Process action determination

• US 10,296,187 B1
• Filed: 04/04/2017
• Issued: 05/21/2019
• Est. Priority Date: 04/04/2016
• Status: Active Grant

• Current Assignee: C-HCA, Inc.
• Original Assignee: HCA Holdings Incorporated (HCA Healthcare, Inc.)
• Inventors: Gregg, William Michael, Kehler, Karl Bradley, Brient, Paul, Doyle, Thomas Andrew, Krayer, Christian, Jirjis, Jim Najib, Perlin, Jonathan, Paslick, Paul Martin, Jackson, Edmund Stephen, Buta, Sarah Hume, Jospe, Erin S., Phirke, Umesh P.
• Primary Examiner(s): Silverman, Seth A
• Application Number:
  US15/479,011
• Time in Patent Office: 777 Days
• CPC Class Codes: G06F 16/24532 of parallel queries
• CPC Class Codes: G06F 16/24568 Data stream processing; Continuous queries
• CPC Class Codes: G06F 16/284 Relational databases
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30

Abstract

In some examples, a documentation service is provided in which documentation may be entered and process actions presented. The process actions can be determined by processing the documentation using a natural language processing technique and suggested to a professional user for performance or validation.

Claims

1. A system, comprising:

a memory that stores computer-executable instructions; and

at least one processor configured to access the memory and execute the computer-executable instructions to at least;

provide a documentation user interface for presentation at a user device, the documentation user interface comprising a documentation area and a medical order area;

gather documentation, which comprises unstructured data, at least in part by;

permitting a medical professional to use the documentation user interface to input medical documentation at the documentation area, wherein;

the documentation area defines an area configured for the medical professional to input the medical documentation as medical note entries that describe a plurality of visits between the medical professional and a patient; and

the medical order area defines an area configured for presenting notifications about future medical orders that are automatically and contemporaneously suggested based on the medical note entries input by the medical professional at the documentation area;

accessing the medical documentation input by the medical professional at the documentation area of the documentation user interface; and

accessing an output from a computerized treatment machine that provided medical-related treatment to the patient, the output being associated with treatment of the patient and being in an unstructured format;

wherein the unstructured data corresponds to the medical documentation input via the documentation user interface and the output from the computerized treatment machine;

analyze the documentation with an unstructured data analysis engine at least partially by parsing subjective data corresponding to the unstructured data to identify one or both of tone and sentiment in the subjective data, where the unstructured data comprises voice data and the analyzing the documentation comprises processing at least a portion of the medical documentation using a natural language processing technique to extract a set of future medical order indicators from the portion of the medical documentation, the set of future medical order indicators being indicative of one or more of a plurality of future medical orders performable with respect to patients;

compute a score for each future medical order indicator of the set of future medical order indicators;

select one or more knowledge artifacts based on the set of future medical order indicators;

determine, using a process action determination engine including a predefined suggestion engine that is executed without querying records of other patients, a particular future medical order to be performed with respect to the patient, wherein the particular future medical order is determined based on the scores of the future medical order indicators of the set of future medical order indicators, the output from the computerized treatment machine, and the one or more knowledge artifacts, and wherein the particular future medical order is described by the medical professional in at least one medical note entry of the medical note entries input at the documentation area contemporaneously with at least one visit of the plurality of visits;

add the particular future medical order to a digital repository of future medical orders; and

provide a notification for presentation at the medical order area of the documentation user interface, the notification identifying the particular future medical order and indicating that the particular future medical order is available in the digital repository of future medical orders for review by the medical professional.

2. The system of claim 1, wherein the natural language processing technique is performed and the notification is provided for presentation at the medical order area of the documentation user interface at least while the medical professional is inputting the medical documentation at the documentation area of the documentation user interface.

3. The system of claim 1, wherein the at least one processor is further configured to access the memory and execute the computer-executable instructions to at least:

receive information indicating selection of the particular future medical order by the medical professional; and

in response to receiving the information, populate one or more fields of an order form that can be provided to a different medical professional to instruct the different medical professional to fulfill the particular future medical order.

