Automatic determination of underlying reasons for patient failures to adhere to patient care plans

1. A method comprising:

retrieving, by a processor, patient information for a patient, the patient information comprising a treatment plan;

determining, by the processor, from the patient information a failure of compliance with the treatment plan by the patient;

generating one or more predetermined rules by association learning, where each of the one or more predetermined rules define a causal relationship between an element of the patient information and the failure of compliance, wherein association learning comprises applying a rule-based machine learning system to a plurality of causes of failure and a plurality of adherence failures, the failure of compliance being one of the plurality of adherence failures;

determining, by the processor, one or more potential cause of the failure of compliance by comparing the one or more predetermined rules with the patient information and cross-correlating information from a plurality of sources;

determining a ranked list of the one or more potential cause of the failure of compliance, the ranked list based on frequency in a general population;

determining responsible relationships for each of the one or more potential cause of the failure of compliance by analyzing express relationships from social media or by sentiment analysis of messages; and

providing the ranked list and the responsible relationships to a user for review.

2. The method of claim 1 , wherein the patient information further comprises an electronic health record, biometric data, location data, calendar data, or social media data.

3. The method of claim 1 , wherein the patient information comprises structured and unstructured data.

4. The method of claim 1 , wherein the treatment plan comprises a pharmaceutical dosage regimen.

5. The method of claim 1 , wherein determining the failure of compliance comprises comparing one or more treatment event of the patient information with the treatment plan.

6. The method of claim 1 , wherein retrieving the patient information comprises applying natural language processing to unstructured textual data.

7. The method of claim 1 , wherein the ranked list is provided for review on a mobile device.

8. A system comprising:

a computing node comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor of the computing node to cause the processor to perform a method comprising:

retrieving patient information for a patient, the patient information comprising a treatment plan;

determining from the patient information a failure of compliance with the treatment plan by the patient;

generating one or more predetermined rules by association learning, where each of the one or more predetermined rules define a causal relationship between an element of the patient information and the failure of compliance, wherein association learning comprises applying a rule-based machine learning system to a plurality of causes of failure and a plurality of adherence failures, the failure of compliance being one of the plurality of adherence failures;

determining one or more potential cause of the failure of compliance by comparing the one or more predetermined rules with the patient information and cross-correlating information from a plurality of sources;

determining a ranked list of the one or more potential cause of the failure of compliance, the ranked list based on frequency in a general population;

determining responsible relationships for each of the one or more potential cause of the failure of compliance by analyzing express relationships from social media or by sentiment analysis of messages; and

providing the ranked list and the responsible relationships to a user for review.

9. A computer program product for determining underlying reasons for lack of treatment adherence, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:

retrieving patient information for a patient, the patient information comprising a treatment plan;

determining from the patient information a failure of compliance with the treatment plan by the patient;

generating one or more predetermined rules by association learning, where each of the one or more predetermined rules define a causal relationship between an element of the patient information and the failure of compliance, wherein association learning comprises applying a rule-based machine learning system to a plurality of causes of failure and a plurality of adherence failures, the failure of compliance being one of the plurality of adherence failures;

determining one or more potential cause of the failure of compliance by comparing the one or more predetermined rules with the patient information and cross-correlating information from a plurality of sources;

determining a ranked list of the one or more potential cause of the failure of compliance, the ranked list based on frequency in a general population;

determining responsible relationships for each of the one or more potential cause of the failure of compliance by analyzing express relationships from social media or by sentiment analysis of messages; and

providing the ranked list and the responsible relationships to a user for review.

10. The computer program product of claim 9 , wherein the patient information further comprises an electronic health record, biometric data, location data, calendar data, or social media data.

11. The computer program product of claim 9 , wherein the patient information comprises structured and unstructured data.

12. The computer program product of claim 9 , wherein the treatment plan comprises a pharmaceutical dosage regimen.

13. The computer program product of claim 9 , wherein determining the failure of compliance comprises comparing one or more treatment event of the patient information with the treatment plan.

14. The computer program product of claim 9 , wherein retrieving the patient information comprises applying natural language processing to unstructured textual data.

15. The computer program product of claim 9 , wherein the ranked list is provided for review on a mobile device.

16. The method of claim 1 , wherein the plurality of sources comprises at least one of: the patient electronic medical record, pharmacy information, a retail establishment computer system, and a hospital system.

17. The computer program product of claim 9 , wherein the plurality of sources comprises at least one of: the patient electronic medical record, pharmacy information, a retail establishment computer system, and a hospital system.