Longitudinal Evaluation of Diadochokinesia Characteristics for Hemiplegic Ankle Rehabilitation by Wearable Systems with Machine Learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21460%2F22%3A00365152" target="_blank" >RIV/68407700:21460/22:00365152 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9991484" target="_blank" >https://ieeexplore.ieee.org/document/9991484</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/EHB55594.2022.9991484" target="_blank" >10.1109/EHB55594.2022.9991484</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Longitudinal Evaluation of Diadochokinesia Characteristics for Hemiplegic Ankle Rehabilitation by Wearable Systems with Machine Learning

Popis výsledku v původním jazyce

The ability to objectively evaluate the efficacy of a rehabilitation regimen from a longitudinal perspective is significant and enabled through the confluence of wearable and wireless inertial sensor systems and machine learning. These capabilities are demonstrated in the context of a 10 month longitudinal study involving a rehabilitation regimen for improving a hemiplegic ankle, such as with respect to the hemiplegic ankle’s diadochokinesia characteristics. Diadochokinesia represents the ability to alternate between agonist and antagonist muscles, such as the dorsiflexion and plantar flexion musculature. The ability to smoothly transition between dorsiflexion and plantar flexion musculature is inherent for the rhythmic process of gait. Using a smartphone as a functional wearable gyroscope platform secured to the dorsum of the foot by an armband, the kinematic properties of the hemiplegic ankle are quantified and recorded in a longitudinal context. A support vector machine implemented through the Waikato Environment for Knowledge Analysis (WEKA) machine learning platform successfully distinguished between the initial phase and final phase of a 10 month longitudinal study involving a rehabilitation regimen for a hemiplegic ankle with considerable classification accuracy. The implications of the research findings establish a pathway for the ascertaining the efficacy of a rehabilitation regimen based on the signal data acquired by wearable systems in conjunction with machine learning.

Název v anglickém jazyce

Longitudinal Evaluation of Diadochokinesia Characteristics for Hemiplegic Ankle Rehabilitation by Wearable Systems with Machine Learning

Popis výsledku anglicky

The ability to objectively evaluate the efficacy of a rehabilitation regimen from a longitudinal perspective is significant and enabled through the confluence of wearable and wireless inertial sensor systems and machine learning. These capabilities are demonstrated in the context of a 10 month longitudinal study involving a rehabilitation regimen for improving a hemiplegic ankle, such as with respect to the hemiplegic ankle’s diadochokinesia characteristics. Diadochokinesia represents the ability to alternate between agonist and antagonist muscles, such as the dorsiflexion and plantar flexion musculature. The ability to smoothly transition between dorsiflexion and plantar flexion musculature is inherent for the rhythmic process of gait. Using a smartphone as a functional wearable gyroscope platform secured to the dorsum of the foot by an armband, the kinematic properties of the hemiplegic ankle are quantified and recorded in a longitudinal context. A support vector machine implemented through the Waikato Environment for Knowledge Analysis (WEKA) machine learning platform successfully distinguished between the initial phase and final phase of a 10 month longitudinal study involving a rehabilitation regimen for a hemiplegic ankle with considerable classification accuracy. The implications of the research findings establish a pathway for the ascertaining the efficacy of a rehabilitation regimen based on the signal data acquired by wearable systems in conjunction with machine learning.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20601 - Medical engineering

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of 2022 E-Health and Bioengineering Conference (EHB)

ISBN

978-1-6654-8557-9

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

—

Název nakladatele

Gr. T. Popa University of Medicine and Pharmacy

Místo vydání

Iasi

Místo konání akce

Iasi

Datum konání akce

17. 11. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—