuzzy matching, and

receive a user-selection of one of the list of potential corrections for the at least one non-exact match entry that is used to generate corrected clinical document data for the SOAP note;

an electronic health record (EHR) query engine configured to enter the SOAP note including the corrected clinical document data and the plurality of exact match entries into an electronic health record.

2. The system of claim 1, wherein the dictation management subsystem further comprises a matcher engine configured to conduct fuzzy matching by scoring the plurality of lines and tokens against the plurality of meaningful medical phrases from the one or more databases.

3. The system of claim 2, wherein the matcher engine is further configured to conduct ranking a particular set of lines and tokens against the meaningful medical phrases to indicate a closeness of the particular set of lines and tokens to the plurality of meaningful medical phrases.

4. The system of claim 3, wherein the matcher engine is further configured to add at least one line or token to the particular set of lines and tokens and re-score the particular set of lines and tokens against the plurality of meaningful medical phrases.

5. The system of claim 3, wherein the matcher engine is further configured to remove at least one line or token from the particular set of lines and tokens and re-score the particular set of lines and tokens against the plurality of meaningful medical phrases.

6. The system of claim 2, wherein the matcher engine is further configured to compare the plurality of lines and tokens having an m-element sequence of items to one of the plurality of meaningful medical phrases having an n-element sequence of items, and wherein the scoring includes

a measure of how the elements in the m-element sequence of items match the n-element sequence of items, and

a measure of the how the ordering of the m-element sequence of items match the n-element sequence of items.

7. The system of claim 2, wherein the matcher engine is further configured with a set of rules, the set of rules used in scoring the plurality of lines and tokens against the plurality of meaningful medical phrases including at least one of:

a one-to-one replacement rule,

a one-for-empty deletion rule, and

a replacement rule.

8. The system of claim 1, wherein the correction engine determines the at least one non-exact match entries below a threshold value based on the fuzzy matching.

9. The system of claim 1, wherein the list of potential corrections derived from the fuzzy matching is sorted in order of decreasing closeness.

10. A machine-implemented method for dynamically-configurable SOAP (subjective, objective, assessment, and plan) note dictation for a computing system, the computing system including computing hardware of at least one processor and a memory operably coupled to the at least one processor, the method comprising:

presenting a dictation user interface with the computing hardware, the dictation user interface including an abstraction layer for programmatic access to a speech-to-text recognition component;

receiving user-dictated clinical document data as a SOAP note from the dictation user interface;

performing segmenting and parsing of the clinical document data with the computing hardware to generate a segmented and parsed clinical document dataset and identify a plurality of section headers for the SOAP note, the segmented and parsed clinical document dataset including a plurality of lines and tokens;

performing fuzzy matching on the plurality of lines and tokens with the computing hardware including implementing at least one rule corresponding to the particular section header for the SOAP note, the particular section header corresponding to a particular plurality of lines and tokens to determine known clinical entries and a set of non-exact match entries by comparison to a plurality of meaningful medical phrases limited by at least one characteristic of a particular section header for the SOAP note;

presenting a correction window on a graphical user interface with the computing hardware, the correction window including at least one non-exact match entry in the segmented and parsed clinical document dataset and a list of potential corrections derived from the fuzzy matching;

receiving a user-selection of one of the potential corrections for the at least one non-exact match entry that is used to generate corrected clinical document data; and

entering, with the computing hardware, the known clinical entries and the corrected clinical document data as the SOAP note into an electronic health record (EHR).

11. The machine-implemented method of claim 10, wherein performing fuzzy matching further comprises scoring the plurality of lines and tokens against the plurality of meaningful medical phrases from the one or more databases.

12. The machine-implemented method of claim 11, wherein the scoring further comprises ranking a particular set of lines and tokens against the meaningful medical phrases to indicate the closeness of the particular set of lines and tokens to the plurality of meaningful medical phrases.

13. The machine-implemented method of claim 12, further comprising adding at least one line or token to the particular set of lines and tokens and re-scoring the particular set of lines and tokens against the plurality of meaningful medical phrases.

14. The machine-implemented method of claim 12, further comprising removing at least one line or token from the particular set of lines and tokens and re-scoring the particular set of lines and tokens against the plurality of meaningful medical phrases.

15. The machine-implemented method of claim 11, wherein the scoring further comprises comparing the plurality of lines and tokens having an m-element sequence of items to one of the plurality of meaningful medical phrases having an n-element sequence of items, wherein the scoring includes

a measure of how the elements in the m-element sequence of items match the n-element sequence of items, and

a measure of the how the ordering of the m-element sequence of items match the n-element sequence of items.

16. The machine-implemented method of claim 11, further comprising utilizing a set of rules for scoring the plurality of lines and tokens against the plurality of meaningful medical phrases including at least one of:

a one-to-one replacement rule,

a one-for-empty deletion rule, and

a replacement rule.

17. The machine-implemented method of claim 10, wherein the at least one non-exact match entry is determined to be below a threshold value based on the fuzzy matching.

18. The machine-implemented method of claim 10, wherein the list of potential corrections derived from the fuzzy matching is sorted in order of decreasing closeness.

19. A system for dynamically-configurable note dictation, the system comprising:

means for presenting a computing system, the computing system including computing hardware of at least one processor and a memory operably coupled to the at least one processor;

means for presenting a dictation user interface, the dictation user interface including an abstraction layer for programmatic access to a speech-to-text recognition component;

means for receiving user-dictated clinical document data from the dictation user interface;

means for performing segmenting and parsing of the clinical document data with the computing hardware to generate a segmented and parsed clinical document dataset and identify a plurality of section headers for the SOAP note, the segmented and parsed clinical document dataset including a plurality of lines and tokens;

means for performing fuzzy matching on the plurality of lines and tokens with the computing hardware including implementing at least one rule corresponding to the particular section header for the SOAP note, the particular section header corresponding to a particular plurality of lines and tokens to determine known clinical entries and a set of non-exact match entries based on at least one database query limited by at least one characteristic of a particular section header for the SOAP note;

means for presenting a correction window on a graphical user interface with the computing hardware, the correction window including at least one non-exact match entry in the segmented and parsed clinical document dataset and a list of potential corrections derived from the fuzzy matching;

means for receiving a user-selection of one of the potential corrections for the at least one non-exact match entry as corrected clinical document data; and

means for entering, with the computing hardware, the known clinical entries and the corrected clinical document data into an electronic health record (EHR).

20. The system of claim 19, wherein the dictation management subsystem further comprises a means for conducting fuzzy matching by scoring the plurality of lines and tokens against the plurality of meaningful medical phrases from the one or more databases, wherein the scoring further comprises a means for ranking a particular set of lines and tokens against the meaningful medical phrases to indicate the closeness of the particular set of lines and tokens to the plurality of meaningful medical phrases.