Automated health data acquisition, processing and communication system and method

• US 10,424,404 B2
• Filed: 11/23/2016
• Issued: 09/24/2019
• Est. Priority Date: 11/13/2013
• Status: Active Grant

• Current Assignee: Dacadoo AG
• Original Assignee: Dacadoo AG
• Inventors: Ohnemus, Peter, Naef, Andre, Jacobs, Laurence, Leason, David
• Primary Examiner(s): Reyes, Reginald R
• Application Number:
  US15/360,807
• Publication Number:
  US 20170147788A1
• Time in Patent Office: 1,035 Days
• CPC Class Codes: G06Q 30/0236 Incentive or reward received by requiring registration or ID from user
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
• 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 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/21 for social networking applications

Abstract

A passive tracking device, a processor configured to receive information from the tracking device, and a database accessible by the processor, among other elements, are disclosed. A first activity unit having a first start time corresponding to detection of engagement is monitored. The processor is further configured to establish a first end time of the first activity unit using the monitored information, and automatically ascribe a classification of the first activity unit. The classification of the first activity unit is output to a display of a computing device, and the classification of the first activity unit is stored in the database. A revised classification is output to a display of a computing device, the revised classification is stored in the database.

Claims

1. A system to classify user activity, the system comprising:

a computing device configured with at least one processor, non-transitory processor readable media, and instructions stored on the non-transitory processor readable media;

a first sensing subsystem for passively tracking a physiological and/or metabolic condition of a person, the first sensing subsystem comprising a biosensor that is in contact with or within a person'"'"'s body and that periodically transmits sensed information associated with the person'"'"'s physiological and/or metabolic condition; and

a second sensing subsystem for passively tracking a location of the person, the second sensing subsystem comprising a Global Positioning System (“

GPS”

) receiver that receives GPS information that is usable to determine a location of the person;

wherein the computing device is configured to execute at least some of the instructions that cause the computing device to;

receive and/or access the sensed information and information representing the determined location,

classify and predict user activity and/or user health as a function of one or more machine learning techniques;

detect a change from a respective baseline condition associated with at least some of the sensed information, and i) at least some information stored in a user profile associated with the person and ii) external information;

in response to detecting the change, the computing device is further configured to;

define a first activity unit having a first start time that corresponds to detection of the user being engaged in an activity;

monitor the sensed information, the external information or both;

establish a first end time of the first activity unit using the monitored information;

automatically ascribe a classification of the first activity unit;

output the classification of the first activity unit to a display;

store the classification of the first activity unit in the database;

provide a user interface that includes selectable options associated with the first activity unit;

revise, in response to at least a received selection of at least one of the selectable options, the classification by;

joining or merging the first activity unit and a second activity unit having a second start time and a second end time, such that the revised classification has a start time equal to the first start time and an end time equal to the second end time;

or

dividing the first activity unit into at least two activity units, each of at least two activity units having a different respective start time and a different respective end time;

output the revised classification to a display of a computing device;

provide the revised classification to the classification engine; and

use the revised classification for machine learning.

2. The system of claim 1, wherein the computing device is configured to execute instructions that cause the computing device to:

generate and provide an audit trail that identifies at least a difference between the classification and the revised classification.

3. The system of claim 2, wherein the audit trail is configured for compliance review.

4. The system of claim 1, wherein the first activity unit and the second activity unit are minor activity units, and joining the first activity unit and the second activity unit comprises including both the first activity unit and the second activity unit into a major activity unit.

5. The system of claim 1, wherein the first activity unit and the second activity unit are minor activity units, and merging the first activity unit and the second activity unit comprises reducing the number of activity units to one minor activity unit that comprises the first activity unit and the second activity unit.

6. The system of claim 1, wherein the user profile information includes demographic information associated with at least one user.

7. The system of claim 1, wherein the external information includes at least one of schedule information, calendar information and weather information.

8. The system of claim 1, wherein the classification engine is configured to execute instructions that cause the computing device to:

define, as a function of a first portion of the sensed information from the first sensing subsystem, the baseline representing a condition of a person who is not engaged in activity; and

wherein the detection of the user being engaged in an activity is based at least in part on a detection in a change from the baseline.

