Method for modeling behavior and depression state

• US 10,068,670 B2
• Filed: 08/28/2015
• 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: Moturu, Sai, Madan, Anmol, Dash, Shishir, Wahba, Karim, De, Gourab
• Primary Examiner(s): Tomaszewski, Michael
• Application Number:
  US14/839,053
• Publication Number:
  US 20150370993A1
• Time in Patent Office: 1,103 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 20/70 relating to mental therapies, e.g. psychological therapy or autogenous training
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 40/67 for remote operation
• 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

A method and system for modeling behavior and depression state of an individual, the method comprising: receiving a log of use dataset associated with communication behavior of the individual during a time period; receiving a supplementary dataset characterizing activity of the individual during the time period; receiving a survey dataset including responses, to at least one of a set of depression-assessment surveys, associated with a set of time points of the time period; generating a predictive analysis of a depression-risk state of the individual associated with at least a portion of the time period, from at least one of the log of use dataset, the supplementary dataset, and the survey dataset; and generating an alert upon detection that a set of parameters from the predictive analysis of the depression-risk state satisfy a threshold condition.

Claims

1. A method for improving depression state determination for an individual, the method comprising:

transmitting, from a communication module executing on a mobile communication device to a computing system, a log of use dataset associated with communication behavior of the individual during a time period;

at the computing system, receiving a motion supplementary dataset corresponding to a motion sensor of the mobile computing device, the motion supplementary dataset characterizing physical orientation of the mobile computing device and associated with physical activity behavior of the individual during the time period;

collecting GPS data corresponding to a GPS sensor of the mobile computing device, the GPS data describing physical location of the mobile computing device and associated with location behavior of the individual during the time period;

at the computing system, receiving a survey dataset including responses, to at least one of a set of depression-assessment surveys, associated with a set of time points of the time period;

selecting a patient subgroup for the individual from a first subgroup and a second subgroup based on the GPS data and the motion supplementary dataset, wherein the first subgroup is selected in response to the physical location and the physical orientation of the mobile computing device indicating a first mobility behavior shared by the first subgroup, wherein the second subgroup is selected in response to the physical location and the physical orientation of the mobile computing device indicating a second mobility behavior shared by the second subgroup, and wherein selection of the patient subgroup is operable to improve data storage, data retrieval, and the depression state determination;

at the computing system, generating a predictive model based on the selected patient subgroup, the survey dataset, and a passive dataset derived from the log of use dataset, the GPS data, and the motion supplementary dataset;

transforming at least one of the passive dataset, the survey dataset, and the an output of the predictive model into an analysis of a depression-risk state of the individual associated with at least a portion of the time period; and

upon detection that parameters of the depression-risk state satisfy a threshold condition, automatically initiating provision of a therapeutic intervention for improving a health outcome of the individual, by way of at least one of the computing system and the mobile communication device.

2. The method of claim 1, wherein transmitting the log of use dataset further includes:

at the computing system, extracting, from the log of use dataset;

a length of text messages received by the individual from a close associate of the individual, a phone call duration, an incoming call count, and a number of ignored calls.

3. The method of claim 2, wherein receiving the supplementary dataset includes extracting a mobility radius associated with at least one time point of the time period and derived from the GPS sensor of the mobile communication device.

4. The method of claim 2, wherein generating the analysis includes generating a first comparison between a) a first threshold condition, associated with isolation behavior of the individual across a portion of the time period, and b) at least one passive data element of the log of use dataset and the supplementary dataset.

5. The method of claim 1, wherein the depression-risk state includes a mobility parameter, and wherein generating the comparison includes comparing the mobility parameter to a mobility radius threshold with an associated duration threshold.

6. The method of claim 1, wherein the depression-risk state includes a communication parameter, and wherein generating the comparison includes comparing the communication parameter to a communication length threshold for a primary contact the individual.

7. The method of claim 1, wherein receiving the survey dataset comprises providing, within an application executing at the mobile communication device, a survey derived from at least one of:

a Patient Health Questionnaire-9 (PHQ-9) assessment, a Hamilton Rating Scale for Depression (HAM-D) assessment, and a Generalized Anxiety Disorder-7 (GAD-7) assessment.

