Method for quantifying balance

Patent metadata

Field	Value
Publication number	US-11246525-B2
Application number	US-201816763573-A
Country	US
Kind code	B2
Filing date	Nov 16, 2018
Priority date	Nov 17, 2017
Publication date	Feb 15, 2022
Grant date	Feb 15, 2022

Abstract

A method for quantifying the balance of an individual includes segmenting, as a function of time, a statokinesigram(s) of an individual so as to generate several statokinesigram portions; extracting, from the statokinesigram portions, values of at least one trajectory parameter; determining the value of at least two quantifiers, from the values of trajectory parameters extracted in the extraction step, for each of the statokinesigram portions generated in the segmentation step; and determining said value representative of the balance of the individual from the values of the quantifiers of each of the statokinesigram portions. The method may be implemented by a processor and memory.

First claim

The invention claimed is:

1. A method for quantifying the balance of an individual to obtain a value representative of the balance of said individual, said method being implemented by a device comprising at least one processor connected to a memory, said method comprising:
recording, on the memory, at least one statokinesigram of the individual obtained from a platform on which the individual is standing, the platform comprising pressure and/or force sensors, and the statokinesigram comprising data related to a trajectory or displacement of a center of pressure;
segmenting as a function of time, at least one of the statokinesigrams of the individual recorded on the memory, by the processor, to generate several statokinesigram portions;
extracting, by the processor and from the statokinesigram portions, values of at least one trajectory parameter, the trajectory parameter being a position, stability, and/or dynamics trajectory parameter of the center of pressure;
determining, by the processor, values of at least two quantifiers, from the values of trajectory parameters extracted in the extraction step, for each of the statokinesigram portions generated in the segmentation step;
inputting the determined values of said quantifiers to an unsupervised partitioning algorithm, the unsupervised portioning algorithm being implemented by the processor and being configured to output an assigned score or category classification for each of the statokinesiogram portions; and
determining, by the processor, said value representative of the balance of the individual based on the assigned scores or category classifications for each of the statokinesiogram portions, as output by the unsupervised partitioning algorithm,
wherein each of the statokinesigram portions is one second to three seconds long, and
wherein consecutive statokinesigram portions have an overlap ratio of 25% to 95%.

2. The quantification method according to claim 1 , wherein the segmenting step generates, for each statokinesigram, at least ten statokinesigram portions.

3. The quantification method according to claim 1 , wherein the unsupervised partitioning algorithm is an unsupervised Gaussian mixture model, a hierarchical bottom-up classification, or a hierarchical top-down classification.

4. The quantification method according to claim 1 , further comprising:
generating raw data corresponding to a displacement of the center of pressure, the pressure being applied by the whole body of the individual over time on the platform.

5. The quantification method according to claim 4 , further comprising:
transforming the raw data into trajectory data of the center of pressure.

6. The quantification method according to claim 4 , wherein the raw data corresponding to the displacement of the center of pressure is obtained in a Romberg test.

7. The quantification method according to claim 6 ,
wherein the at least one of the statokinesigrams comprises a statokinesigram obtained while the individual has his/her eyes open (O) and a statokinesigram obtained while the individual has his/her eyes closed (F), and
wherein the method further comprises, for at least one of the quantifiers, calculating an O/F or F/O ratio corresponding to a ratio between the value of the trajectory parameter calculated from the statokinesigram obtained while the individual has his/her eyes open (O) and the value of the trajectory parameter calculated from the statokinesigram obtained while the individual has his/her eyes closed (O/F ratio) or the opposite (F/O ratio).

8. The quantification method according to claim 1 , wherein the trajectory parameter is a position trajectory parameter, and the position trajectory parameter is:
a position of the center of pressure along an X-axis, corresponding to the position of the center of pressure compared to a median line of an orthonormal reference frame in a plane of the X-axis;
a position of the center of pressure along a Y-axis, corresponding to the position of the center of pressure with respect to a median line of an orthonormal reference frame in a plane of the Y-axis; or
a radius in polar coordinates, corresponding to a distance of the center of pressure from an average position of the center of pressure according to the orthonormal reference plane.

9. The quantification method according to claim 1 , wherein the trajectory parameter is a stability trajectory parameter, and the stability trajectory parameter is:
a radial balance corresponding to a maximum distance of the center of pressure from its current value at a given time over a predefined duration between 0.1 and 2 seconds;
a time balance corresponding to a time required for the center of pressure to move more than a distance between 1 and 10 millimeters away from its current position at any given time; or
a ballistic interval corresponding to a time interval between two balance positions.

10. The quantification method according to claim 1 , wherein the trajectory parameter is a dynamics trajectory parameter, and the dynamics trajectory parameter is:
a velocity of the displacement of the center of pressure, calculated for all sampling points of the displacement of the center of pressure over the duration of the acquisition;
an acceleration of the displacement of the center of pressure, calculated for all sampling points of the displacement of the center of pressure over the duration of the acquisition;
a power corresponding to a value of a scalar product of a velocity and acceleration calculated for all sampling points; or
a deviation corresponding to a normal of a vector product of the velocity and acceleration calculated for all sampling points.

11. The quantification method according to claim 1 , wherein the quantifiers calculated for each portion of the statokinesigram are a mean value, a variance, a square mean, or an extreme value, of the extracted trajectory parameter.

12. A device for quantifying the balance of an individual, said device comprising:
a receiver and/or transmitter configured to receive a statokinesigram of said individual obtained from a platform on which the individual is standing, the platform comprising pressure and/or force sensors, and the statokinesigram comprising data related to a trajectory or displacement of a center of pressure;
a memory configured to record said statokinesigram; and
at least one processor configured to connect to the memory and configured to:
segment, as a function of time, the statokinesigrams of the individual recorded on the memory to generate several statokinesigram portions;
extract, from the statokinesigram portions, values of at least one trajectory parameter, the trajectory parameter being a position, stability, and/or dynamics trajectory parameter of the center of pressure;
determine several quantifiers from the extracted values of the at least one trajectory parameter;
input the determined values of said quantifiers to an unsupervised partitioning algorithm, the unsupervised portioning algorithm being implemented by the processor and being configured to output an assigned score or category classification for each of the statokinesiogram portions; and
determine a value representative of the balance of the individual based on the assigned scores or category classifications for each of the statokinesiogram portions, as output by the unsupervised partitioning algorithm,

wherein each of the statokinesigram portions is one second to three seconds long, and
wherein consecutive statokinesigram portions have an overlap ratio of 25% to 95%.

13. The quantifying device according to claim 12 , wherein the processor is further configured to process raw d

Assignees

• Hopitaux Paris Assist Publique
• Centre Nat Rech Scient
• Etat Francais—Ministere De La Defense—Direction Centrale Du Service De Sante Des Armee
• Ecole Normale Superieure Paris Saclay
• Univ Paris Xiii Paris Nord Villetaneuse
• Univ Paris

Inventors

• Vayatis Nicolas
• Vidal Pierre Paul
• Audiffren Julien
• Yelnik Alain
• Ricard Damien
• Bargiotas Ioannis
• Oudre Laurent
• Buffat Stéphane

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• A61B5/7264

  Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems · CPC title

• A61B5/1122

  of movement trajectories · CPC title

• A61B5/4023 Primary

  Evaluating sense of balance · CPC title

• A61B2562/0247

  Pressure sensors · CPC title