SYSTEMS AND METHODS FOR ANALYSIS OF SUBJECT ACTIVITY

• US 20160379476A1
• Filed: 11/26/2014
• Published: 12/29/2016
• Est. Priority Date: 11/26/2013
• Status: Active Grant

• Current Assignee: Kytera Technologies Ltd.
• Original Assignee: Kytera Technologies Ltd.
• Inventors: SELLA, Assaf
• Granted Patent: US 9,940,822 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A61B 2505/07 Home care
• 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 5/1113 Local tracking of patients, e.g. in a hospital or private home
• CPC Class Codes: A61B 5/1117 Fall detection
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/746 Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms alarms per se G08B
• CPC Class Codes: G08B 21/0423 detecting deviation from an expected pattern of behaviour or schedule
• CPC Class Codes: G08B 21/043 detecting an emergency event, e.g. a fall
• CPC Class Codes: G08B 21/0446 worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait
• CPC Class Codes: G08B 21/0453 worn on the body to detect health condition by physiological monitoring, e.g. electrocardiogram, temperature, breathing detecting, measuring or recording for diagnostic purposes A61B5/00
• CPC Class Codes: G08B 21/0492 Sensor dual technology, i.e. two or more technologies collaborate to extract unsafe condition, e.g. video tracking and RFID tracking
• CPC Class Codes: G08B 25/016 Personal emergency signalling and security systems emergency non-personal manually actuated alarm activators G08B25/12
• CPC Class Codes: H04L 65/102 Gateways arrangements for connecting between networks having differing types of switching systems, e.g. gateways, H04L12/66
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04W 4/025 using location based information parameters

Abstract

There is provided a method of detection and monitoring of at least one position based activity by a subject, comprising: providing a wearable monitoring device including at least one position tag for tracking location of the subject in a space; collecting body movement and location data of the subject within the space based on the tracked location of the position tag; providing at least one activity sensor configured to sense at least one body movement of the subject within the space; collecting body movement data based on the activity sensor; correlating the body movement data with the location data; contextually analyzing the correlation to identify at least one abnormal event or at least one normal event based on subject body movement and location where the body movement is performed; and generating an alert indicative of the abnormal event or the normal event.

Claims

1. A computerized method of detection and monitoring of at least one position based activity by a subject, comprising:

providing a wearable monitoring device including at least one position tag configured to communicate with a plurality of anchor devices, each device including at least one sensor configured for tracking location of the position tag in a space, the wearable monitoring device further configured to be detachable and wearable on a subject;

collecting body movement and location data of the subject within the space based on the tracked location of the at least one position tag;

providing at least one activity sensor configured to sense at least one body movement of the subject within the space, wherein the wearable monitoring device includes the at least one activity sensor;

collecting body movement data based on the at least one activity sensor;

correlating the body movement data and the location data and a time of day and day of week;

contextually analyzing the correlation to identify at least one abnormal event or at least one normal event based on a deviation of the correlated subject body movement and the location data and the time of day and day of week from past recorded data of a previous combination of similar body movement data and location data and time of day and day of week; and

generating an alert indicative of the at least one abnormal event or the at least one normal event.

2. The method of claim 1, further comprising:

collecting postural data based on the at least one activity sensor;

wherein correlating comprises correlating the postural data and the body movement and location data and the time of day and day of week; and

wherein contextually analyzing comprises contextually analyzing the correlation to identify at least one abnormal event or at least one normal event based on subject body movement and location where the postural data is performed.

3. The method of claim 1, further comprising:

collecting gesture data based on the at least one activity sensor;

wherein correlating comprises correlating the gesture data and the body movement and location data and the time of day and day of week; and

wherein contextually analyzing comprises contextually analyzing the correlation to identify at least one abnormal event or at least one normal event based on subject body movement and location where the gesture data is performed.

5. The method of claim 1, further comprising:

providing at least one physiological sensor configured to sense at least one physiological parameter of the subject within the space, wherein the wearable monitoring device includes the at least one physiological sensor;

collecting the at least one physiological parameter based on the at least one physiological sensor; and

wherein correlating comprises at least one of correlating the at least one physiological parameter and the body movement and location data and time of day and day of week;

wherein contextually analyzing comprises contextually analyzing the correlation to identify at least one abnormal event or at least one normal event based on subject body movement and location where the at least one physiological parameter is measured.

7. The method of claim 1, wherein contextually analyzing comprises contextually analyzing the correlation based on a learned routine data set storing at least one normal routine of the subject to identify the at least one abnormal event, and generating the learned routine data set based on learning at least one normal routine of the subject based on a pattern of the tracked location and at least one of:

body movement, posture, gesture, and physiological parameters, recorded with the time of day, and day of week.

9. The method of claim 7, wherein the learned routine data set includes at least one normal routine learned from a plurality of different subjects each similar to the subject.

12. The method of claim 1, wherein contextually analyzing comprises contextually analyzing the correlation to identify at least one activity of daily living, and analyzing the at least one activity of daily living to identify the at least one abnormal event related to the at least one activity of daily living.

19. The method of claim 1, further comprising activating an audio monitor closest to the location of the subject according to a tracked location of the subject, for communication between the subject and a caregiver based on the identification of the at least one abnormal event.