8. The method of claim 7, wherein providing the survey includes automatically providing a first portion of the survey within the application at a first subset of time points of the time period, and providing a second portion of the survey within the application at a second subset of time points of the time period.

9. The method of claim 8, wherein the threshold condition includes a threshold survey score associated with a critical depression state, and wherein generating the analysis includes generating a second comparison between a) the threshold survey score and b) a survey score of the individual associated with at least one time point of the time period.

10. The method of claim 1, wherein automatically initiating provision of the therapeutic intervention includes at least one of:

enabling a healthcare entity to contact the individual and providing health advice related to depression to the individual within an application executing at the mobile computing device.

11. A method for improving depression state determination for an individual, the method comprising:

at a computing system in communication with a mobile communication device of the individual, receiving a log of use dataset associated with communication behavior of the individual during a time period;

at the computing system, receiving a mobility sensor supplementary dataset corresponding to a mobility sensor of the mobile communication device, the mobility supplementary dataset characterizing activity of the individual during the time period;

at the computing system, receiving a survey dataset including responses, to at least one of a set of depression-assessment surveys, associated with a set of time points of the time period;

selecting a patient subgroup for the individual from a first subgroup and a second subgroup based on the mobility sensor supplementary dataset, wherein the first subgroup is selected in response to the mobility sensor supplementary dataset indicating a first mobility behavior associated with the first subgroup, wherein the second subgroup is selected in response to the mobility sensor supplementary dataset indicating a second mobility behavior associated with the second subgroup, and wherein selection of the patient subgroup is operable to improve data storage, data retrieval, and the depression state determination;

at the computing system, generating a predictive model of a depression-risk state of the individual associated with at least a portion of the time period, based on the selected patient subgroup and at least one of the log of use dataset, the mobility sensor supplementary dataset, and the survey dataset; and

by way of at least one of the computing system and the mobile communication device, automatically initiating provision of a therapeutic intervention for improving a health outcome of the individual, upon detection that a set of parameters outputted from the predictive model of the depression-risk state satisfy a threshold condition.

12. The method of claim 11, wherein receiving the log of use dataset further includes:

at the computing system, extracting, from the log of use dataset;

a length of text messages received by the individual from a close associate of the individual, a phone call duration, an incoming call count, and a number of ignored calls.

13. The method of claim 11, wherein receiving the supplementary dataset includes extracting a mobility radius associated with at least one time point of the time period and derived from global positioning sensors of the mobile communication device.

14. The method of Claim 11, wherein generating the predictive model includes:

at the computing system, implementing a factor analysis approach that models diversity in interaction behavior of the individual across the time period.

15. The method of claim 14, wherein generating the predictive model includes processing the log of use dataset, the supplementary dataset, and the survey dataset with a correlation-based feature selection (CFS) algorithm to extract features of the depression-risk state across the time period.

16. The method of claim 11, wherein the set of parameters of the depression-risk state includes parameters derived from at least one of a mobility radius parameter from the supplementary dataset and a communication count parameter from the log of use dataset.

17. The method of claim 16, wherein automatically initiating provision of the therapeutic intervention comprises rendering an alert at a user interface of a dashboard of a healthcare entity associated with the individual, and wherein rendering the alert further includes providing the healthcare entity with an electronically-implemented tool for contacting the individual.

18. The method of claim 11, wherein generating the predictive model of the depression-risk state of the individual includes generating an anticipated depression-related state of the user at a future time point outside of the time period, and wherein the method further includes automatically initiating provision of a therapeutic intervention for the individual to prevent the anticipated depression-related state of the user.

19. The method of claim 18, wherein the anticipated depression-related state is a suicidal state, and wherein automatically initiating provision of the therapeutic intervention includes enabling a healthcare entity to contact the individual proximal in time to the future time point.

20. The method of claim 11, further comprising, with the predictive model, identifying a first set of features that enable determination of depression severity for a first categorization of individuals, and a second set of features that enable determination of depression severity for a second categorization of individuals.

21. The method of claim 11, further comprising transforming at least one of the passive dataset, the survey dataset, and the an output of the predictive model into an analysis of an anxiety state of the individual associated with at least a portion of the time period;

and upon detection that parameters of the anxiety state satisfy a threshold condition, automatically initiating provision of a therapeutic intervention for the individual by way of at least one of the computing system and the mobile communication device.