Classifying muscle parameters with artificial neural networks and simulated lateral pinch data.

<h4>Objective</h4>Hill-type muscle models are widely employed in simulations of human movement. Yet, the parameters underlying these models are difficult or impossible to measure in vivo. Prior studies demonstrate that Hill-type muscle parameters are encoded within dynamometric data. But...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kalyn M Kearney, Joel B Harley, Jennifer A Nichols
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/6b5ee3e5a9bf444db366dcddb94e50fc
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6b5ee3e5a9bf444db366dcddb94e50fc
record_format	dspace
spelling	oai:doaj.org-article:6b5ee3e5a9bf444db366dcddb94e50fc2021-12-02T20:04:45ZClassifying muscle parameters with artificial neural networks and simulated lateral pinch data.1932-620310.1371/journal.pone.0255103https://doaj.org/article/6b5ee3e5a9bf444db366dcddb94e50fc2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0255103https://doaj.org/toc/1932-6203<h4>Objective</h4>Hill-type muscle models are widely employed in simulations of human movement. Yet, the parameters underlying these models are difficult or impossible to measure in vivo. Prior studies demonstrate that Hill-type muscle parameters are encoded within dynamometric data. But, a generalizable approach for estimating these parameters from dynamometric data has not been realized. We aimed to leverage musculoskeletal models and artificial neural networks to classify one Hill-type muscle parameter (maximum isometric force) from easily measurable dynamometric data (simulated lateral pinch force). We tested two neural networks (feedforward and long short-term memory) to identify if accounting for dynamic behavior improved accuracy.<h4>Methods</h4>We generated four datasets via forward dynamics, each with increasing complexity from adjustments to more muscles. Simulations were grouped and evaluated to show how varying the maximum isometric force of thumb muscles affects lateral pinch force. Both neural networks classified these groups from lateral pinch force alone.<h4>Results</h4>Both neural networks achieved accuracies above 80% for datasets which varied only the flexor pollicis longus and/or the abductor pollicis longus. The inclusion of muscles with redundant functions dropped model accuracies to below 30%. While both neural networks were consistently more accurate than random guess, the long short-term memory model was not consistently more accurate than the feedforward model.<h4>Conclusion</h4>Our investigations demonstrate that artificial neural networks provide an inexpensive, data-driven approach for approximating Hill-type muscle-tendon parameters from easily measurable data. However, muscles of redundant function or of little impact to force production make parameter classification more challenging.Kalyn M KearneyJoel B HarleyJennifer A NicholsPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 9, p e0255103 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Kalyn M Kearney Joel B Harley Jennifer A Nichols Classifying muscle parameters with artificial neural networks and simulated lateral pinch data.
description	<h4>Objective</h4>Hill-type muscle models are widely employed in simulations of human movement. Yet, the parameters underlying these models are difficult or impossible to measure in vivo. Prior studies demonstrate that Hill-type muscle parameters are encoded within dynamometric data. But, a generalizable approach for estimating these parameters from dynamometric data has not been realized. We aimed to leverage musculoskeletal models and artificial neural networks to classify one Hill-type muscle parameter (maximum isometric force) from easily measurable dynamometric data (simulated lateral pinch force). We tested two neural networks (feedforward and long short-term memory) to identify if accounting for dynamic behavior improved accuracy.<h4>Methods</h4>We generated four datasets via forward dynamics, each with increasing complexity from adjustments to more muscles. Simulations were grouped and evaluated to show how varying the maximum isometric force of thumb muscles affects lateral pinch force. Both neural networks classified these groups from lateral pinch force alone.<h4>Results</h4>Both neural networks achieved accuracies above 80% for datasets which varied only the flexor pollicis longus and/or the abductor pollicis longus. The inclusion of muscles with redundant functions dropped model accuracies to below 30%. While both neural networks were consistently more accurate than random guess, the long short-term memory model was not consistently more accurate than the feedforward model.<h4>Conclusion</h4>Our investigations demonstrate that artificial neural networks provide an inexpensive, data-driven approach for approximating Hill-type muscle-tendon parameters from easily measurable data. However, muscles of redundant function or of little impact to force production make parameter classification more challenging.
format	article
author	Kalyn M Kearney Joel B Harley Jennifer A Nichols
author_facet	Kalyn M Kearney Joel B Harley Jennifer A Nichols
author_sort	Kalyn M Kearney
title	Classifying muscle parameters with artificial neural networks and simulated lateral pinch data.
title_short	Classifying muscle parameters with artificial neural networks and simulated lateral pinch data.
title_full	Classifying muscle parameters with artificial neural networks and simulated lateral pinch data.
title_fullStr	Classifying muscle parameters with artificial neural networks and simulated lateral pinch data.
title_full_unstemmed	Classifying muscle parameters with artificial neural networks and simulated lateral pinch data.
title_sort	classifying muscle parameters with artificial neural networks and simulated lateral pinch data.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/6b5ee3e5a9bf444db366dcddb94e50fc
work_keys_str_mv	AT kalynmkearney classifyingmuscleparameterswithartificialneuralnetworksandsimulatedlateralpinchdata AT joelbharley classifyingmuscleparameterswithartificialneuralnetworksandsimulatedlateralpinchdata AT jenniferanichols classifyingmuscleparameterswithartificialneuralnetworksandsimulatedlateralpinchdata
_version_	1718375547399045120

Classifying muscle parameters with artificial neural networks and simulated lateral pinch data.

Ejemplares similares