Integrated sensor network methods and systems
First Claim
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.
2 Assignments
0 Petitions
Accused Products
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.
-
Citations
35 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. - View Dependent Claims (9, 14, 15, 29, 30, 31, 32)
-
-
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. - View Dependent Claims (3, 4, 5, 6, 7, 8, 10, 11, 12, 13, 16, 17, 18, 19, 20, 21, 22, 28)
-
-
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. - View Dependent Claims (24, 25, 26, 27)
-
-
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. - View Dependent Claims (34, 35)
-
Specification