Novel AI driven approach to classify infant motor functions

Abstract The past decade has evinced a boom of computer-based approaches to aid movement assessment in early infancy. Increasing interests have been dedicated to develop AI driven approaches to complement the classic Prechtl general movements assessment (GMA). This study proposes a novel machine lea...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Simon Reich, Dajie Zhang, Tomas Kulvicius, Sven Bölte, Karin Nielsen-Saines, Florian B. Pokorny, Robert Peharz, Luise Poustka, Florentin Wörgötter, Christa Einspieler, Peter B. Marschik
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/5e84508d3ab84cf5b9b5854daeaa0dd4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5e84508d3ab84cf5b9b5854daeaa0dd4
record_format	dspace
spelling	oai:doaj.org-article:5e84508d3ab84cf5b9b5854daeaa0dd42021-12-02T17:02:05ZNovel AI driven approach to classify infant motor functions10.1038/s41598-021-89347-52045-2322https://doaj.org/article/5e84508d3ab84cf5b9b5854daeaa0dd42021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-89347-5https://doaj.org/toc/2045-2322Abstract The past decade has evinced a boom of computer-based approaches to aid movement assessment in early infancy. Increasing interests have been dedicated to develop AI driven approaches to complement the classic Prechtl general movements assessment (GMA). This study proposes a novel machine learning algorithm to detect an age-specific movement pattern, the fidgety movements (FMs), in a prospectively collected sample of typically developing infants. Participants were recorded using a passive, single camera RGB video stream. The dataset of 2800 five-second snippets was annotated by two well-trained and experienced GMA assessors, with excellent inter- and intra-rater reliabilities. Using OpenPose, the infant full pose was recovered from the video stream in the form of a 25-points skeleton. This skeleton was used as input vector for a shallow multilayer neural network (SMNN). An ablation study was performed to justify the network’s architecture and hyperparameters. We show for the first time that the SMNN is sufficient to discriminate fidgety from non-fidgety movements in a sample of age-specific typical movements with a classification accuracy of 88%. The computer-based solutions will complement original GMA to consistently perform accurate and efficient screening and diagnosis that may become universally accessible in daily clinical practice in the future.Simon ReichDajie ZhangTomas KulviciusSven BölteKarin Nielsen-SainesFlorian B. PokornyRobert PeharzLuise PoustkaFlorentin WörgötterChrista EinspielerPeter B. MarschikNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Simon Reich Dajie Zhang Tomas Kulvicius Sven Bölte Karin Nielsen-Saines Florian B. Pokorny Robert Peharz Luise Poustka Florentin Wörgötter Christa Einspieler Peter B. Marschik Novel AI driven approach to classify infant motor functions
description	Abstract The past decade has evinced a boom of computer-based approaches to aid movement assessment in early infancy. Increasing interests have been dedicated to develop AI driven approaches to complement the classic Prechtl general movements assessment (GMA). This study proposes a novel machine learning algorithm to detect an age-specific movement pattern, the fidgety movements (FMs), in a prospectively collected sample of typically developing infants. Participants were recorded using a passive, single camera RGB video stream. The dataset of 2800 five-second snippets was annotated by two well-trained and experienced GMA assessors, with excellent inter- and intra-rater reliabilities. Using OpenPose, the infant full pose was recovered from the video stream in the form of a 25-points skeleton. This skeleton was used as input vector for a shallow multilayer neural network (SMNN). An ablation study was performed to justify the network’s architecture and hyperparameters. We show for the first time that the SMNN is sufficient to discriminate fidgety from non-fidgety movements in a sample of age-specific typical movements with a classification accuracy of 88%. The computer-based solutions will complement original GMA to consistently perform accurate and efficient screening and diagnosis that may become universally accessible in daily clinical practice in the future.
format	article
author	Simon Reich Dajie Zhang Tomas Kulvicius Sven Bölte Karin Nielsen-Saines Florian B. Pokorny Robert Peharz Luise Poustka Florentin Wörgötter Christa Einspieler Peter B. Marschik
author_facet	Simon Reich Dajie Zhang Tomas Kulvicius Sven Bölte Karin Nielsen-Saines Florian B. Pokorny Robert Peharz Luise Poustka Florentin Wörgötter Christa Einspieler Peter B. Marschik
author_sort	Simon Reich
title	Novel AI driven approach to classify infant motor functions
title_short	Novel AI driven approach to classify infant motor functions
title_full	Novel AI driven approach to classify infant motor functions
title_fullStr	Novel AI driven approach to classify infant motor functions
title_full_unstemmed	Novel AI driven approach to classify infant motor functions
title_sort	novel ai driven approach to classify infant motor functions
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/5e84508d3ab84cf5b9b5854daeaa0dd4
work_keys_str_mv	AT simonreich novelaidrivenapproachtoclassifyinfantmotorfunctions AT dajiezhang novelaidrivenapproachtoclassifyinfantmotorfunctions AT tomaskulvicius novelaidrivenapproachtoclassifyinfantmotorfunctions AT svenbolte novelaidrivenapproachtoclassifyinfantmotorfunctions AT karinnielsensaines novelaidrivenapproachtoclassifyinfantmotorfunctions AT florianbpokorny novelaidrivenapproachtoclassifyinfantmotorfunctions AT robertpeharz novelaidrivenapproachtoclassifyinfantmotorfunctions AT luisepoustka novelaidrivenapproachtoclassifyinfantmotorfunctions AT florentinworgotter novelaidrivenapproachtoclassifyinfantmotorfunctions AT christaeinspieler novelaidrivenapproachtoclassifyinfantmotorfunctions AT peterbmarschik novelaidrivenapproachtoclassifyinfantmotorfunctions
_version_	1718381970191286272

Novel AI driven approach to classify infant motor functions

Ejemplares similares