Fall prevention

• US 10,670,621 B2
• Filed: 04/23/2015
• Issued: 06/02/2020
• Est. Priority Date: 07/10/2009
• Status: Active Grant

• Current Assignee: Lifeline Systems Company (Koninklijke Philips N.V.)
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Ten Kate, Warner Rudolph Theophile
• Primary Examiner(s): Quigley, Kyle R
• Application Number:
  US14/693,953
• Publication Number:
  US 20150226764A1
• Time in Patent Office: 1,867 Days
• CPC Class Codes: A61B 5/1117 Fall detection
• 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: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: G01C 22/006 Pedometers
• CPC Class Codes: G01P 15/00 Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
• 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: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A fall risk of a user is determined by collecting measurements of the motion of the user. A value for a parameter related to the gait of the user is estimated from the measurements. The fall risk for the user is determined from a comparison of the estimated value with a normal value for the parameter determined from motion of the user in which the user is at their normal risk of falling.

Claims

1. A fall prevention device, comprising:

at least one sensor configured to measure the motion of a user wearing the device;

an alarm; and

a processor programmed to;

determine a value for one or more parameters related only to a gait of the user from the measurements, wherein the one or more parameters includes a forward step size and a lateral step size, and wherein the processor is further programmed to;

integrate horizontal components of the received motion measurements with integral bounds being given by consecutive identified step boundaries to give a start and end position for a step;

determine a norm of the vector connecting the start and end positions to the current value of the forward step size;

define a straight line between the start and end positions;

integrate collected motion measurements occurring during the step to give a series of positions during the step;

determine a distance between each position of the series and the straight line; and

determine a maximum distance of the series of positions as the lateral step size; and

determine a fall risk for the user to trigger a warning of an increased risk of falling, wherein the fall risk is determined from a comparison of the value with a normal value for the one or more parameters determined from motion of the user in which the user is at a normal risk of falling, wherein the determination of the fall risk further comprises;

receive motion measurements over a first period of time when the user is walking normally;

determine a mean μ

of values for the one or more parameters from the motion measurements over the first period of time;

determine a standard deviation σ

of the mean μ

;

receive motion measurements subsequent to the first period of time;

determine a current value a of the one or more parameters from the motion measurements received subsequent to the first period of time;

periodically calculate

2. The device of claim 1, wherein the one or more parameters includes both average forward direction step length and average lateral direction step width over the first period of time and a second period of time, and wherein the second period of time is shorter than the first period of time.

3. The device of claim 1, wherein the one or more parameters includes step length and the processor is further programmed to:

when the user is walking, identify clusters in the motion measurements exceeding a threshold;

from the clusters, determine step boundaries;

from the step boundaries, determine lengths of a plurality of steps; and

average the lengths to calculate the current value a.

4. The device of claim 3, wherein the processor is programmed to identify the step boundaries as the motion measurement in each cluster with the highest magnitude.

5. The device of claim 3, wherein the one or more parameters of the user comprises a step size and the processor is further programmed to:

compute a double integration with respect to time of horizontal acceleration components of the received motion measurements to determine the length of each step.

6. The device of claim 1, wherein the processor is configured to estimate the value for the one or more parameters of the user by identifying a step boundary in the collected measurements by:

identifying clusters of contiguous measurements in the collected measurements in which the magnitude of each of the measurements exceeds a threshold;

identifying clusters of contiguous measurements in the collected measurements in which the magnitude of each of the measurements exceeds a threshold apart from a subset of the measurements whose magnitude is less than the threshold, provided that the subset covers a time period less than a time threshold;

or

identifying clusters of contiguous measurements in the collected measurements, wherein the first collected measurement in the collected measurements whose magnitude exceeds a first threshold denotes the first measurement in a cluster and wherein the first collected measurement after the first measurement in the cluster whose magnitude falls below a second threshold denotes the last measurement in the cluster, provided that the last measurements is more than a minimum period after the first measurement.

