Integrated sensor network methods and systems

• US 10,188,295 B2
• Filed: 06/01/2010
• Issued: 01/29/2019
• Est. Priority Date: 06/01/2009
• Status: Active Grant

• Current Assignee: Curators of the University of Missouri (University of Missouri)
• Original Assignee: Curators of the University of Missouri (University of Missouri)
• Inventors: Skubic, Marjorie, Rantz, Marilyn J., Popescu, Mihail, Wang, Shuang, Sledge, Isaac J., Guevara, Rainer Dane A., Florea, Elena, Keller, James M.
• Primary Examiner(s): Zimmerman, Brian A
• Assistant Examiner(s): Lau, Kevin
• Application Number:
  US12/791,628
• Publication Number:
  US 20100302043A1
• Time in Patent Office: 3,164 Days
• Field of Search: None
• CPC Class Codes: A61B 2503/08 Elderly
• CPC Class Codes: A61B 2505/07 Home care
• CPC Class Codes: A61B 2560/0242 adapted to measure environmental factors, e.g. temperature, pollution
• CPC Class Codes: A61B 5/002 Monitoring the patient using a local or closed circuit, e.g. in a room or building A61B5/0017 takes precedence
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/0816 Measuring devices for examining respiratory frequency measuring frequency of electric signals G01R23/00
• CPC Class Codes: A61B 5/1113 Local tracking of patients, e.g. in a hospital or private home
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: G08B 21/0423 detecting deviation from an expected pattern of behaviour or schedule
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Methods and systems for an integrated sensor network are described. In one embodiment, sensor data may be accessed from a plurality of motion sensors and a bed sensor deployed in a living unit for a first time period. An activity pattern for the first time period may be identified based on at least a portion of sensor data associated with the first time period. The activity pattern may represent a physical and cognitive health condition of a person residing in the living unit. Additional sensor data may be accessed from the motion sensors and the bed sensor deployed for a second time period. A determination of whether a deviation of the activity pattern of the first time period has occurred for the second time period may be performed. An alert may be generated based on a determination that the derivation has occurred. In some embodiments, user feedback is captured on the significance of the alerts, and the alert method is customized based on this feedback. Additional methods and systems are disclosed.

Claims

1. A method comprising:

processing sensor data from a plurality of motion sensors and a bed sensor deployed in a living unit for a first time period to establish a frame of reference for an activity pattern by a person residing in the living unit, wherein the activity pattern frame of reference represents a health condition of a person residing in the living unit, wherein the processed sensor data for the first time period comprises a plurality of data values corresponding to a plurality of subintervals within the first time period, wherein each subinterval data value represents (1) a total number of sensor hits during that subinterval of the first time period or (2) a total time for sensor firings during that subinterval of the first time period, and wherein the activity pattern frame of reference comprises a statistical value about the subinterval data values over the first time period;

computing a standard deviation for the processed sensor data over the first time period based on the subinterval data values;

defining a statistical parameter threshold, wherein the statistical parameter threshold comprises a defined number of the standard deviations;

processing additional sensor data from the plurality of motion sensors and the bed sensor deployed in the living unit for a second time period, the second time period occurring after the first time period;

computing a value for the activity pattern for the second time period based on the processed additional sensor data, the computed activity pattern value of the second time period also representing a health condition of the person, wherein the computed activity pattern value comprises (1) data about a total number of sensor hits during the second time period if the activity pattern frame of reference is based on the total number of sensor hits during the first time period or (2) data about a total time for sensor firings during the second time period if the activity pattern frame of reference is based on the total time for sensor firings during the first time period;

comparing the computed activity pattern value with the activity pattern frame of reference and the defined statistical parameter threshold to determine whether the computed activity pattern value deviates from the activity pattern frame of reference by more than the defined number of the standard deviations;

generating an alert based on a determination that the computed activity pattern value deviates from the activity pattern frame of reference by more than the defined number of standard deviations;

receiving a feedback response to the alert, the feedback response including feedback regarding clinical relevance of the alert; and

adjusting the defined number of the standard deviations for the statistical parameter threshold to a different defined number of the standard deviations based on the feedback response to the alert.

9. The method of claim 1, wherein the first time period has a same time duration as the second time period.

14. The method of claim 1, wherein the activity patterns of the first and second time periods are based on the total number of sensor hits during the first and second time periods.

15. The method of claim 1, wherein the activity patterns of the first and second time periods are based on the total time for sensor firings during the first and second time periods.

29. The method of claim 1, wherein the activity pattern frame of reference comprises (1) a statistical value about a daily total number of sensor hits during the first time period or (2) a statistical value about a daily total time for sensor firings during the first time period.

30. The method of claim 1, wherein the motion sensors comprise at least one motion sensor deployed in at least one of (1) a bathroom of the living unit, (2) a kitchen of the living unit, (3) a living room of the living unit, (4) a bedroom of the living unit, (5) a cup cabinet of the living unit, (6) an office of the living unit, (7) a bedroom of the living unit, (8) a plate cabinet of the living unit, (9) a shower of the living unit, (10) a closet of the living unit, (11) a silverware drawer of the living unit, (12) a den of the living unit, (13) a refrigerator of the living unit, (14) a front door of the living unit, and (15) a laundry of the living unit.

