Driving patient campaign based on trend patterns in patient registry information

• US 10,437,957 B2
• Filed: 02/17/2016
• Issued: 10/08/2019
• Est. Priority Date: 02/17/2016
• Status: Active Grant

• Current Assignee: Merative US LP
• Original Assignee: International Business Machines Corporation
• Inventors: Cox, James S., DiGiorgio, Anthony J.
• Primary Examiner(s): Tomaszewski, Michael
• Assistant Examiner(s): Patel, Jay M.
• Application Number:
  US15/045,387
• Publication Number:
  US 20170235894A1
• Time in Patent Office: 1,329 Days
• Field of Search: None
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 20/40 relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
• CPC Class Codes: G16H 40/20 for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 70/20 relating to practices or guidelines

Abstract

A medical campaign method, computer program product, and system are provided. A patient registry record in a patient registry is analyzed to identify at least one trend of a clinical measure for a corresponding patient and correlate the at least one trend with one or more medical campaigns directed to improving the clinical measure. A medical campaign is selected from the one or more medical campaigns for application to the patient. The medical campaign is executed to apply the medical campaign to the patient. Executing the medical campaign involves sending a communication to a communication device associated with the patient.

Claims

1. A method, in a data processing system comprising a processor and a memory, for executing a medical campaign, comprising:

training, by a pattern/trend learning engine of a patient campaign system of the data processing system, via a machine learning operation executed on a corpus of electronic medical information, a pattern/trend analysis engine of the patient campaign system to identify at least one of patterns of medical codes, patterns of patient cohort membership transitions, or patterns in patient characteristics or patient activities, that correlate with criteria specified in predefined medical campaign records of a medical campaign database;

analyzing, by the pattern/trend analysis engine of the patient campaign system of the data processing system, a patient registry record in a patient registry to identify at least one trend of a clinical measure for a corresponding patient;

correlating, by the pattern/trend analysis engine of the patient campaign system of the data processing system, the at least one trend with one or more medical campaigns, specified in predefined medical campaign records in the medical campaign database, directed to improving the clinical measure, based on results of the machine learning operation and application of learned correlations between at least one of patterns of medical codes, patterns of patient cohort membership transitions, or patterns in patient characteristics or patient activities, with the criteria specified in the predefined medical campaign records of the medical campaign database;

selecting, by a patient campaign selection engine of the patient campaign system of the data processing system, a medical campaign from the one or more medical campaigns for application to the patient, wherein the medical campaign is a selected medical campaign that specifies a computer executable workflow that comprises at least one transmission of a communication to the corresponding patient; and

executing, by the patient campaign system of the data processing system, the medical campaign to apply the medical campaign to the patient, wherein executing the medical campaign comprises transmitting, by a communication system of the data processing system, the communication to a communication device associated with the corresponding patient.

2. The method of claim 1, wherein the medical campaign comprises one or more intervention actions, for intervening in management of the patient'"'"'s health, which are performed in response to executing the medical campaign.

3. The method of claim 1, wherein the medical campaign comprises an executable workflow applicable to a plurality of patients and having campaign criteria specifying attributes of patients for which the medical campaign is designed to be applicable.

4. The method of claim 3, wherein the campaign criteria specifies at least one patient cohort with which patients are to be associated for the medical campaign to be applicable to the patient.

5. The method of claim 1, wherein executing the medical campaign comprises at least one of:

initiating a human assessor communicating with the patient regarding the patient'"'"'s health and an intervention associated with the medical campaign;

scheduling an office appointment with medical personnel;

scheduling a medical lab test;

or

sending an automated communication to gain additional information and perform an action to initiate or engage in a treatment associated with the medical campaign.

6. The method of claim 1, wherein executing the medical campaign comprises creating a new personalized patient care plan for the patient or modifying an existing personalized patient care plan associated with the patient.

7. The method of claim 1, wherein analyzing the patient registry record in the patient registry to identify the at least one trend of the clinical measure for the corresponding patient comprises identifying a pattern in the patient registry record of at least one of medical codes, patient cohort membership transitions, patient characteristics, or patient activities.

8. The method of claim 7, wherein identifying the pattern in the patient registry record comprises:

comparing features extracted from the patient registry record to a plurality of patterns of features learned over time through a machine learning process applied to a plurality of patient registry records; and

determining which patterns in the plurality of patterns of features are matched by the features extracted from the patient registry record, wherein matched patterns indicate a trend of the extracted features from the patient registry record.

9. The method of claim 8, wherein different medical campaigns in the one or more medical campaigns are associated with different patterns of features in the plurality of patterns of features.

10. The method of claim 1, wherein analyzing the patient registry record in the patient registry to identify the at least one trend of a clinical measure for the corresponding patient comprises identifying the at least one trend as a pattern of transitions of membership of the corresponding patient between a plurality of patient cohorts indicating a trend of a medical condition of the corresponding patient not being properly managed by the corresponding patient.

