Method, system and apparatus for fall detection

• US 9,999,377 B2
• Filed: 03/01/2017
• Issued: 06/19/2018
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Ivan Osorio
• Original Assignee: Ivan Osorio
• Inventors: Osorio, Ivan
• Primary Examiner(s): HINDENBURG, MAX F
• Application Number:
  US15/446,819
• Publication Number:
  US 20170172465A1
• Time in Patent Office: 475 Days
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• 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 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/026 Measuring blood flow A61B3/1233, A61B3/1241 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 5/1117 Fall detection
• CPC Class Codes: A61B 5/14551 for measuring blood gases
• CPC Class Codes: A61B 5/16 Devices for psychotechnics using teaching or educational appliances G09B1/00 - G09B7/00; Testing reaction times ; Devices for evaluating the psychological state
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/389 Electromyography [EMG]
• 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 21/043 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

Abstract

Methods, systems, and apparatuses are provided for detecting fall events of a person. Fall events are falls that are likely to occur, are occurring, or have occurred. Fall detectors and fall detector systems detect fall events of the person. Data relating to the person are received from sensors and analyzed to perform fall detection. Data relating to the person includes accelerations and forces experience by the person, changes in body position of the person, movements of the person, and body signals and sounds of the person. Neurological tests are administered to determine levels of responsiveness and awareness of the person in response to detections. Warnings are issued, and safety measures are deployed, in response to detections. Data relating to fall events are recorded and logged. Fall event histories based upon the logged data and fall detection algorithm performance are used to improve future fall detection and prediction.

Claims

1. A method for detecting a fall, comprising:

receiving data from at least one sensor associated with a person;

analyzing the received data to detect changes therein;

detecting the person is falling or that a fall is imminent based on the analysis of the received data;

administering to the person, in response to the detection, a first neurological test requiring the person to manually or orally input a level of responsiveness; and

administering to the person a second neurological test, wherein the second neurological test is at least one of an awareness test or a cognitive level test, and wherein the second neurological test is administered in response to the person not failing the first neurological test.

2. The method of claim 1, wherein administering the first neurological test further comprises at least one of:

administering an orientation test,

administering a motor test, or

administering a memory test.

3. The method of claim 1, wherein the second neurological test is re-administered to the person based on at least one of motor activity of the person, one or more sounds associated with the person, or a time interval.

4. The method of claim 1, further comprising categorizing possible causes of the fall based on a type of fall, a presence or absence of breaking arm movements, a body part that first makes contact with a surface, a body position before the fall, a body position during the fall, a direction of the fall, a body position immediately after the fall, a type of kinetic activity before the fall, an amount of time elapsed since the last kinetic activity of the person, a type and/or a level of kinetic activity, autonomic activity before, during or after the fall, or neurologic activity before, during or after the fall.

5. The method of claim 1, further comprising ranking a severity of the fall based on at least one of a result of the first neurological test, motion data, a presence of pain or severity pain, a force of impact, a site of impact on the body of the person, or a distance traveled by the body of the person after a first impact;

wherein the motion data comprises a duration of time spent falling, a duration of time spent lying down after the fall, or one or more changes in acceleration during the fall.

6. The method of claim 5, further comprising automatically reporting at least one of a location of the person or the ranking of the severity of the fall to a remote entity after detecting the fall.

7. A method for detecting a fall, comprising:

receiving data from at least one sensor associated with a person, wherein the received data includes electromyogram (EMG) data measured from at least one anti-gravitatory muscle;

analyzing the received data to detect changes therein;

detecting the person is falling or that a fall is imminent based on the analysis of the received data, wherein the detection is based at least in part on whether the EMG data deviates above a first threshold indicating abnormally high muscle tone or below a second threshold indicating abnormally decreased muscle tone;

issuing a warning;

administering to the person, in response to the detection, a neurological test requiring the person to manually or orally input a level of responsiveness or awareness; and

logging to a memory at least of one a date and time of the fall or one or more results of a test administered to the person.

8. The method of claim 7, wherein the received data includes data detected by at least one of a tri-axial accelerometer, a clinometer, a force transducer, a gyroscope, a body signal sensor, an optical sensor, a motor sensor or a sound sensor, and

wherein the received data includes at least one of a change in acceleration along at least one axis of the tri-axial accelerometer, change in incline or decline detected by the clinometer, a measure of force detected by the force transducer, a sway or a loss of balance detected by the gyroscope, the clinometer, or the tri-axial accelerometer, a body signal detected by the body signal sensor, a body movement detected by the optical sensor, a muscle state detected by the motor sensor, or a sound associated with the person detected by the sound sensor.

9. The method of claim 7, wherein the neurological test is at least one of an awareness test or a cognitive level test.

10. The method of claim 7, wherein the fall detection is further based on a force of contraction on at least one anti-gravitatory muscle or at least one of its antagonists.

11. The method of claim 7, wherein detecting a person is falling or that a fall is imminent is based at least upon a value of the received data crossing a threshold or deviating from a baseline value by a predetermined amount.

12. The method of claim 11, further comprising adjusting the threshold or the baseline value based upon at least on one of a fall history of the person or past performance of an algorithm used for fall detection.

13. The method of claim 7, wherein the fall detection is further based on a decrease in autonomic signals below a first autonomic baseline or above a second autonomic baseline.

14. The method of claim 7, further comprising sensing a force of impact on a part of the body of the person resulting from the fall.

15. A method for detecting whether a person has fallen, comprising:

receiving a measure of force from a sensor associated with the person;

analyzing the measure of force with respect to time;

detecting the person has fallen based on the analysis of the measure of force with respect to time;

administering to the person, in response to the detection, a first neurological test requiring the person to manually or orally input a level of responsiveness;

administering to the person a second neurological test, wherein the second neurological test is at least one of an awareness test or a cognitive level test, and wherein the second neurological test is administered in response to the person not failing the first neurological test;

logging to a memory at least one of, a date and time of the fall, a force of impact or results of the neurological test; and

issuing a warning in response to the detection that the person has fallen.

16. The method of claim 15, wherein the sensor is a force transducer or a tri-axial accelerometer.

17. The method of claim 15, wherein the first neurological test includes at least one of an awareness test or a cognitive level test.

18. The method of claim 15, further comprising:

logging an amount of time spent in an unresponsive state or an amount of time spent lying on the ground.

19. The method of claim 15, further comprising:

automatically reporting at least one of a location of the person or a severity of the fall to a remote entity after detecting the fall.