Increased Temporal Variability of Gait in ASD: A Motion Capture and Machine Learning Analysis

Motor deficits, including atypical gait, are common in individuals with autism spectrum disorder (ASD), although the precise nature and cause of this co-occurrence is unclear. Because walking is a natural activity and gait timing is a metric that is relatively accessible to measurement, we explored...

Full description

Saved in:
Bibliographic Details
Main Authors: Katharine Goldthorp, Benn Henderson, Pratheepan Yogarajah, Bryan Gardiner, Thomas Martin McGinnity, Brad Nicholas, Dawn C. Wimpory
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Biology
Subjects:
Online Access:https://www.mdpi.com/2079-7737/14/7/832
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849714662489194496
author Katharine Goldthorp
Benn Henderson
Pratheepan Yogarajah
Bryan Gardiner
Thomas Martin McGinnity
Brad Nicholas
Dawn C. Wimpory
author_facet Katharine Goldthorp
Benn Henderson
Pratheepan Yogarajah
Bryan Gardiner
Thomas Martin McGinnity
Brad Nicholas
Dawn C. Wimpory
author_sort Katharine Goldthorp
collection DOAJ
description Motor deficits, including atypical gait, are common in individuals with autism spectrum disorder (ASD), although the precise nature and cause of this co-occurrence is unclear. Because walking is a natural activity and gait timing is a metric that is relatively accessible to measurement, we explored whether autistic gait could be described solely in terms of the timing of gait parameters. The aim was to establish whether temporal analysis, including machine learning models, could be used as a group classifier between ASD and typically developing (TD) individuals. Thus, we performed a high-resolution temporal analysis of gait on two age-matched groups of male participants: one group with high-functioning ASD and a comparison TD group (each <i>N</i> = 16, age range 7 to 35 years). The primary data were collected using a VICON<sup>®</sup> 3D motion analysis system. Significant increased temporal variability of all gait parameters tested was observed for the ASD group compared to the TD group (<i>p</i> < 0.001). Further machine learning analysis showed that the temporal variability of gait could be used as a group classifier for ASD. Of the twelve models tested, the best-fitting model type was random forest. The temporal analysis of gait with machine learning algorithms may be useful as a future ASD diagnostic aid.
format Article
id doaj-art-78d647219c7d4286a47d07404000a3a9
institution DOAJ
issn 2079-7737
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Biology
spelling doaj-art-78d647219c7d4286a47d07404000a3a92025-08-20T03:13:39ZengMDPI AGBiology2079-77372025-07-0114783210.3390/biology14070832Increased Temporal Variability of Gait in ASD: A Motion Capture and Machine Learning AnalysisKatharine Goldthorp0Benn Henderson1Pratheepan Yogarajah2Bryan Gardiner3Thomas Martin McGinnity4Brad Nicholas5Dawn C. Wimpory6School of Psychology and Sports Science, Bangor University, Bangor LL57 2DG, UKSchool of Computing, Engineering and Intelligent Systems, Ulster University, Derry (Londonderry) BT48 7JL, UKSchool of Computing, Engineering and Intelligent Systems, Ulster University, Derry (Londonderry) BT48 7JL, UKSchool of Computing, Engineering and Intelligent Systems, Ulster University, Derry (Londonderry) BT48 7JL, UKSchool of Computing, Engineering and Intelligent Systems, Ulster University, Derry (Londonderry) BT48 7JL, UKSchool of Psychology and Sports Science, Bangor University, Bangor LL57 2DG, UKSchool of Psychology and Sports Science, Bangor University, Bangor LL57 2DG, UKMotor deficits, including atypical gait, are common in individuals with autism spectrum disorder (ASD), although the precise nature and cause of this co-occurrence is unclear. Because walking is a natural activity and gait timing is a metric that is relatively accessible to measurement, we explored whether autistic gait could be described solely in terms of the timing of gait parameters. The aim was to establish whether temporal analysis, including machine learning models, could be used as a group classifier between ASD and typically developing (TD) individuals. Thus, we performed a high-resolution temporal analysis of gait on two age-matched groups of male participants: one group with high-functioning ASD and a comparison TD group (each <i>N</i> = 16, age range 7 to 35 years). The primary data were collected using a VICON<sup>®</sup> 3D motion analysis system. Significant increased temporal variability of all gait parameters tested was observed for the ASD group compared to the TD group (<i>p</i> < 0.001). Further machine learning analysis showed that the temporal variability of gait could be used as a group classifier for ASD. Of the twelve models tested, the best-fitting model type was random forest. The temporal analysis of gait with machine learning algorithms may be useful as a future ASD diagnostic aid.https://www.mdpi.com/2079-7737/14/7/832ASDgaitmachine learningtimingvariability
spellingShingle Katharine Goldthorp
Benn Henderson
Pratheepan Yogarajah
Bryan Gardiner
Thomas Martin McGinnity
Brad Nicholas
Dawn C. Wimpory
Increased Temporal Variability of Gait in ASD: A Motion Capture and Machine Learning Analysis
Biology
ASD
gait
machine learning
timing
variability
title Increased Temporal Variability of Gait in ASD: A Motion Capture and Machine Learning Analysis
title_full Increased Temporal Variability of Gait in ASD: A Motion Capture and Machine Learning Analysis
title_fullStr Increased Temporal Variability of Gait in ASD: A Motion Capture and Machine Learning Analysis
title_full_unstemmed Increased Temporal Variability of Gait in ASD: A Motion Capture and Machine Learning Analysis
title_short Increased Temporal Variability of Gait in ASD: A Motion Capture and Machine Learning Analysis
title_sort increased temporal variability of gait in asd a motion capture and machine learning analysis
topic ASD
gait
machine learning
timing
variability
url https://www.mdpi.com/2079-7737/14/7/832
work_keys_str_mv AT katharinegoldthorp increasedtemporalvariabilityofgaitinasdamotioncaptureandmachinelearninganalysis
AT bennhenderson increasedtemporalvariabilityofgaitinasdamotioncaptureandmachinelearninganalysis
AT pratheepanyogarajah increasedtemporalvariabilityofgaitinasdamotioncaptureandmachinelearninganalysis
AT bryangardiner increasedtemporalvariabilityofgaitinasdamotioncaptureandmachinelearninganalysis
AT thomasmartinmcginnity increasedtemporalvariabilityofgaitinasdamotioncaptureandmachinelearninganalysis
AT bradnicholas increasedtemporalvariabilityofgaitinasdamotioncaptureandmachinelearninganalysis
AT dawncwimpory increasedtemporalvariabilityofgaitinasdamotioncaptureandmachinelearninganalysis