A Brief Review on the Sensor Measurement Solutions for the ten-meter walk test. Computers 2021, 10, 49
Journal
Computers
Date Issued
2021
Author(s)
Pires, Ivan Miguel
Lopes, Eurico
Villasana, María Vanessa
Ponciano, Vasko
Abstract
The wide-spread use of wearables and the adoption of the Internet of Things (IoT) paradigm provide an opportunity to use mobile-device sensors for medical applications. Sensors available in the commonly used devices may inspire innovative solutions for physiotherapy striving for
accurate and early identification of various pathologies. An essential and reliable performance
measure is the ten-meter walk test, which is employed to determine functional mobility, gait, and
vestibular function. Sensor-based approaches can identify the various test phases and their segmented duration, among other parameters. The measurement parameter primarily used is related to the tests’ duration, and after identifying patterns, a variety of physical treatments can be recommended. This paper reviews multiple studies focusing on automated measurements of the ten-meter walk test with different sensors. Most of the analyzed studies measure similar parameters as traditional methods, such as velocity, duration, and other involuntary and dangerous patients’ movements after stroke. That provides an opportunity to measure different parameters that can be later fed into machine learning models for analyzing more complex patterns.
accurate and early identification of various pathologies. An essential and reliable performance
measure is the ten-meter walk test, which is employed to determine functional mobility, gait, and
vestibular function. Sensor-based approaches can identify the various test phases and their segmented duration, among other parameters. The measurement parameter primarily used is related to the tests’ duration, and after identifying patterns, a variety of physical treatments can be recommended. This paper reviews multiple studies focusing on automated measurements of the ten-meter walk test with different sensors. Most of the analyzed studies measure similar parameters as traditional methods, such as velocity, duration, and other involuntary and dangerous patients’ movements after stroke. That provides an opportunity to measure different parameters that can be later fed into machine learning models for analyzing more complex patterns.
Subjects
File(s)![Thumbnail Image]()
Loading...
Name
computers-10-00049.pdf
Size
552.05 KB
Format
Adobe PDF
Checksum
(MD5):c1d9cb6fd1c57b5ffd51d7fa991b59a8