A Novel Video-Based Methodology for Automated Classification of Dystonia and Choreoathetosis in Dyskinetic Cerebral Palsy During a Lower Extremity Task.

Neurorehabilitation and neural repair Pub Date : 2024-07-01 Epub Date: 2024-06-06 DOI:10.1177/15459683241257522
Helga Haberfehlner, Zachary Roth, Inti Vanmechelen, Annemieke I Buizer, Roland Jeroen Vermeulen, Anne Koy, Jean-Marie Aerts, Hans Hallez, Elegast Monbaliu
{"title":"A Novel Video-Based Methodology for Automated Classification of Dystonia and Choreoathetosis in Dyskinetic Cerebral Palsy During a Lower Extremity Task.","authors":"Helga Haberfehlner, Zachary Roth, Inti Vanmechelen, Annemieke I Buizer, Roland Jeroen Vermeulen, Anne Koy, Jean-Marie Aerts, Hans Hallez, Elegast Monbaliu","doi":"10.1177/15459683241257522","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Movement disorders in children and adolescents with dyskinetic cerebral palsy (CP) are commonly assessed from video recordings, however scoring is time-consuming and expert knowledge is required for an appropriate assessment.</p><p><strong>Objective: </strong>To explore a machine learning approach for automated classification of amplitude and duration of distal leg dystonia and choreoathetosis within short video sequences.</p><p><strong>Methods: </strong>Available videos of a heel-toe tapping task were preprocessed to optimize key point extraction using markerless motion analysis. Postprocessed key point data were passed to a time series classification ensemble algorithm to classify dystonia and choreoathetosis duration and amplitude classes (scores 0, 1, 2, 3, and 4), respectively. As ground truth clinical scoring of dystonia and choreoathetosis by the Dyskinesia Impairment Scale was used. Multiclass performance metrics as well as metrics for summarized scores: absence (score 0) and presence (score 1-4) were determined.</p><p><strong>Results: </strong>Thirty-three participants were included: 29 with dyskinetic CP and 4 typically developing, age 14 years:6 months ± 5 years:15 months. The multiclass accuracy results for dystonia were 77% for duration and 68% for amplitude; for choreoathetosis 30% for duration and 38% for amplitude. The metrics for score 0 versus score 1 to 4 revealed an accuracy of 81% for dystonia duration, 77% for dystonia amplitude, 53% for choreoathetosis duration and amplitude.</p><p><strong>Conclusions: </strong>This methodology study yielded encouraging results in distinguishing between presence and absence of dystonia, but not for choreoathetosis. A larger dataset is required for models to accurately represent distinct classes/scores. This study presents a novel methodology of automated assessment of movement disorders solely from video data.</p>","PeriodicalId":94158,"journal":{"name":"Neurorehabilitation and neural repair","volume":" ","pages":"479-492"},"PeriodicalIF":0.0000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neurorehabilitation and neural repair","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1177/15459683241257522","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/6/6 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Movement disorders in children and adolescents with dyskinetic cerebral palsy (CP) are commonly assessed from video recordings, however scoring is time-consuming and expert knowledge is required for an appropriate assessment.

Objective: To explore a machine learning approach for automated classification of amplitude and duration of distal leg dystonia and choreoathetosis within short video sequences.

Methods: Available videos of a heel-toe tapping task were preprocessed to optimize key point extraction using markerless motion analysis. Postprocessed key point data were passed to a time series classification ensemble algorithm to classify dystonia and choreoathetosis duration and amplitude classes (scores 0, 1, 2, 3, and 4), respectively. As ground truth clinical scoring of dystonia and choreoathetosis by the Dyskinesia Impairment Scale was used. Multiclass performance metrics as well as metrics for summarized scores: absence (score 0) and presence (score 1-4) were determined.

Results: Thirty-three participants were included: 29 with dyskinetic CP and 4 typically developing, age 14 years:6 months ± 5 years:15 months. The multiclass accuracy results for dystonia were 77% for duration and 68% for amplitude; for choreoathetosis 30% for duration and 38% for amplitude. The metrics for score 0 versus score 1 to 4 revealed an accuracy of 81% for dystonia duration, 77% for dystonia amplitude, 53% for choreoathetosis duration and amplitude.

Conclusions: This methodology study yielded encouraging results in distinguishing between presence and absence of dystonia, but not for choreoathetosis. A larger dataset is required for models to accurately represent distinct classes/scores. This study presents a novel methodology of automated assessment of movement disorders solely from video data.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
一种基于视频的新方法,用于在下肢任务中对运动障碍型脑瘫患者的肌张力障碍和家务障碍进行自动分类。
背景:患有运动障碍型脑性瘫痪(CP)的儿童和青少年的运动障碍通常通过视频记录进行评估,但是评分非常耗时,而且需要专家知识才能进行适当的评估:目的:探索一种机器学习方法,用于在短视频序列中对腿远端肌张力障碍和舞蹈症的振幅和持续时间进行自动分类:方法:使用无标记运动分析法对现有的足跟轻叩任务视频进行预处理,以优化关键点提取。将经过后处理的关键点数据传递给时间序列分类集合算法,以划分肌张力障碍和舞蹈症的持续时间和振幅等级(分别为 0、1、2、3 和 4 分)。根据肌张力障碍损害量表对肌张力障碍和舞蹈症进行临床评分,作为基本事实。确定了多分类性能指标以及汇总分数的指标:无(0 分)和有(1-4 分):结果:共纳入 33 名参与者:年龄为 14 岁:6 个月± 5 岁:15 个月。肌张力障碍的多分类准确率为:持续时间 77%,振幅 68%;舞蹈症的持续时间 30%,振幅 38%。得分 0 与得分 1 至 4 的指标显示,肌张力障碍持续时间的准确率为 81%,肌张力障碍振幅的准确率为 77%,舞蹈症持续时间和振幅的准确率为 53%:这项方法学研究在区分肌张力障碍的存在与否方面取得了令人鼓舞的结果,但在舞蹈症方面则没有。需要更大的数据集,模型才能准确代表不同的类别/评分。本研究提出了一种仅通过视频数据自动评估运动障碍的新方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Reinforcement Learning is Impaired in the Sub-acute Post-stroke Period. Post-Stroke Recovery in Relation to Parvalbumin-Positive Interneurons and Perineuronal Nets. Mapping Trajectories of Gait Recovery in Clinical Stroke Rehabilitation. Exploring Non-invasive Brain Stimulation Effects on Physical Outcomes in People With Parkinson's Disease: An Umbrella Evidence Mapping Review With Meta-analyses. Acute and Longitudinal Effects of Concussion on Reactive Balance in Collegiate Athletes.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1