Method for providing patient indications to an entity

• US 10,269,448 B2
• Filed: 11/18/2017
• Issued: 04/23/2019
• 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
• Primary Examiner(s): Augustine, Victoria P
• Assistant Examiner(s): Newton, Chad A
• Application Number:
  US15/817,190
• Publication Number:
  US 20180101650A1
• Time in Patent Office: 521 Days
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• 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 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• 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: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A method and system for providing patient indications to an entity, the method comprising: for each of a set of patients: by way of an application executing at a mobile computing device, accessing a sensor system and a log of use of a communication application executing on the mobile computing device; receiving a survey response dataset; generating a behavioral dataset, derived from the sensor system and the log of use; generating a predictive model derived from at least one of the survey response dataset and the behavioral dataset; generating comparisons of outputs of blocks of the method to threshold conditions; producing a set of indications corresponding to the set of patients, derived from generation of, for each of the set of patients, an indication in response to the comparisons; and transmitting a portion of the set of indications to the entity according to a resource constraint of the entity.

Claims

1. A method for calculating position of a GPS receiver in relation to human communication behavior, during a human communication period, for providing patient-related indications to an entity, the method comprising:

generating a set of patient indications for a set of patients, wherein generating the set of patient indications comprises for each patient of the set of patients;

collecting a mobility dataset for the patient, the mobility dataset corresponding to a mobility sensor of a mobile computing device associated with the patient, wherein collecting the mobility dataset comprises collecting GPS satellite data at a remote server from the mobile computing device, wherein the GPS satellite data corresponds to a GPS receiver of the mobile computing device comprising the GPS receiver, a microprocessor, a display, and a wireless communication transceiver, and wherein the remote server comprises a central processing unit (CPU);

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

generating a behavioral dataset for the patient based on the mobility dataset and the log of use, wherein generating the behavioral dataset comprises extracting a set of behavioral features from the mobility dataset and the log of use, and wherein extracting the set of behavioral features comprises;

calculating, by the remote server CPU, a physical isolation feature based on the GPS satellite data of the mobility dataset, wherein the physical isolation feature is operable to improve determination of the patient indication, wherein the physical isolation feature is associated with the human communication period; and

calculating a human communication behavior feature based on a quantitative assessment of the log of use for phone calls and textual communications from the mobile computing device during the human communication period;

generating a comparison between the behavioral dataset and a threshold condition, wherein generating the comparison between the behavioral dataset and the threshold condition comprises generating the comparison based on the physical isolation feature and the human communication behavior feature; and

determining a patient indication for the patient from a first indication and a second indication based on the comparison, wherein the first indication is configured to be selected based on the behavioral dataset satisfying the threshold condition, and wherein the second indication is configured to be selected based on the behavioral dataset failing to satisfy the threshold condition; and

transmitting a portion of the set of patient indications to the entity, wherein the portion of the set of patient indications is associated with a subset of the set of patients.

2. The method of claim 1, further comprising in response to determining the patient indication based on the comparison, automatically associating, at a remote database, the patient indication with the patient.

3. The method of claim 1, further comprising, for the each patient of the set of patients:

selecting a patient subgroup for the patient from a first subgroup and a second subgroup based on the mobility dataset, wherein the first subgroup is configured to be selected based on the mobility dataset indicating a first mobility behavior shared by the first subgroup, and wherein the second subgroup is configured to be selected based on the mobility dataset indicating a second mobility behavior shared by the second subgroup,

wherein determining the patient indication for the patient comprises determining the patient indication from the first indication and the second indication based on the subgroup and the comparison between the behavioral dataset and the threshold condition.

4. The method of claim 3, further comprising, automatically storing, at a remote database, the patient indication with the patient subgroup for the patient.

5. The method of claim 1, wherein the patient indication comprises a mental health patient indication, wherein generating the comparison comprises:

determining, for the patient, an activity level associated with physical activity behavior and human communication behavior, wherein the physical activity behavior is extracted from a location feature, and wherein the human communication behavior is extracted from the human communication feature based on the quantitative assessment of a frequency and a duration of outgoing phone calls and textual communications from the mobile computing device during a preset time period; and

comparing the activity level to the threshold condition comprising a threshold activity level.

6. The method of claim 1, wherein extracting the set of behavioral features comprises determining an amount of time that the patient spends at home in comparison to an amount of time that the patient spends at work, for each of a set of days, based on the GPS satellite data, wherein generating the comparison between the behavioral dataset and the threshold condition comprises generating the comparison based on the amount of time that the patient spends at home in comparison to the amount of time that the patient spends at work.

7. The method of claim 6, further comprising recommending, to the entity, provision of a stress-reduction intervention for the subset of the set of patients based on the amount of time that the patient spends at home in comparison to the amount of time that the patient spends at work, wherein the stress-reduction intervention is associated with the portion of the set of indications.

8. The method of claim 1, further comprising, for the each patient of the set of patients:

receiving a survey response dataset from the patient through the mobile application; and

determining an output of a predictive model for the patient based on at least one of the behavioral dataset and the survey response dataset,

wherein determining the patient indication comprises determining the patient indication from the first and the second indications based on the survey response dataset, the output of the predictive model, and the comparison between the behavioral dataset and the threshold condition.