9. The system of claim 1, wherein the machine learning includes at least one of cluster-based learning, such as for pattern recognition (e.g., K-Mean clustering, self-organizing mapping (SOM, Kohonen), Gaussian-Mixture Modeling (GMM), Support Vector Machine (SVM), Case-Based Reasoning (CBR), and Induction Trees.

10. The system of claim 1, further comprising an artificial neural network for implementing at least some of the machine learning.

11. A method for classifying user activity, the method comprising:

passively tracking, by a first sensing subsystem, a physiological and/or metabolic condition of a person, the first sensing subsystem comprising a biosensor that is in contact with or within a person'"'"'s body and that periodically transmits sensed information associated with the person'"'"'s physiological and/or metabolic condition;

passively tracking, by a second sensing subsystem, a location of the person, the second sensing subsystem comprising a Global Positioning System (“

GPS”

) receiver that receives GPS information that is usable to determine a location of the person;

receiving, by a computing device spaced apart from the first sensing subsystem, configured with a processor, a communication module, and instructions stored on non-transitory processor readable media, the sensed information from the first sensing subsystem and the second sensing subsystem;

classifying and predicting, by the computing device, user activity and/or user health as a function of one or more machine learning techniques,

detecting, by the computing device, a change from a respective baseline condition associated with at least some of the sensed information, and i) at least some information stored in a user profile associated with the person and ii) external information;

in response to detecting the change;

defining, by the computing device, a first activity unit having a first start time that corresponds to detection of the user being engaged in an activity unit;

monitoring, by the computing device, the sensed information, the external information or both;

establishing, by the computing device, a first end time of the first activity unit using the monitored information;

automatically ascribing, by the computing device, a classification of the first activity unit;

outputting, by the computing device, the classification of the first activity unit to a display;

storing, by the computing device, the classification of the first activity unit in the database;

providing, by the computing device, a user interface that includes selectable options associated with the first activity unit;

revising, by the computing device, in response to at least a received selection of at least one of the selectable options, the classification by;

joining or merging the first activity unit and a second activity unit having a second start time and a second end time, such that the revised classification has a start time equal to the first start time and an end time equal to the second end time;

or

dividing the first activity unit into at least two activity units, each of at least two activity units having a different respective start time and a different respective end time;

outputting, by the computing device, the revised classification to a display of a computing device;

providing, by the computing device, the revised classification to the classification engine; and

using the revised classification, by the computing device, for machine learning.

12. The method of claim 11, further comprising:

generating and providing, by the computing device, an audit trail that identifies at least a difference between the classification and the revised classification.

13. The method of claim 12, wherein the audit trail is configured for compliance review.

14. The method of claim 11, wherein the first activity unit and the second activity unit are minor activity units, and joining the first activity unit and the second activity unit comprises including both the first activity unit and the second activity unit into a major activity unit.

15. The method of claim 11, wherein the first activity unit and the second activity unit are minor activity units, and merging the first activity unit and the second activity unit comprises reducing the number of activity units to one minor activity unit that comprises the first activity unit and the second activity unit.

16. The method of claim 11, wherein the user profile information includes demographic information associated with at least one user.

17. The method of claim 11, wherein the external information includes at least one of schedule information, calendar information and weather information.

18. The method of claim 11, further comprising:

defining, by the computing device, as a function of a first portion of the sensed information from the first sensing subsystem, the baseline representing a condition of a person who is not engaged in activity; and

wherein the detection of the user being engaged in an activity is based at least in part on a detection in a change from the baseline.

19. The method of claim 11, wherein the machine learning includes at least one of cluster-based learning, such as for pattern recognition (e.g., K-Mean clustering, self-organizing mapping (SOM, Kohonen), Gaussian-Mixture Modeling (GMM), Support Vector Machine (SVM), Case-Based Reasoning (CBR), and Induction Trees.

20. The method of claim 11, wherein at least some of the machine learning is implemented in an artificial neural network.