Method for modeling behavior and health changes

• US 10,068,673 B2
• Filed: 11/08/2017
• Issued: 09/04/2018
• Est. Priority Date: 08/16/2012
• Status: Active Grant

• Current Assignee: OrangeDot, Inc.
• Original Assignee: Ginger.io, Inc. (OrangeDot, Inc.)
• Inventors: Madan, Anmol, Moturu, Sai Thejasvee
• Primary Examiner(s): Tomaszewski, Michael
• Application Number:
  US15/807,323
• Publication Number:
  US 20180068085A1
• Time in Patent Office: 300 Days
• Field of Search: None
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 20/10 relating to drugs or medications, e.g. for ensuring correct administration to patients
• CPC Class Codes: G16H 40/60 for the operation of medical equipment or devices
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

One method for supporting a patient through a treatment regimen includes: accessing a log of use of a native communication application executing on a mobile computing device by a patient; selecting a subgroup of a patient population based on the log of use of the native communication application and a communication behavior common to the subgroup; retrieving a regimen adherence model associated with the subgroup, the regimen adherence model defining a correlation between treatment regimen adherence and communication behavior for patients within the subgroup; predicting patient adherence to the treatment regimen based on the log of use of the native communication application and the regimen adherence model; and presenting a treatment-related notification based on the patient adherence through the mobile computing device.

Claims

1. A method for improving treatment efficacy determination, the method comprising:

collecting a mobility sensor dataset for a population of patients, the mobility dataset corresponding to mobility sensors of mobile computing devices associated with the population of patients;

selecting a first patient subgroup for a first patient from the population of patients based on first patient mobility data from the mobility sensor dataset indicating a first mobility behavior associated with the first patient subgroup and wherein selection of the first patient subgroup is operable to improve data storage, data retrieval, and the adherence determination;

selecting a second patient subgroup for a second patient from the population of patients based on second patient mobility data from the mobility sensor dataset indicating a second mobility behavior associated with the second patient subgroup and wherein selection of the second patient subgroup is operable to improve data storage, data retrieval, and the treatment efficacy determination;

determining first medical symptom characteristics for the first patient subgroup;

identifying a relationship between the first medical symptom characteristics and first communication behaviors associated with the first patient subgroup; and

generating a first treatment efficacy model based on the selected first patient subgroup to facilitate improvement of the treatment efficacy determination, wherein the first treatment efficacy model is operable to determine a treatment efficacy for a treatment regimen; and

facilitating provision of a health-related intervention for improving a health outcome of the first patient, based on the treatment efficacy determined from the first treatment efficacy model.

2. The method of claim 1, wherein selecting the first patient subgroup and selecting the second patient subgroup are operable to improve data storage and data retrieval associated with treatment efficacy determination, and wherein the method further comprises in response to generating the first treatment efficacy model, automatically storing the first treatment efficacy model in association with the first patient subgroup.

3. The method of claim 2, further comprising:

generating a second treatment efficacy model for the second patient subgroup based on second medical symptom characteristics and second communication behaviors associated with the second subgroup; and

in response to generating the second treatment efficacy model, automatically storing the second treatment efficacy model in association with the second patient subgroup.

4. The method of claim 1, wherein the mobility sensors comprise location sensors and motion sensors, wherein the mobility sensor dataset comprises a location dataset and a motion dataset, wherein selecting the first patient subgroup comprises selecting the first patient subgroup based on first patient location data from the location dataset and on first patient motion data from the motion dataset, and wherein selecting the second patient subgroup comprises selecting the second patient subgroup based on second patient location data from the location dataset and on second patient motion data from the motion dataset.

5. The method of claim 1, wherein the first mobility behavior comprises a total patient movement below a threshold, wherein selecting the first patient subgroup comprises selecting the first patient subgroup based on the first patient mobility data indicating movement of the first patient being below the threshold, wherein the second mobility behavior comprises the total patient movement above the threshold, and wherein selecting the second patient subgroup comprises selecting the second patient subgroup based on the second patient mobility data indicating movement of the second patient being above the threshold.

6. The method of claim 1, further comprising accessing logs of use for the population of patients, the logs of use corresponding to communication applications for the mobile computing devices, wherein selecting the first patient subgroup comprises selecting the first patient subgroup based on the first patient mobility data and a first communication behavior extracted from the logs of use, and wherein selecting the second patient subgroup comprises selecting the second patient subgroup based on the second patient mobility data and a second communication behavior extracted from the logs of use.

7. The method of claim 1, wherein the first medical symptom characteristics comprise a mental health status comprising at least one of a depression disorder, an anxiety disorder, a bipolar disorder, and a psychotic disorder, wherein identifying the relationship comprises identifying a correlation between the mental health status and the first communication behaviors, and wherein the treatment efficacy model is operable to determine the treatment efficacy in improving the mental health status.