4. The system of claim 1, wherein the medical documentation further comprises structured data.

5. The system of claim 1, wherein:

the at least one processor is further configured to access the memory and execute the computer-executable instructions to at least determine professional user information associated with the medical professional who contributed at least the portion of the medical documentation, the professional user information representative of at least one of a first characteristic of the medical professional or a second characteristic shared by a group of medical professionals that is similar to the medical professional; and

determining the particular future medical order is further based at least in part on the professional user information.

6. The system of claim 5, wherein:

the at least one processor is further configured to access the memory and execute the computer-executable instructions to at least determine patient information associated with the patient, the patient information representative of at least one of a third characteristic of the patient or a fourth characteristic shared by a group of patients that is similar to the patient; and

determining the particular future medical order is further based at least in part on the patient information.

7. The system of claim 1, wherein:

determining the particular future medical order comprises determining a second future medical order that is related to the particular future medical order; and

the at least one processor is further configured to access the memory and execute the computer-executable instructions to at least add the second future medical order to the digital repository of future medical orders.

8. The system of claim 7, wherein the at least one processor is further configured to access the memory and execute the computer-executable instructions to at least:

receive information indicating selection of the particular future medical order by the medical professional; and

in response to receiving the information, send the particular future medical order and the second future medical order to a different medical professional for performance of the particular future medical order and the second future medical order.

9. The system of claim 1, wherein processing the portion of the medical documentation using the natural language processing technique comprises processing the portion of the medical documentation using a predefined suggestion engine that is executed without querying records of other patients.

10. A computer-implemented method, comprising:

receiving a set of future medical order indicators indicative of one or more of a plurality of future medical orders performable with respect to patients, the set of future medical order indicators determined by at least;

gathering documentation, which comprises unstructured data, at least in part by;

accessing medical documentation describing at least one visit between a medical professional and a patient, the medical documentation comprising part of the unstructured data that is input by the medical professional at a documentation user interface during a time period, wherein the documentation user interface comprises;

a documentation area defining an area configured for the medical professional to input the medical documentation as medical note entries that describe a plurality of visits between the medical professional and the patient; and

a medical order area defining an area configured for presenting notifications about future medical orders that are automatically and contemporaneously suggested based on the medical note entries input by the medical professional at the documentation area; and

accessing an output from a computerized treatment machine that provided medical-related treatment to the patient, the output being associated with treatment of the patient and being in an unstructured format;

wherein the unstructured data corresponds to the medical documentation input via the documentation user interface and the output from the computerized treatment machine; and

analyzing the documentation with an unstructured data analysis engine at least partially by parsing subjective data corresponding to the unstructured data to identify one or both of tone and sentiment in the subjective data, where the unstructured data comprises voice data and the analyzing the documentation comprises processing, during the time period or after the time period, at least a portion of the medical documentation using a natural language processing technique to extract the set of future medical order indicators from the portion of the medical documentation;

computing a score for each future medical order indicator of the set of future medical order indicators;

selecting one or more knowledge artifacts based on the set of future medical order indicators;

determining, using a process action determination engine including a predefined suggestion engine that is executed without querying records of other patients, a particular future medical order to be performed with respect to the patient, wherein the particular future medical order is determined based on the scores of the future medical order indicators of the set of future medical order indicators, the output from the computerized treatment machine, and the one or more knowledge artifacts, and wherein the particular future medical order is described by the medical professional in at least one medical note entry of the medical note entries input at the documentation area contemporaneously with the at least one visit;

adding the particular future medical order to a digital repository of future medical orders;

providing a notification for presentation at the medical order area of the documentation user interface, the notification identifying the particular future medical order and indicating that the particular future medical order is available in the digital repository of future medical orders for review by the medical professional; and

receiving information indicating selection of the particular future medical order by the medical professional.

11. The computer-implemented method of claim 10, wherein the natural language processing technique is performed and the notification provided for presentation at the medical order area at least while the medical professional is inputting the medical documentation at the documentation area of the documentation user interface.