9. The method of claim 1,

wherein the set of behavioral features comprises a social isolation feature from communication data of the log of use, a sleep quality feature from mobile device interaction data for the mobile computing device, and a restlessness feature derived from the mobile device interaction data, and

wherein generating the comparison comprises determining a comparison between the threshold condition and at least a subset of behavioral features from the set of behavioral features.

10. The method of claim 1, wherein determining the patient indication comprises determining, based on the comparison, the patient indication indicative of at least one of a pain-related condition, a cardiovascular disease-related condition, a sleep-related condition, and a mental health state, wherein the mental health state comprises at least one of:

a depression disorder, an anxiety disorder, a bipolar disorder, a psychotic disorder, and a mental health symptom status.

11. A method for providing patient-related indications to an entity, the method comprising:

generating a set of patient indications for a set of patients, wherein generating the set of patient indications comprises for each patient of the set of patients;

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

collecting GPS satellite data at a remote server from the mobile computing device, wherein the GPS satellite data corresponds to a GPS receiver of the mobile computing device comprising the GPS receiver, a microprocessor, a display, and a wireless communication transceiver, and wherein the remote server comprises a central processing unit (CPU)

generating a set of behavioral features based on the log of use and the GPS satellite data, wherein generating the set of behavior features comprises;

calculating, by the remote server CPU, a physical isolation feature based on the GPS satellite data of the mobility dataset, wherein the physical isolation feature is operable to improve determination of the patient indication; and

calculating a phone calling feature and a text messaging feature describing human communication behavior for the patient;

generating a comparison between at least a subset of the set of behavioral features and a threshold condition;

determining the patient indication for the patient from a first indication and a second indication based on the comparison, wherein the first indication is configured to be selected based on satisfaction of the threshold condition, and wherein the second indication is configured to be selected based on failure to satisfy the threshold condition; and

transmitting a portion of the set of patient indications to the entity, wherein the portion of the set of patient indications is associated with a subset of the set of patients.

12. The method of claim 11,

wherein accessing the log of use comprises accessing audio sensor data corresponding to an audio sensor of the mobile computing device,

wherein generating the set of behavioral features comprises generating a voice communication-related feature based on the audio sensor data,

wherein generating the comparison comprises generating the comparison between the voice communication-related feature and the threshold condition, and

wherein determining the patient indication comprises determining the patient indication from the first indication and the second indication based on the comparison between the voice communication-related feature and the threshold condition.

13. The method of claim 11, further comprising:

assigning intervention categories to patient indication types, wherein the intervention categories comprise at least one of patient alerts, care provider alerts, interventions for a level of care corresponding to the patient indication types, presenting information associated with the patient indication types, interventions improving resource usage, and interventions improving patient relationships, wherein the portion of the set of indications corresponds to the patient indication types; and

providing interventions based on the assigned intervention categories.

14. The method of claim 11, further comprising for the each patient of the set of patients:

collecting a mobility dataset for the patient, the mobility dataset corresponding to a mobility sensor of the mobile computing device associated with the patient, wherein generating the set of behavioral features comprises extracting a mobility feature for the patient based on the mobility dataset, and

wherein generating the comparison comprises generating the comparison between the mobility feature and the threshold condition.

15. The method of claim 11, further comprising:

ranking the portion of the set of indications based on at least one of;

time points associated with intervention provision to the subset of the set of patients, medication adherence, resiliency factors, and adherence to meeting patient goals,

wherein transmitting the portion of the set of indications comprises transmitting the ranked portion of the set of indications to the entity.

16. The method of claim 11, wherein generating the set of behavioral features comprises extracting, from the log of use, the set of behavioral features comprising at least one of:

a communication amount feature, a communication diversity feature, a communication predictability, communication entropy feature, a mobility feature, a content feature, and an active time by category feature.

17. The method of claim 11, further comprising,

facilitating provision of an intervention through the mobile application to an individual patient from the subset of patients, based on the patient indication for the individual patient;

collecting, for the individual patient, mobile application usage data corresponding to at least one of frequency and duration of usage by the individual patient of the mobile application and associated with the intervention; and

determining an additional patient indication for the individual patient based on an additional comparison between the mobile application usage data, the human communication behavior feature, and an additional threshold condition.

18. The method of claim 17, further comprising:

generating a longitudinal analysis of health for the individual patient based on the additional patient indication and the patient indication for the individual patient; and

providing information derived from the longitudinal analysis to the entity.

19. The method of claim 11, wherein determining the patient indication comprises determining, based on the comparison, the patient indication indicative of a mental health state comprising at least one of:

a depression disorder, an anxiety disorder, a bipolar disorder, a psychotic disorder, and a mental health symptom status.

20. The method of claim 19, wherein determining the patient indication indicative of the mental health state comprises determining an emotion-related issue for the user based on the comparison, and wherein transmitting the portion of the set of patient indications to the entity comprises transmitting information associated with the emotion-related issue to the entity.

21. The method of claim 11, further comprising receiving a survey response dataset from the patient through the mobile application, wherein generating the set of behavioral features comprises generating the set of behavioral features based on the survey dataset and the log of use.