Fall detection system and method

• US 10,335,059 B2
• Filed: 08/28/2014
• Issued: 07/02/2019
• Est. Priority Date: 09/11/2013
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Annegarn, Janneke, Ten Kate, Warner Rudoph Theophile, Baldus, Heribert
• Primary Examiner(s): Abouelela, May A
• Application Number:
  US14/917,603
• Publication Number:
  US 20160220153A1
• Time in Patent Office: 1,769 Days
• Field of Search: 600300, 600587, 600595, 34053912
• CPC Class Codes: A61B 2560/0223 of calibration, e.g. protocols for calibrating sensors
• CPC Class Codes: A61B 2560/0242 adapted to measure environmental factors, e.g. temperature, pollution
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/1117 Fall detection
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: G01P 13/00 Indicating or recording presence, absence, or direction, of movement electric switches H01H; counting moving objects G06M7/00
• 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 29/185 Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
• CPC Class Codes: G08B 29/20 Calibration, including self-calibrating arrangements

Abstract

There is provided a fall detection system for use in detecting falls by a user, the fall detection system comprising a processing unit configured to determine context information about the user and/or the environment in which the user is located, and to increase the sensitivity of a fall detection algorithm used to detect falls by a user in the event that the determined context information indicates that the user is or may be at an increased risk of falling, the increase in sensitivity occurring while the increased risk of falling is indicated by the determined context information.

Claims

1. A fall detection system for use in detecting falls by a user, the fall detection system comprising:

a processing unit configured to determine context information about the user and/or an environment in which the user is located, and to increase a detection sensitivity of a fall detection algorithm used to detect falls by the user based on the determined context information indicating that the user is at an increased risk of falling, the increase in detection sensitivity occurring while the increased risk of falling is indicated by the determined context information.

2. The fall detection system of claim 1, wherein the context information comprises an indication of whether the user is performing a fall risk assessment test or balance training, and the processing unit is configured to determine that the user is at the increased risk of falling if the context information indicates that the user is performing the fall risk assessment test or the balance training.

3. The fall detection system of claim 1, wherein the context information comprises an indication of whether the user is walking, and the processing unit is configured to determine that the user is at the increased risk of falling if the context information indicates that the user is walking.

4. The fall detection system of claim 1, wherein the context information comprises an indication of whether an unusual movement pattern for the user has been detected, and the processing unit is configured to determine that the user is at the increased risk of falling if the context information indicates the unusual movement pattern.

5. The fall detection system of claim 1, wherein the context information comprises an indication of a current location of the user, and the processing unit is configured to determine that the user is at the increased risk of falling if the current location of the user is a known location where the user is at a higher risk of falling.

6. The fall detection system of claim 1, wherein the context information about the environment in which the user is located comprises an indication of an ambient light in the user'"'"'s location, an indication of how even or uneven the ground is, an indication of a current weather or temperature and/or an indication of an ambient noise level and the processing unit is configured to determine that the user is at the increased risk of falling if the ambient light is below a threshold, if the ground is uneven, if the current weather is wet or the temperature is below a threshold and/or if the ambient noise level is above a threshold.

7. The fall detection system of claim 1, wherein the context information comprises an indication of a current time, and the processing unit is configured to determine that the user is at the increased risk of falling if the current time is within one or more specified time periods.

8. The fall detection system of claim 7, wherein the one or more specified time periods comprises night time and/or time periods shortly before and/or after a scheduled dose of medication.

9. The fall detection system of claim 1, wherein the context information comprises an indication of whether the user is making use of a required walking aid, whether the user is wearing their glasses, and/or an indication of a type of shoes the user is wearing, and the processing unit is configured to determine that the user is at the increased risk of falling if the user is not using the required walking aid, not wearing their glasses and/or not wearing their regular or the correct shoes.

10. The fall detection system of claim 1, wherein the context information comprises an indication of a current activity level of the user, and the context information indicates that the user is at the increased risk of falling if the current activity level is above a threshold activity level.

11. The fall detection system of claim 1, wherein the processing unit is further configured to determine if the context information indicates that the user is at a decreased risk of falling, and to decrease the detection sensitivity of the fall detection algorithm while the decreased risk of falling is indicated by the determined context information.

12. The fall detection system of claim 1, wherein the processing unit is configured to adjust the detection sensitivity of the fall detection algorithm by moving an operating point on a receiver operating characteristic curve, the receiver operating characteristic curve comprising a relation between detection probability and false alarm rate.

13. A method of operating a fall detection system to detect falls by a user, the method comprising:

in a processing unit;

determining context information about the user and/or an environment in which the user is located; and

based on the determined context information indicating that the user is at an increased risk of falling, increasing a detection sensitivity of a fall detection algorithm used to detect falls by the user while the increased risk of falling is indicated by the determined context information.

14. The method of claim 13, the method further comprising:

determining further context information about the user and/or the environment in which the user is located; and

resetting or reducing the detection sensitivity of the fall detection algorithm if the further context information indicates that the user is no longer at an increased risk of falling.

15. The method of claim 13, the method further comprising:

initially operating the fall detection system with the fall detection algorithm set to a normal detection sensitivity corresponding to a normal risk of falling for the user;

wherein when the context information indicates that the user is at an increased risk of falling relative to the normal risk of falling for the user, the detection sensitivity of the fall detection algorithm is increased above the normal detection sensitivity.

16. The method of claim 13, wherein the context information comprises an indication of whether the user is walking, the method further comprising determining that the user is at the increased risk of falling if the context information indicates that the user is walking.

17. The method of claim 13, wherein the context information comprises an indication of whether an unusual movement pattern for the user has been detected, the method further comprising determining that the user is at the increased risk of falling if the context information indicates the unusual movement pattern.

18. The method of claim 13, wherein the context information comprises an indication of a current location of the user, the method further comprising determining that the user is at the increased risk of falling if the current location of the user is a known location where the user is at a higher risk of falling.

19. The method of claim 13, wherein the context information about the environment in which the user is located comprises an indication of an ambient light in the user'"'"'s location, an indication of how even or uneven the ground is, an indication of a current weather or temperature and/or an indication of an ambient noise level, the method further comprising determining that the user is at the increased risk of falling if the ambient light is below a threshold, if the ground is uneven, if the current weather is wet or the temperature is below a threshold and/or if the ambient noise level is above a threshold.

20. The method of claim 13, wherein the context information comprises an indication of a current time, wherein the method further comprising determining that the user is at the increased risk of falling if the current time is within one or more specified time periods, wherein the one or more specified time periods comprises night time and/or time periods shortly before and/or after a scheduled dose of medication.

21. A non-transitory computer program product having computer readable code embodied therein, the computer readable code being configured such that, on execution by a suitable computer or processing unit, the computer or processing unit performs a method of:

determining context information about a user and/or an environment in which the user is located; and

based on the determined context information indicating that the user is at an increased risk of falling, increasing a detection sensitivity of a fall detection algorithm used to detect falls by the user while the increased risk of falling is indicated by the determined context information.