Multi-modal communication with patients based on historical analysis

• US 10,528,702 B2
• Filed: 02/02/2016
• Issued: 01/07/2020
• Est. Priority Date: 02/02/2016
• Status: Active Grant

• Current Assignee: Merative US LP
• Original Assignee: International Business Machines Corporation
• Inventors: Cox, James S., Danks, Jacob R., DiGiorgio, Anthony J., Edwards, Alan C., Gattis, David J., Harmon, Jonathan M., Hill, Charles W., Jayantilal, Tushar Kumar, Patterson, William R., Sexton, James A.
• Primary Examiner(s): Go, John P
• Application Number:
  US15/012,887
• Publication Number:
  US 20170220757A1
• Time in Patent Office: 1,435 Days
• Field of Search: 705 2, 705 3, 705 4
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 40/67 for remote operation

Abstract

Mechanisms are provided for communicating with a patient. The mechanisms generate a patient registry comprising a plurality of patient registry records, each patient registry record being associated with a corresponding patient and comprising personal and medical information about the corresponding patient. The mechanisms collect, for each patient registry record, first data regarding treatment of the corresponding patient and second data regarding communications made with the corresponding patient. The mechanisms determine, based on analysis of the first data and second data associated with each of the patient registry records, a mode of communication that is most likely to result in a successful treatment of patients. The mechanisms initiate a communication with a patient of interest using the determined mode of communication based on the results of the determination.

Claims

1. A method, in a data processing system comprising a processor and a memory comprising instructions executed by the processor to configure the processor to implement a communication workflow engine, for communicating with a patient, comprising:

generating, by the communication workflow engine of the data processing system, a patient registry comprising a plurality of patient registry records, each patient registry record being associated with a corresponding patient and comprising personal and medical information about the corresponding patient;

collecting, by the communication workflow engine, for each patient registry record, first data regarding treatment of the corresponding patient and second data regarding communications made with the corresponding patient;

analyzing, by the communication workflow engine, the first data and second data for each patient registry record at least by parsing the patient registry record and performing pattern analysis to identify first patterns of communications followed by compliance events identified in the patient registry record, and second patterns of communications that are not followed by compliance events in the patient registry record, and scoring each communication mode of the communications based on a number of occurrences of the first patterns and a number of occurrences of the second patterns present in the patient registry record for that communication mode, such that a set of communication modes and corresponding scores are generated for each patient registry record;

determining, by the communication workflow engine, a first mode of communication that is a personal mode of communication for a patient of interest based on a first set of communication modes and corresponding scores generated by the analysis of the first data and second data for the patient of interest;

determining, by the communication workflow engine, based on one or more second sets of communication modes and corresponding scores generated by the analysis of the first data and second data associated with each of the patient registry records of one or more other patients across all of the patient registry records, a second mode of communication;

determining, by the communication workflow engine, a final mode of communication based on a weighted comparison of a first weighted score associated with the first mode of communication and a second weighted score associated with the second mode of communication, wherein the first mode of communication has a different weight factor than the second mode of communication in the weighted comparison; and

performing, by a communication system associated with the data processing system, a communication between the communication system and a communication device associated with the patient of interest using the determined final mode of communication.

2. The method of claim 1, wherein a first weight factor associated with the first mode of communication, used to generate the first weighted score, is a relatively higher weight than a second weight factor associated with the second mode of communication, used to generate the second weighted score, in the weighted comparison.

3. The method of claim 1, wherein a compliance event is an event in which a corresponding patient performs a compliance action associated with bringing the corresponding patient into compliance with a pre-defined personalized patient care plan associated with the corresponding patient.

4. The method of claim 1, wherein determining a first mode of communication comprises identifying a communication workflow comprising a sequence of modes of communication and a timing between communications based on the analysis of the first data and second data for the patient of interest.

5. The method of claim 1, wherein determining a first mode of communication for the patient of interest comprises selecting the first mode of communication from the first set of communication modes and corresponding scores at least based on an evaluation of a combination of the scores of the communication modes in the first set and at least one of preferences specified in a patient registry record associated with the patient of interest or communication consents specified in the patient registry record associated with the patient of interest, wherein the first mode of communication is a communication mode having a relatively highest corresponding score of the communication modes in the first set and which also matches at least one of a preference or a communication consent specified in the patient registry record.

