Method and system for assessing locomotive bio-rhythms

• US 9,179,862 B2
• Filed: 07/19/2005
• Issued: 11/10/2015
• Est. Priority Date: 07/19/2005
• Status: Active Grant

• Current Assignee: Board of Regents of the University of Nebraska
• Original Assignee: Board of Regents of the University of Nebraska
• Inventors: Stergiou, Nikolaos, Kurz, Maximilian Joseph
• Primary Examiner(s): DOUGHERTY, SEAN PATRICK
• Application Number:
  US11/184,490
• Publication Number:
  US 20070021689A1
• Time in Patent Office: 3,766 Days
• Field of Search: 600/595, 600/546, 600/300, 600/558, 600/559, 706/8, 377/24, 601/5
• US Class Current: 1/1
• CPC Class Codes: A61B 5/1038 Measuring plantar pressure during gait
• 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: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A method, system, and article of manufacture for detecting, recording, quantifying, and classifying gait data. In one embodiment, the method of the invention includes a step of detecting foot contact events using a portable sensor device. Stride data is collected by processing the detected foot contact events to obtain and record gait pattern data. At least one gait stability value is determined from the gait pattern data using a specified gait stability metric. The gait stability value is preferably a mathematical chaos value which is processed utilizing clustering correlation to classify the gait pattern data in association with a neuromuscular status. In a preferred embodiment, fuzzy logic is utilized to correlate the determined gait stability value with a plurality of gait stability values each associated with a distinct neuromuscular status.

Claims

1. A method for analyzing gait comprising:

collecting gait pattern data via a gait monitor device having a portable monitor unit adapted to be wearable by a subject and a gait data collection device including at least one toe-off (TO) force-sensitive sensor adapted to be positioned on a surface of an insole near a front ball of a foot of the subject, and at least one heel strike (HS) force-sensitive sensor adapted to be positioned on a surface of the insole below a heel of the subject, the gait data collection device communicatively coupled to the portable monitor unit and adapted to provide data to the portable monitor unit about initiation and termination of foot contact times during a gait cycle;

specifying, via a data analyzer communicatively coupled to the portable monitor unit, a gait stability metric that is used to quantify a stability associated with the collected gait pattern data;

determining, via one or more processors of the data analyzer, a gait stability value from the gait pattern data using the specified gait stability metric;

wherein the determined gait stability value is a quantification of the stability associated with the collected gait pattern data;

processing, via one or more processors of the data analyzer, the determined gait stability value in association with a pre-classified gait stability value utilizing a clustering correlation module of a memory of the data analyzer to determine the level of association of the collected gait pattern data with pre-classified gait pattern data,

wherein the pre-classified gait pattern data has a pre-specified association with a neuromuscular status; and

classifying, via one or more processors of the data analyzer, the gait pattern data in association with the neuromuscular status based on the determined level of association of the collected gait pattern data with pre-classified gait pattern data.

2. The method of claim 1, wherein the collecting gait pattern data further comprises:

collecting the gait pattern data by detecting and recording foot contact events.

3. The method of claim 2, said collecting further comprising:

collecting data related to foot contact events to detect gait-related events including one or more of (a) initiation and termination of foot contact times during gait, (b) a stance phase duration between heel strike and toe-off, (c) absolute and relative heal strike and toe-off timing;

(d) stride distance;

(e) velocity; and

(f) foot support patterns; and

processing, via one or more processors of the data analyzer, the recorded foot contact events to obtain one or more gait stability values using the gait stability metric and at least one stride interval data.

4. The method of claim 1, wherein:

said gait stability metric is one of multiple gait stability metrics,

said specified gait stability metric is a chaos metric and chaos metric data is processed, via one or more processors, to classify the gait pattern in association with a neuromuscular status and said stability is provided by one of multiple measures for stability which measures include;

(a) a rate of divergence;

(b) a complexity measure, and (c) other measures for stability.

5. The method of claim 4, wherein the chaos metric is included among the group including (a) Lyapunov exponent and (b) a correlation dimension.

6. The method of claim of claim 4, wherein processing, via one or more processors, the gait stability value comprises using a fuzzy logic clustering technique to correlate the gait stability value with a plurality of other gait stability values each associated with a distinct neuromuscular status, wherein a fuzzy clustering algorithm leverages a determined gait stability value to derive one or more of optimal diagnostic indicia and prognostic indicia from the gait pattern data.

7. The method of claim 6, wherein the fuzzy logic clustering technique is included in the group comprising fuzzy subtractive clustering and fuzzy c-means clustering.