4. (canceled)

6. (canceled)

8. (canceled)

10-11. -11. (canceled)

13-18. -18. (canceled)

20. A system for detection and monitoring of at least one position based activity by a subject, comprising:

a wearable monitoring device configured to be detachable and wearable on a subject, comprising;

at least one position tag configured to communicate with a plurality of anchor devices, each device including at least one sensor configured for tracking location of the at least one position tag in a space; and

at least one activity sensor configured to sense at least one body movement of the subject within the space; and

a monitoring unit configured to;

receive body movement and location data of the subject within the space, and a time of day, and day of week;

generate, based on a contextual analysis of a deviation of a correlation of the body movement and the location data and time of day and day of week from past recorded data of a previous combination of similar body movement data and location data and time of day and day of week, a message indicative of at least one abnormal event or at least one normal event; and

an activity database storing learned data representing combinations of tracked subject location data and subject body movement data and/or gesture data and/or physiological data, correlated with time of day and day of week, representing different activities, wherein the activity database is in communication with the monitoring unit, and the monitoring unit uses the activity database to identify the at least one abnormal event, wherein the data within the activity database is collected based on one or more members of the group consisting of;

past data of the same subject, data from other similar subjects, data from other similar subjects having similar medical conditions as the subject.

21. The system of claim 20, wherein:

the at least one activity sensor is further configured to sense at least one of;

at least one gesture and at least one postural data of the subject within the space; and

the monitoring unit is further configured to receive at least one of the at least one gesture and the at least one postural change; and

generate, based on a contextual analysis of a correlation of the body movement and the location and time of day and day of week with at least one of the at least one gesture and the at least one postural change, a message indicative of at least one abnormal event or at least one normal event.

22. The system of claim 20, wherein:

the wearable monitoring device further includes at least one physiological sensor configured to sense at least one physiological parameter of the subject within the space; and

the monitoring unit is further configured to receive the at least one physiological parameter; and

generate faster than without the at least one physiological parameter, based on a contextual analysis of a correlation of the body movement and location data with the at least one physiological parameter, a message indicative of at least one abnormal event or at least one normal event.

24. The system of claim 22, further comprising code executable by at least one processor, the code including instructions for activating the at least one physiological sensor based on identification of the at least one abnormal event, to confirm or retract the at least one abnormal event, to reduce overall power consumption.

34. The system of claim 20, wherein the wearable monitoring device further includes a global position element configured to generate a global location of the data representing at least one tracked location of the subject when the subject is located out outdoors and out of range of the plurality of anchor devices.

36. The system of claim 20, wherein the monitoring unit is further configured to detect a fall based on the detected deviation from past routine in at least one of the following:

the subject is static for a predefined period of time in a location in which the subject is usually active, the subject is static in an abnormal location for the current time of day, the subject is in a location where the subject is usually active and with abnormal heart-rate.

39. The system of claim 20, wherein the monitoring unit is further configured to at least one of:

dynamically increase the rate at which messages are transmitted by the at least one activity sensor of the wearable device when the at least one abnormal event is detected to improve accuracy of determination of the position of the subject, and dynamically reduce the rate at which messages are transmitted when the at least one normal event is detected to reduce overall power consumption.

48. The system of claim 20, wherein at least one of the plurality of anchor devices includes an audio monitor used for communication between the subject and a caregiver based on the identification of the at least one abnormal event.

23. (canceled)

25-33. -33. (canceled)

35. (canceled)

37-38. -38. (canceled)

40. A computerized method of detection and monitoring of care provided by a caregiver to a subject, comprising:

providing a wearable monitoring device including at least one position tag to a caregiver, and another wearable monitoring device including at least one position tag to a subject, the at least one position tag configured to communicate with plurality of anchor devices, each device including at least one sensor for tracking location of the position tag in a space, each wearable monitoring device further configured to be detachable and wearable on the caregiver and on the subject being cared for by the caregiver;

calculating a quality of care dataset based on the relative tracked locations of the at least one position tag of the subject relative to the at least one position tag of the caregiver;

analyzing the quality of care dataset to identify at least one abnormal event in care provided to the subject by the caregiver;

generating an alert indicative of the at least one abnormal event;

providing at least one activity sensor to the caregiver and to the subject, the at least one activity sensor configured to sense at least one of a posture and a gesture of the caregiver and at least one of a posture and a gesture of the subject;

identifying at least one of a sequence of gestures and a sequence of postures of at least one of the caregiver and the subject representing good care or bad care; and

calculating the quality of care dataset based on the sequence of gestures;

wherein identifying at least one of the sequence of gestures and sequence of postures is based on machine learning including training data gathered from the same caregiver and/or different caregivers performing pre-defined good care or had care on the same subject and/or different subjects.

41. The method of claim 40, wherein the quality of care data set includes at least one quality of care metric calculated based on one or more members of the group consisting of:

an average of a distance between the caregiver and the subject as a function of time, a maximal of the distance, and a function of the distance over time.

42. The method of claim 40, wherein analyzing further comprising analyzing the quality of care dataset based on a location context of the subject and the caregiver based on body movements detected by respective position tags.

45. The method of claim 40, wherein the quality of care dataset is calculated based on an analysis of voice data generated by the subject calling the caregiver, and the responsiveness of the caregiver to the calling subject associated with changes in the relative locations of the at least one position tag of the subject relative to the at least one position tag of the caregiver.

43-44. -44. (canceled)

46-47. -47. (canceled)