31. The method of claim 1, wherein the motion sensors comprise a plurality of motion sensors deployed in at least two of (1) a bathroom of the living unit, (2) a kitchen of the living unit, (3) a living room of the living unit, (4) a bedroom of the living unit, (5) a cup cabinet of the living unit, (6) an office of the living unit, (7) a bedroom of the living unit, (8) a plate cabinet of the living unit, (9) a shower of the living unit, (10) a closet of the living unit, (11) a silverware drawer of the living unit, (12) a den of the living unit, (13) a refrigerator of the living unit, (14) a front door of the living unit, and (15) a laundry of the living unit.

32. The method of claim 1, further comprising:

defining the first time period in response to user input.

2. A method of comprising:

accessing sensor data from a plurality of motion sensors and a bed sensor deployed in a living unit for a first time period, wherein the accessed sensor data comprises a total number of sensor hits during the first time period;

identifying an activity pattern for the first time period based on the total number of sensor hits during the first time period, the activity pattern of the first time period representing a health condition of a person residing in the living unit, and wherein the activity pattern for the first time period comprises a plurality of first time period data values, wherein each first time period data value corresponds to a subinterval of the first time period and is indicative of a total number of sensor hits for its corresponding subinterval of the first time period;

accessing additional sensor data from the plurality of motion sensors and the bed sensor deployed in the living unit for a second time period, the second time period occurring after the first time period, wherein the first time period is longer than the second time period, and wherein the accessed additional sensor data comprises a total number of sensor hits during the second time period;

identifying an activity pattern for the second time period based on the total number of sensor hits during the second time period, the activity pattern of the second time period also representing a health condition of the person;

calculating statistics about the first time period data values, the calculated statistics including a standard deviation for the first time period data values;

defining a statistical parameter threshold, wherein the statistical parameter threshold comprises a defined number of the standard deviations;

analyzing the activity pattern of the second time period with respect to the statistical parameter threshold, wherein the analyzing step comprises comparing a data value indicative of a total number of sensor hits for the second time period with the calculated statistics to determine whether the second time period data value exceeds a calculated statistic about the first time period data values by more than the threshold number of the standard deviations;

generating an alert in response to the second time period data value exceeding the calculated statistic about the first time period data values by more than the threshold number of the standard deviations;

receiving a feedback response to the alert, the feedback response including feedback regarding clinical relevance of the alert; and

adjusting the defined number of the standard deviations for the statistical parameter threshold to a different defined number of the standard deviations based on the feedback response to the alert.

3. The method of claim 2, wherein the activity pattern includes a plurality of features and the deviation is associated with a particular feature of the plurality of features.

4. The method of claim 2, further comprising:

recording ignored indicia for the person based on the receipt of the feedback response; and

determining whether the deviation has occurred based in part on the recorded ignored indicia.

5. The method of claim 2, further comprising:

analyzing health data associated with the person;

wherein generation of the alert is based on (1) when the deviation exceeds the statistical parameter threshold and (2) an analysis of the health data.

6. The method of claim 2, further comprising:

accessing the sensor data from a stove sensor deployed in the living unit; and

accessing the additional sensor data from the stove sensor deployed in the living unit.

7. The method of claim 2, wherein the plurality of motion sensors and the bed sensor are passive, non-wearable sensors.

8. The method of claim 2, further comprising:

identifying at least a portion of the sensor data associated with the first time period as being associated with the person;

wherein identification of the activity pattern for the first time period is based on at least the portion of sensor data associated with the first time period associated with the person.

10. The method of claim 2, wherein the calculating step comprises calculating the statistical parameters of at least a portion of the sensor data for the first time period;

and

wherein the statistical parameter threshold is an individualized statistical parameter threshold.

11. The method of claim 2, further comprising:

transmitting the alert including a link to a web interface, the web interface including the sensor data of the second time period in the context of the sensor data of the first time period.

12. The method of claim 2, further comprising:

adjusting a sensor parameter used for the alert based on the receipt of the feedback response.

13. The method of claim 2, wherein the activity pattern includes a plurality of features.

16. The method of claim 2, wherein the activity patterns of the first and second time periods are based on a density of sensor hits during the first and second time periods.

17. The method of claim 16, wherein the calculating step includes calculating a dis-similarity between the activity pattern densities as between the first and second time periods.

18. The method of claim 17, wherein the dis-similarity calculating comprises calculating the dis-similarity based on at least one member of the group consisting of a spatial frequency and perceptual property of the activity pattern densities.

19. The method of claim 2 wherein the subinterval corresponds to a daily subinterval within the first time period.

20. The method of claim 2 wherein the second time period is the same as the subinterval.

21. The method of claim 2 further comprising:

providing a user interface through which a user can adjustably define a plurality of parameters for the sensor data;

defining the first time period and the subinterval in response to user input through the provided user interface.