12. The computer-implemented method of claim 10, wherein:

the method further comprises determining professional user information associated with the medical professional who contributed to at least the portion of the medical documentation, the professional user information representative of at least one of a first characteristic of the medical professional or a second characteristic shared by a group of medical professionals that is similar to the medical professional; and

determining the particular future medical order is further based at least in part on the professional user information.

13. The computer-implemented method of claim 10, wherein:

the method further comprises determining patient information associated with the patient, the patient information representative of at least one of a first characteristic of the patient or a second characteristic shared by a group of patients that is similar to the patient; and

determining the particular future medical order is further based at least in part on the patient information.

14. The computer-implemented method of claim 10, wherein receiving the information indicating selection of the particular future medical order causes the particular future medical order to be sent to a different medical professional or an entity for performance.

15. The computer-implemented method of claim 10, wherein receiving the information indicating selection of the particular future medical order comprises receiving a relevance rating from the medical professional of the particular future medical order with respect to the medical documentation.

16. The computer-implemented method of claim 15, wherein the relevance rating is used as feedback for a natural language processing model used when the natural language processing technique is performed.

17. One or more non-transitory, computer-readable storage devices for storing computer-executable instructions that, when executed by one or more computer systems, configure the one or more computer systems to perform operations comprising:

receiving a set of future medical order indicators indicative of one or more of a plurality of future medical orders performable with respect to patients, the set of future medical order indicators determined by at least;

gathering documentation, which comprises unstructured data, at least in part by;

accessing medical documentation describing at least one visit between a medical professional and a patient, the medical documentation comprising part of the unstructured data that is input by the medical professional at a documentation user interface during a time period, wherein the documentation user interface comprises;

a documentation area defining an area configured for the medical professional to input the medical documentation as medical note entries that describe a plurality of visits between the medical professional and the patient; and

a medical order area defining an area configured for presenting notifications about future medical orders that are automatically and contemporaneously suggested based on the medical note entries input by the medical professional at the documentation area; and

accessing an output from a computerized treatment machine that provided medical-related treatment to the patient, the output being associated with treatment of the patient and being in an unstructured format;

wherein the unstructured data corresponds to the medical documentation input via the documentation user interface and the output from the computerized treatment machine;

analyzing the documentation with an unstructured data analysis engine at least partially by parsing subjective data corresponding to the unstructured data to identify one or both of tone and sentiment in the subjective data, where the unstructured data comprises voice data and the analyzing the documentation comprises processing at least a portion of the medical documentation using a natural language processing technique to extract the set of future medical order indicators from the portion of the medical documentation;

computing a score for each future medical order indicator of the set of future medical order indicators;

selecting one or more knowledge artifacts based on the set of future medical order indicators;

determining, using a process action determination engine including a predefined suggestion engine that is executed without querying records of other patients, a particular future medical order to be performed with respect to the patient, wherein the particular future medical order is determined based on the scores of the future medical order indicators of the set of future medical order indicators, professional user information, the output from the computerized treatment machine, and the one or more knowledge artifacts, and wherein the particular future medical order is described by the medical professional in at least one medical note entry of the medical note entries input at the documentation area contemporaneously with the at least one visit;

adding the particular future medical order to a digital repository of future medical orders; and

providing a notification for presentation at the medical order area of the documentation user interface, the notification identifying the particular future medical order and indicating that the particular future medical order is available in the digital repository of future medical orders for review by the medical professional.

18. The one or more non-transitory, computer-readable storage devices of claim 17, wherein:

the operations further comprise accessing patient information associated with the patient, the patient information representative of at least one of a third characteristic of the patient or a fourth characteristic shared by a group of patients that is similar to the patient; and

determining the particular future medical order is further based on the patient information.

19. The one or more non-transitory, computer-readable storage devices of claim 17, wherein the natural language processing technique is performed at least while the medical professional is preparing the medical documentation.

20. The one or more non-transitory, computer-readable storage devices of claim 17, wherein determining the professional user information is based on accessing a database that includes professional user information for a plurality of professional users.