7. A method of determining a fall risk of a user using a device comprising one or more motion measuring sensors and one or more processors, the method comprising:

with the one or more motion measuring sensors, collecting measurements of motion of the user;

with the one or more processors;

estimating a value for one or more parameters related only to a gait of the user from the measurements, wherein the one or more parameters comprises a forward step size and a lateral step size, further comprising;

integrating horizontal components of the received motion measurements with integral bounds being given by consecutive identified step boundaries to give a start and end position for a step;

determining a norm of the vector connecting the start and end positions to the current value of the forward step size;

defining a straight line between the start and end positions;

integrating collected motion measurements occurring during the step to give a series of positions during the step;

determining a distance between each position of the series and the straight line; and

determining a maximum distance of the series of positions as the lateral step size; and

determining a fall risk for the user to trigger a warning of an increased risk of falling, wherein the fall risk is determined from a comparison of the estimated value with a normal value for the one or more parameters determined from motion of the user in which the user is at a normal risk of falling, wherein the determining further comprises;

receiving motion measurements over a first period of time when the user is walking normally;

determining a mean μ

of values for the one or more parameters from the motion measurements over the first period of time;

determining a standard deviation σ

of the mean μ

;

receiving motion measurements subsequent to the first period of time;

determining a current value a of the one or more parameters from the motion measurements received subsequent to the first period of time;

periodically calculating

8. The method of claim 7, wherein estimating the value of the one or more parameters includes:

identifying a step boundary by identifying clusters of contiguous measurements in the collected measurements in which at least one of;

a magnitude of each of the measurements exceeds a threshold;

a magnitude of each of the measurements exceeds a threshold, apart from a subset of the measurements whose magnitude is less than the threshold, provided that the subset covers a time period less than a time threshold; and

wherein the collected measurements whose magnitude exceeds a first threshold denotes a first measurement in a cluster and a first collected measurement after the first measurement in the cluster whose magnitude falls below a second threshold denotes a last measurement in the cluster, and in which the last measurement is more than a minimum period after the first measurement.

9. The method of claim 7, wherein the one or more parameters includes a step length and further including with the one or more processors:

when the user is walking, identify clusters in the motion measurements exceeding a threshold;

from the clusters, determining step boundaries;

from the step boundaries, determining lengths of a plurality of steps; and

averaging the lengths to calculate the current value a.

10. The method of claim 8, wherein the one or more parameters comprises a step size and the step of estimating a value for the one or more parameters comprises computing a double integration with respect to time of the horizontal components of the collected measurements relating to acceleration with integration constants being set to zero at the beginning of the step.

11. The method of claim 8, wherein the one or more parameters includes forward step size and the step of estimating a value for the one or more parameters comprises:

integrating horizontal components of the collected measurements with the integral bounds being given by consecutive identified step boundaries to give a start position and an end position for a step; and

determining the forward step size as a norm of a vector connecting the start and end positions.

12. A method of determining a fall risk of a user using a device comprising one or more motion measuring sensors and one or more processors, the method comprising:

with the one or more motion measuring sensors, collecting measurements of motion of the user;

with the one or more processors;

estimating a value for one or more parameters related to a gait of the user from the measurements, wherein estimating the value of the one or more parameters includes;

identifying a step boundary by identifying clusters of contiguous measurements in the collected measurements in which at least one of;

a magnitude of each of the measurements exceeds a threshold;

a magnitude of each of the measurements exceeds a threshold, apart from a subset of the measurements whose magnitude is less than the threshold, provided that the subset covers a time period less than a time threshold; and

wherein the collected measurements whose magnitude exceeds a first threshold denotes a first measurement in a cluster and a first collected measurement after the first measurement in the cluster whose magnitude falls below a second threshold denotes a last measurement in the cluster, and in which the last measurement is more than a minimum period after the first measurement;

wherein the one or more parameters comprises a step size and the step of estimating a value for the one or more parameters comprises computing a double integration with respect to time of the horizontal components of the collected measurements relating to acceleration with integration constants being set to zero at the beginning of the step;

wherein the one or more parameters comprises a lateral step size and the step of estimating a value for the one or more parameters further comprises;

defining a straight line between the start and end positions;

integrating collected measurements occurring during the step to give a series of positions during the step;

determining the distance between each position and the straight line; and

determining the lateral step size as the maximum distance in this series; and

determining a fall risk for the user, wherein the fall risk is determined from a comparison of the estimated value with a normal value for the one or more parameters determined from motion of the user in which the user is at a normal risk of falling.

13. A fall prevention device, comprising:

at least one sensor configured to measure the motion of a user wearing the device; and

a processor programmed to;

determine a value for one or more parameters related only to a gait of the user from the measurements; and

determine a fall risk for the user to trigger a warning of an increased risk of falling, wherein the fall risk is determined from a comparison of the value with a normal value for the one or more parameters determined from motion of the user in which the user is at a normal risk of falling, wherein the one or more parameters includes both average forward direction step length and average lateral direction step width over a first period of time when the user is walking normally and a second period of time, and wherein the second period of time is shorter than the first period of time.