6. The method of claim 1, wherein the patient registry records are patient registry records in the patient registry that are part of a patient cohort corresponding to the patient of interest, and wherein the patient registry comprises patient registry records that are not part of the patient cohort and wherein determining the second mode of communication comprises:

determining, for the patient cohort, a best mode of communication for corresponding patients associated with patient registry records grouped into the patient cohort by aggregating, for each communication mode in the one or more second sets of communication modes and corresponding scores, the corresponding scores for that communication mode across all of the patient registry records grouped the patient cohort to generate aggregate scores for each communication mode; and

selecting a communication mode having a relatively highest corresponding aggregate score as the best mode of communication and outputting the best mode of communication as the second mode of communication.

7. The method of claim 6, further comprising:

analyzing the patient registry record for the patient of interest to identify a medical condition of the patient of interest and an area of non-compliance of the patient of interest with an associated patient care plan; and

associating the patient of interest with the patient cohort based on the medical condition of the patient of interest and the area of non-compliance of the patient of interest, wherein the patient cohort comprises patient registry records associated with patients having a same medical condition as the patient of interest and for which the patients are compliant in the area of non-compliance of the patient of interest.

16. The method of claim 1, wherein generating the patient registry comprises:

obtaining, via an information communication interface of the data processing system, patient electronic medical record (EMR) data from a plurality of different sources of patient EMR data, via at least one data network coupled to the information communication interface, and

compiling the patient EMR data into entries of the patient registry in association with an identifier of a corresponding patient.

17. The method of claim 1, wherein analyzing, by the data processing system, the first data and second data for each patient registry record further comprises:

analyzing content of communications in the first patterns of communications and second patterns of communications to identify content characteristics of the first patterns of communications and second patterns of communications, wherein scoring each communication mode of the communications further comprises scoring each content characteristic based on occurrences of the content characteristic in the first patterns of communication and second patterns of communication, and wherein content of the communication performed with the communication device associated with the patient of interest is generated based on scores associated with the content characteristics.

18. The method of claim 17, wherein the content characteristics comprise template or script identifiers identifying pre-defined templates or scripts used to generate content for a corresponding communication.

19. The method of claim 17, wherein content characteristics comprise key words or key phrases extracted from natural language content of corresponding communications using natural language processing.

20. The method of claim 17, further comprising associating the content characteristics with personality characteristics of patients, wherein performing a communication with a communication device associated with the patient of interest further comprises generating content of the communication based on a correspondence between a content characteristic and a personality characteristic of the patient of interest based on the association of the content characteristics with personality characteristics of patients.

8. A computer program product comprising a non-transitory computer readable medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device implement a communication workflow engine that operates to:

generate a patient registry comprising a plurality of patient registry records, each patient registry record being associated with a corresponding patient and comprising personal and medical information about the corresponding patient;

collect, for each patient registry record, first data regarding treatment of the corresponding patient and second data regarding communications made with the corresponding patient;

analyze the first data and second data for each patient registry record at least by parsing the patient registry record and performing pattern analysis to identify first patterns of communications followed by compliance events identified in the patient registry record, and second patterns of communications that are not followed by compliance events in the patient registry record, and scoring each communication mode of the communications based on a number of occurrences of the first patterns and a number of occurrences of the second patterns present in the patient registry record for that communication mode, such that a set of communication modes and corresponding scores are generated for each patient registry record;

determine a first mode of communication that is a personal mode of communication for a patient of interest based on a first set of communication modes and corresponding scores generated by the analysis of the first data and second data for the patient of interest;

determine, based on one or more second sets of communication modes and corresponding scores generated by the analysis of the first data and second data associated with each of the patient registry records of one or more other patients across all of the patient registry records, a second mode of communication; and

determine a final mode of communication based on a weighted comparison of a first weighted score associated with the first mode of communication and a second weighted score associated with the second mode of communication, wherein the first mode of communication has a different weight factor than the second mode of communication in the weighted comparison, and wherein the computer readable program further causes the computing device to perform a communication, between a communication system associated with the computing device and a communication device associated with the patient of interest, using the determined final mode of communication.