8. The method of claim 1, wherein generating the treatment efficacy model for the subgroup comprises generating the treatment efficacy model defining a correlation between a change in the first communication behaviors and response to the treatment regimen within the subgroup, based on the first medical symptom characteristics for the first patient subgroup during administration of the treatment regimen.

9. The method of claim 1, further comprising:

characterizing the first communication behaviors for the first patient subgroup based on at least one of frequency, duration, timing, content, and contact diversity for at least one of textual communications and voice communications corresponding to communication applications executing on patient mobile computing devices associated with the first patient subgroup.

10. The method of claim 1, wherein determining the first medical symptom characteristics comprises extracting the first medical symptom characteristics from anonymized survey responses uploaded from the mobile computing devices associated with the population of subjects, and wherein the method further comprises automatically storing the first medical symptom characteristics in association with the first patient subgroup.

11. A method for improving treatment regimen characterization for a patient, the method comprising:

accessing a log of use corresponding to a communication application for a mobile computing device associated with the patient;

collecting mobility sensor data corresponding to a mobility sensor of the mobile computing device;

selecting a patient subgroup for the patient from a first subgroup and a second subgroup based on the log of use data and the mobility sensor data, wherein the first subgroup is configured to be selected based on the log of use data and the mobility sensor data indicating a first patient behavior associated with the first subgroup, wherein the second subgroup is configured to be selected based on the log of use data and the mobility sensor data indicating a second patient behavior associated with the second subgroup, wherein the selection of the patient subgroup is operable to improve data storage, data retrieval, and the treatment regimen characterization;

retrieving a treatment model associated with the selected patient subgroup, the treatment model defining a relationship between communication behavior patterns and treatment patterns associated with the patient subgroup;

characterizing the treatment regimen for the patient based on the log of use and the treatment model; and

facilitating provision of a health-related intervention for improving a health outcome of the patient, based on the treatment regimen characterization.

12. The method of claim 11, further comprising:

in response to characterizing the treatment regimen for the patient, facilitating a digital communication between the patient and a care provider; and

determining a custom treatment regimen for the patient based on the digital communication between the patient and the care provider, wherein the custom treatment regimen comprises at least one of a medication type and a medication dosage.

13. The method of claim 11, wherein accessing the log of use associated with the patient comprises analyzing at least one of voice communications and textual communications to extract a communication behavior feature set comprising at least one of a quantitative assessment of content, a qualitative assessment of content, a quantitative assessment of frequency, and a quantitative assessment of length, and wherein characterizing the treatment regimen for the patient comprises characterizing the treatment regimen based on the treatment model and the communication behavior feature set.

14. The method of claim 11, wherein retrieving the treatment model comprises retrieving the treatment model defining a correlation between a change in communication behaviors and a change in symptom severity for patients within the patient subgroup.

15. The method of claim 11, wherein characterizing the treatment regimen comprises generating a predicted treatment regimen outcome for the treatment regimen for the patient based on the treatment model and a similarity between a patient communication behavior derived from the log of use and the communication behavior patterns associated with the patient subgroup.

16. The method of claim 15, wherein generating the predicted treatment regimen outcome comprises predicting a health condition relapse risk for the patient based on the treatment model and the similarity between the patient communication behavior and the communication behavior patterns.

17. The method of claim 15, further comprising:

determining a custom treatment regimen for the patient based on the predicted treatment regimen outcome; and

transmitting the predicted treatment regimen outcome and the custom treatment regimen to a care provider associated with the patient.

18. The method of claim 11, wherein characterizing the treatment regimen comprises determining a treatment efficacy for the treatment regimen for the patient based on the log of use, the treatment model, and a treatment adherence determined for the patient in relation to the treatment regimen.

19. The method of claim 18, further comprising:

generating an updated treatment regimen for the patient based on the treatment efficacy for the treatment regimen; and

transmitting the updated treatment regimen to the patient.

20. The method of claim 11, further comprising:

collecting mobile application usage data for the patient during a time period associated with administration of the treatment regimen; and

characterizing the treatment regimen for the patient based on the mobile application usage data, the log of use, and the treatment efficacy model.

21. The method of claim 11, further comprising:

collecting mobility data corresponding to a mobility sensor of the mobile computing device, wherein selecting the patient subgroup comprises selecting the patient subgroup based on the mobility data, wherein the first subgroup is configured to be selected based on the mobility data indicating a first mobility behavior, and wherein the second subgroup is configured to be selected based on the mobility data indicating a second mobility behavior.

22. The method of claim 11, wherein characterizing the treatment regimen comprises:

identifying a change in a composite function associated with stress and productivity of the patient based on the log of use; and

characterizing the treatment regimen for the patient based on the treatment model and the change in the composite function associated with stress and productivity.

23. The method of claim 11, wherein the treatment regimen comprises a mental health treatment regimen for a mental health status comprising at least one of a depression disorder, an anxiety disorder, a bipolar disorder, and a psychotic disorder, and wherein characterizing the treatment regimen comprises determining a treatment efficacy for the mental health treatment regimen in improving the mental health status.