22. The method of claim 21 wherein the providing step comprises providing the user interface in response to user input with respect to the alert.

28. The method of claim 2 wherein the health condition is representative of a physical and cognitive health condition of the person.

23. A method of comprising:

accessing sensor data from a plurality of motion sensors and a bed sensor deployed in a living unit for a first time period, wherein the accessed sensor data comprises a total time for sensor firings during the first time period;

identifying an activity pattern for the first time period based on the total time for sensor firings during the first time period, the activity pattern of the first time period representing a health condition of a person residing in the living unit, and wherein the activity pattern for the first time period comprises a plurality of first time period data values, wherein each first time period data value corresponds to a subinterval of the first time period and is indicative of a total time for sensor firings for its corresponding subinterval of the first time period;

accessing additional sensor data from the plurality of motion sensors and the bed sensor deployed in the living unit for a second time period, the second time period occurring after the first time period, wherein the first time period is longer than the second time period, and wherein the accessed additional sensor data comprises a total time for sensor firings during the second time period;

identifying an activity pattern for the second time period based on the total time for sensor firings during the second time period, the activity pattern of the second time period also representing a health condition of the person;

calculating statistics about the first time period data values, the calculated statistics including a standard deviation for the first time period data values;

defining a statistical parameter threshold, wherein the statistical parameter threshold comprises a defined number of the standard deviations;

analyzing the activity pattern of the second time period with respect to the statistical parameter threshold, wherein the analyzing step comprises comparing a data value indicative of a total time for sensor firings for the second time period with the calculated statistics to determine whether the second time period data value exceeds a calculated statistic about the first time period data values by more than the threshold number of the standard deviations;

generating an alert in response to the second time period data value exceeding the calculated statistic about the first time period data values by more than the threshold number of the standard deviations;

receiving a feedback response to the alert, the feedback response including feedback regarding clinical relevance of the alert; and

adjusting the defined number of the standard deviations for the statistical parameter threshold to a different defined number of the standard deviations based on the feedback response to the alert.

24. The method of claim 23 wherein the subinterval corresponds to a daily subinterval within the first time period.

25. The method of claim 23 wherein the second time period is the same as the subinterval.

26. The method of claim 23 further comprising:

providing a user interface through which a user can adjustably define a plurality of parameters for the sensor data;

defining the first time period and the subinterval in response to user input through the provided user interface.

27. The method of claim 26 wherein the providing step comprises providing the user interface in response to user input with respect to the alert.

33. A system comprising:

a plurality of motion sensors and a bed sensor deployed in a living unit; and

a computer system for communication with the motion sensors and the bed sensor, wherein the computer system is configured to;

process sensor data from the motion sensors and the bed sensor for a first time period to establish a frame of reference for an activity pattern by a person residing in the living unit, wherein the activity pattern frame of reference represents a health condition of a person residing in the living unit, wherein the processed sensor data for the first time period comprises a plurality of data values corresponding to a plurality of subintervals within the first time period, wherein each subinterval data value represents (1) a total number of sensor hits during that subinterval of the first time period or (2) a total time for sensor firings during that subinterval of the first time period, and wherein the activity pattern frame of reference comprises a statistical value about the subinterval data values over the first time period;

compute a standard deviation for the processed sensor data over the first time period based on the subinterval data values;

define a statistical parameter threshold, wherein the statistical parameter threshold comprises a defined number of the standard deviations;

process additional sensor data from the plurality of motion sensors and the bed sensor deployed in the living unit for a second time period, the second time period occurring after the first time period;

compute a value for the activity pattern for the second time period based on the processed additional sensor data, the computed activity pattern value of the second time period also representing a health condition of the person, wherein the computed activity pattern value comprises (1) data about a total number of sensor hits during the second time period if the activity pattern frame of reference is based on the total number of sensor hits during the first time period or (2) data about a total time for sensor firings during the second time period if the activity pattern frame of reference is based on the total time for sensor firings during the first time period;

compare the computed activity pattern value with the activity pattern frame of reference and the defined statistical parameter threshold to determine whether the computed activity pattern value deviates from the activity pattern frame of reference by more than the defined number of the standard deviations;

generate an alert based on a determination that the computed activity pattern value deviates from the activity pattern frame of reference by more than the defined number of standard deviations;

receive a feedback response to the alert, the feedback response including feedback regarding clinical relevance of the alert; and

adjust the defined number of the standard deviations for the statistical parameter threshold to a different defined number of the standard deviations based on the feedback response to the alert.

34. The system of claim 33 wherein the computer system is further configured to provide a plurality of graphical user interfaces (GUIs) for presentation to a user, at least one of the GUIs configured to receive inputs from the user that define the first time period and the subinterval.

35. The system of claim 34 wherein at least another of the GUIs is configured to display sensor data over the defined first time period for each defined subinterval.