Bringing spatiotemporal gait analysis into clinical practice: Instrument validation and pilot study of a commercial sensorized carpet.
Accidental Falls
/ prevention & control
Aged
Algorithms
Cluster Analysis
Female
Floors and Floorcoverings
Gait
Gait Analysis
/ instrumentation
Healthy Volunteers
Humans
Male
Middle Aged
Pilot Projects
ROC Curve
Rehabilitation
/ instrumentation
Signal Processing, Computer-Assisted
Spatio-Temporal Analysis
Fall prevention
Gait analysis
Remote monitoring,
Sensorized carpet
Signal processing
Journal
Computer methods and programs in biomedicine
ISSN: 1872-7565
Titre abrégé: Comput Methods Programs Biomed
Pays: Ireland
ID NLM: 8506513
Informations de publication
Date de publication:
May 2020
May 2020
Historique:
received:
26
07
2019
revised:
01
12
2019
accepted:
20
12
2019
pubmed:
11
1
2020
medline:
9
2
2021
entrez:
11
1
2020
Statut:
ppublish
Résumé
We illustrate a low-cost platform easing the estimation of spatio-temporal parameters (GA-STP) ready for large-scale deployment in fall prevention. We used a commercial sensorized carpet with a limited cost and a very coarse resolution. An instrument validation test was accomplished: the Wilcoxon test for paired samples and the correlation test with Spearman method were used to compare the values computed by the platform with reference ones. Hierarchical clustering using Ward's method and ROC curves have been used to assess the performance in a pilot study enrolling patients. Validation shows no significant difference between computed and reference values of gait speed (ρ-value:0.99; p-value:2.2E-16), step number (ρ-value:0.91; p-value:5.8E-16) and stride-length (ρ-value:0.92; p-value:7.5E-9). The clinical pilot study confirms that the platform may also be used to track the improvements occurring during a rehabilitation program. We believe that the use of a commercial carpet makes the solution proposed ready to be deployed on a large scale for effectively bringing GA into the clinical practice.
Sections du résumé
BACKGROUND AND OBJECTIVE
OBJECTIVE
We illustrate a low-cost platform easing the estimation of spatio-temporal parameters (GA-STP) ready for large-scale deployment in fall prevention.
METHODS
METHODS
We used a commercial sensorized carpet with a limited cost and a very coarse resolution. An instrument validation test was accomplished: the Wilcoxon test for paired samples and the correlation test with Spearman method were used to compare the values computed by the platform with reference ones. Hierarchical clustering using Ward's method and ROC curves have been used to assess the performance in a pilot study enrolling patients.
RESULTS
RESULTS
Validation shows no significant difference between computed and reference values of gait speed (ρ-value:0.99; p-value:2.2E-16), step number (ρ-value:0.91; p-value:5.8E-16) and stride-length (ρ-value:0.92; p-value:7.5E-9). The clinical pilot study confirms that the platform may also be used to track the improvements occurring during a rehabilitation program.
CONCLUSIONS
CONCLUSIONS
We believe that the use of a commercial carpet makes the solution proposed ready to be deployed on a large scale for effectively bringing GA into the clinical practice.
Identifiants
pubmed: 31923818
pii: S0169-2607(19)31165-4
doi: 10.1016/j.cmpb.2019.105292
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
105292Informations de copyright
Copyright © 2019. Published by Elsevier B.V.