9. The computer program product of claim 8, wherein a first weight factor associated with the first mode of communication, used to generate the first weighted score, is a relatively higher weight than a second weight factor associated with the second mode of communication, used to generate the second weighted score, in the weighted comparison.

10. The computer program product of claim 8, wherein a compliance event is an event in which a corresponding patient performs a compliance action associated with bringing the corresponding patient into compliance with a pre-defined personalized patient care plan associated with the corresponding patient.

11. The computer program product of claim 8, wherein the computer readable program further causes the communication workflow engine to determine a first mode of communication at least by identifying a communication workflow comprising a sequence of modes of communication and a timing between communications based on the analysis of the first data and second data for the patient of interest.

12. The computer program product of claim 8, wherein the computer readable program further causes the communication workflow engine to determine a first mode of communication for the patient of interest at least by selecting the first mode of communication from the first set of communication modes and corresponding scores at least based on an evaluation of a combination of the scores of the communication modes in the first set and at least one of preferences specified in a patient registry record associated with the patient of interest or communication consents specified in the patient registry record associated with the patient of interest, wherein the first mode of communication is a communication mode having a relatively highest corresponding score of the communication modes in the first set and which also matches at least one of a preference or a communication consent specified in the patient registry record.

13. The computer program product of claim 8, wherein the patient registry records are patient registry records in the patient registry that are part of a patient cohort corresponding to the patient of interest, and wherein the patient registry comprises patient registry records that are not part of the patient cohort, and wherein the computer readable program further causes the communication workflow engine to determine the second mode of communication at least by:

determining, for the patient cohort, a best mode of communication for corresponding patients associated with patient registry records grouped into the patient cohort by aggregating, for each communication mode in the one or more second sets of communication modes and corresponding scores the corresponding scores for that communication mode across all of that patient registry records grouped into the patient cohort to generate aggregate scores for each communication mode; and

selecting a communication mode having a relatively highest corresponding aggregate score as the best mode of communication and outputting the best mode of communication as the second mode of communication.

14. The computer program product of claim 13, wherein the computer readable program further causes the communication workflow engine to:

analyze the patient registry record for the patient of interest to identify a medical condition of the patient of interest and an area of non-compliance of the patient of interest with an associated patient care plan; and

associate the of interest with the patient cohort based on the medical condition of the patient of interest and the area of non-compliance of the patient of interest, wherein the patient cohort comprises patient registry records associated with patients having a same medical condition as the patient of interest and for which the patients are compliant in the area of non-compliance of the patient of interest.

15. 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 implement a communication workflow engine that operates to;

generate a patient registry comprising a plurality of patient registry records, each patient registry record being associated with a corresponding patient and comprising personal and medical information about the corresponding patient;

collect, for each patient registry record, first data regarding treatment of the corresponding patient and second data regarding communications made with the corresponding patient;

analyze the first data and second data for each patient registry record at least by parsing the patient registry record and performing pattern analysis to identify first patterns of communications followed by compliance events identified in the patient registry record, and second patterns of communications that are not followed by compliance events in the patient registry record, and scoring each communication mode of the communications based on a number of occurrences of the first patterns and a number of occurrences of the second patterns present in the patient registry record for that communication mode, such that a set of communication modes and corresponding scores are generated for each patient registry record;

determine a first mode of communication that is a personal mode of communication for a patient of interest based on a first set of communication modes and corresponding scores generated by the analysis of the first data and second data for the patient of interest;

determine, based on one or more second sets of communication modes and corresponding scores generated by the analysis of the first data and second data associated with each of the patient registry records of one or more other patients across all of the patient registry records, a second mode of communication; and

determine a final mode of communication based on a weighted comparison of a first weighted score associated with the first mode of communication and a second weighted score associated with the second mode of communication, wherein the first mode of communication has a different weight factor than the second mode of communication in the weighted comparison, and wherein the instructions further cause the communication system associated with the apparatus to perform a communication with a communication device associated with the patient of interest using the determined final mode of communication.