11. A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to implement a patient campaign system which operates to:

train, by a pattern/trend learning engine of the patient campaign system of the data processing system, via a machine learning operation executed on a corpus of electronic medical information, a pattern/trend analysis engine of the patient campaign system to identify at least one of patterns of medical codes, patterns of patient cohort membership transitions, or patterns in patient characteristics or patient activities, that correlate with criteria specified in predefined medical campaign records of a medical campaign database;

analyze, by the pattern/trend analysis engine of the patient campaign system, a patient registry record in a patient registry to identify at least one trend of a clinical measure for a corresponding patient;

correlate, by the pattern/trend analysis engine of the patient campaign system, the at least one trend with one or more medical campaigns, specified in predefined medical campaign records in the medical campaign database, directed to improving the clinical measure, based on results of the machine learning, operation and application of learned correlations between at least one of patterns of medical codes, patterns of patient cohort membership transitions, or patterns in patient characteristics or patient activities, with the criteria specified in the predefined medical campaign records of the medical campaign database;

select, by a patient campaign selection engine of the patient campaign system, a medical campaign from the one or more medical campaigns for application to the patient, wherein the medical campaign is a selected medical campaign that specifies a computer executable workflow that comprises at least one transmission of a communication to the corresponding patient; and

execute the medical campaign to apply the medical campaign to the patient, wherein executing the medical campaign comprises transmitting, by a communication system of the data processing system, the communication to a communication device associated with the corresponding patient.

12. The computer program product of claim 11, wherein the medical campaign comprises one or more intervention actions, for intervening in management of the patient'"'"'s health, which are performed in response to executing the medical campaign.

13. The computer program product of claim 11, wherein the medical campaign comprises an executable workflow applicable to a plurality of patients and having campaign criteria specifying attributes of patients for which the medical campaign is designed to be applicable.

14. The computer program product of claim 13, wherein the campaign criteria specifies at least one patient cohort with which patients are to be associated for the medical campaign to be applicable to the patient.

15. The computer program product of claim 11, wherein the medical campaign system further operates to execute the medical campaign by at least one of:

initiating a human assessor communicating with the patient regarding the patient'"'"'s health and an intervention associated with the medical campaign;

scheduling an office appointment with medical personnel;

scheduling a medical lab test;

or

sending an automated communication to gain additional information and perform an action to initiate or engage in a treatment associated with the medical campaign.

16. The computer program product of claim 11, wherein the medical campaign system executes the medical campaign at least by creating a new personalized patient care plan for the patient or modifying an existing personalized patient care plan associated with the patient.

17. The computer program product of claim 11, wherein the medical campaign system analyzes the patient registry record in the patient registry to identify the at least one trend of the clinical measure for the corresponding patient at least by identifying a pattern in the patient registry record of at least one of medical codes, patient cohort membership transitions, patient characteristics, or patient activities.

18. The computer program product of claim 17, wherein the medical campaign system identifies the pattern in the patient registry record at least by:

comparing features extracted from the patient registry record to a plurality of patterns of features learned over time through a machine learning process applied to a plurality of patient registry records; and

determining which patterns in the plurality of patterns of features are matched by the features extracted from the patient registry record, wherein matched patterns indicate a trend of the extracted features from the patient registry record.

19. The computer program product of claim 11, wherein the medical campaign system analyzes the patient registry record in the patient registry to identify the at least one trend of a clinical measure for the corresponding patient at least by identifying the at least one trend as a pattern of transitions of membership of the corresponding patient between a plurality of patient cohorts indicating a trend of a medical condition of the corresponding patient not being properly managed by the corresponding patient.

20. An apparatus comprising:

a processor; and

a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to implement a patient campaign system which operates to;

train, by a pattern/trend learning engine of the patient campaign system of the data processing system, via a machine learning operation executed on a corpus of electronic medical information, a pattern/trend analysis engine of the patient campaign system to identify at least one of patterns of medical codes, patterns of patient cohort membership transitions, or patterns in patient characteristics or patient activities, that correlate with criteria specified in predefined medical campaign records of a medical campaign database;

analyze, by the pattern/trend analysis engine of the patient campaign system, a patient registry record in a patient registry to identify at least one trend of a clinical measure for a corresponding patient;

correlate, by the pattern/trend analysis engine of the patient campaign system, the at least one trend with one or more medical campaigns, specified in predefined medical campaign records in the medical campaign database, directed to improving the clinical measure, based on results of the machine learning operation and application of learned correlations between at least one of patterns of medical codes, patterns of patient cohort membership transitions, or patterns in patient characteristics or patient activities, with the criteria specified in the predefined medical campaign records of the medical campaign database;

select, by a patient campaign selection engine of the patient campaign system, a medical campaign from the one or more medical campaigns for application to the patient, wherein the medical campaign is a selected medical campaign that specifies a computer executable workflow that comprises at least one transmission of a communication to the corresponding patient; and

execute the medical campaign to apply the medical campaign to the patient, wherein executing the medical campaign comprises transmitting, by a communication system of the data processing system, the communication to a communication device associated with the corresponding patient.