8. A system for analyzing gait comprising:

a portable monitor unit adapted to be wearable by a subject;

a gait data collection device communicatively coupled to the portable monitor unit and adapted to provide data to the portable monitor unit about initiation and termination of foot contact times during a gait cycle, the gait data collection device including at least one toe-off (TO) sensor adapted to be positioned on a surface of an insole near a front ball of a foot of the subject, and at least one heel strike (HS) sensor adapted to be positioned on a surface of the insole below a heel of the subject; and

a data analyzer communicatively coupled to the portable monitor unit and having at least one processing unit and a memory, wherein a gait stability value from gait pattern data using a specified gait stability metric is determined and

used to quantify a stability associated with the collected gait pattern data; and

wherein the determined gait stability value is processed in association with a pre-classified gait stability value utilizing clustering correlation to determine the level of association of the collected gait pattern data with pre-classified gait pattern data, the pre-classified gait pattern data having a pre-specified association with a neuromuscular status; and

the gait pattern data is classified in association with the neuromuscular status based on the determined level of association of the collected gait pattern data with pre-classified gait pattern data.

9. The system of claim 8, further comprising.

wherein said data analyzer completes the functions of:

collecting data related to foot contact events to detect gait-related events, including one or more of (a) initiation and termination of foot contact times during gait, (b) a stance phase duration between heel strike and toe-off, (c) absolute and relative heal strike and toe-off timing;

(d) stride distance;

(e) velocity; and

(f) foot support patterns; and

processing the recorded foot contact events to obtain one or more gait stability values using the gait stability metric and at least one stride interval data.

10. The system of claim 8, wherein said specified gait stability metric is a chaos metric, and chaos metric data is processed to classify the gait pattern in association with a neuromuscular status and wherein said stability is provided by one of multiple measures for stability which measures include:

(a) a rate of divergence;

(b) a complexity measure; and

(c) other measures for stability.

11. The system of claim 10, wherein the chaos metric is included among the group including (a) Lyapunov exponent and (b) a correlation dimension.

12. The system of claim of claim 10, wherein said data analyzer utilizes a fuzzy logic clustering technique to correlate the gait stability value with a plurality of gait stability values each associated with a distinct neuromuscular status, wherein a fuzzy clustering algorithm leverages a determined gait stability value to derive one or more of optimal diagnostic indicia and prognostic indicia from the gait pattern data.

13. The system of claim 12, wherein the fuzzy logic clustering technique is included in the group comprising fuzzy subtractive clustering and fuzzy c-means clustering.

14. A system comprising a processor, a computer-readable storage medium having encoding thereon computer-executable instructions for analyzing gait, said computer-executable instructions executable by the processor to:

collect gait pattern data via a gate monitor device having a portable monitor unit adapted to be wearable by a subject and a gait data collection device, the gait data collection device including at least one force-sensitive sensor adapted to be positioned on a surface of an insole;

specify a gait stability metric that is used to quantify a stability associated with the collected gait pattern data;

determine a gait stability value from the gait pattern data using the specified gait stability metric;

wherein the determined gait stability value is a quantification of the stability associated with the collected gait pattern data;

process the determined gait stability value in association with and a pre-classified gait stability value utilizing clustering correlation to determine the level of association of the collected gait pattern data with pre-classified gait pattern data,

wherein the pre-classified gait pattern data has a pre-specified association with a neuromuscular status; and

classify the gait pattern data in association with the neuromuscular status based on the determined level of association of the collected gait pattern data with pre-classified gait pattern data.

15. The system of claim 14, wherein wherein said computer-executable instructions are executable by the processor to collect the gait pattern data by detecting and recording foot contact events.

16. The system of claim 15, said wherein said computer-executable instructions are executable by the processor to further:

collect data related to foot contact events to detect gait-related events, including one or more of (a) initiation and termination of foot contact times during gait, (b) a stance phase duration between heel strike and toe-off, (c) absolute and relative heal strike and toe-off timing;

(d) stride distance;

(e) velocity; and

(f) foot support patterns; and

process the recorded foot contact events to obtain one or more gait stability values using the gait stability metric and at least one stride interval data.

17. The system of claim 14, wherein:

said gait stability metric is one of multiple gait stability metrics;

said specified gait stability metric is a chaos metric, and chaos metric data is processed to classify the gait pattern in association with a neuromuscular status and

said stability is provided by one of multiple measures for stability which measures include;

(a) a rate of divergence;

(b) a complexity measure; and

(c) other measures for stability.

18. The system of claim 17, wherein the chaos metric is included among the group including (a) Lyapunov exponent and (b) a correlation dimension.

19. The system of claim of claim 18, wherein to process the gait stability value comprises using a fuzzy logic clustering technique to correlate the gait stability value with a plurality of pre-classified gait stability values, each associated with a distinct neuromuscular status, wherein a fuzzy clustering algorithm leverages a determined gait stability value to derive one or more of optimal diagnostic indicia and prognostic indicia from the gait pattern data.

20. The system of claim 19, wherein the fuzzy logic clustering technique is included in the group comprising fuzzy subtractive clustering and fuzzy c-means clustering.