Automated and accurate assessment for postural abnormalities in patients with Parkinson’s disease based on Kinect and machine learning

Abstract Background Automated and accurate assessment for postural abnormalities is necessary to monitor the clinical progress of Parkinson’s disease (PD). The combination of depth camera and machine learning makes this purpose possible. Methods Kinect was used to collect the postural images from 70...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhuoyu Zhang, Ronghua Hong, Ao Lin, Xiaoyun Su, Yue Jin, Yichen Gao, Kangwen Peng, Yudi Li, Tianyu Zhang, Hongping Zhi, Qiang Guan, LingJing Jin
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Parkinson’s disease Postural abnormalities Kinect Machine learning Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/bbfb35c0b43e4991ab0d06267f4a261a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bbfb35c0b43e4991ab0d06267f4a261a
record_format	dspace
spelling	oai:doaj.org-article:bbfb35c0b43e4991ab0d06267f4a261a2021-12-05T12:24:44ZAutomated and accurate assessment for postural abnormalities in patients with Parkinson’s disease based on Kinect and machine learning10.1186/s12984-021-00959-41743-0003https://doaj.org/article/bbfb35c0b43e4991ab0d06267f4a261a2021-12-01T00:00:00Zhttps://doi.org/10.1186/s12984-021-00959-4https://doaj.org/toc/1743-0003Abstract Background Automated and accurate assessment for postural abnormalities is necessary to monitor the clinical progress of Parkinson’s disease (PD). The combination of depth camera and machine learning makes this purpose possible. Methods Kinect was used to collect the postural images from 70 PD patients. The collected images were processed to extract three-dimensional body joints, which were then converted to two-dimensional body joints to obtain eight quantified coronal and sagittal features (F1-F8) of the trunk. The decision tree classifier was carried out over a data set established by the collected features and the corresponding doctors’ MDS-UPDRS-III 3.13 (the 13th item of the third part of Movement Disorder Society-Sponsored Revision of the Unified Parkinson’s Disease Rating Scale) scores. An objective function was implanted to further improve the human–machine consistency. Results The automated grading of postural abnormalities for PD patients was realized with only six selected features. The intraclass correlation coefficient (ICC) between the machine’s and doctors’ score was 0.940 (95%CI, 0.905–0.962), meaning the machine was highly consistent with the doctors’ judgement. Besides, the decision tree classifier performed outstandingly, reaching 90.0% of accuracy, 95.7% of specificity and 89.1% of sensitivity in rating postural severity. Conclusions We developed an intelligent evaluation system to provide accurate and automated assessment of trunk postural abnormalities in PD patients. This study demonstrates the practicability of our proposed method in the clinical scenario to help making the medical decision about PD.Zhuoyu ZhangRonghua HongAo LinXiaoyun SuYue JinYichen GaoKangwen PengYudi LiTianyu ZhangHongping ZhiQiang GuanLingJing JinBMCarticleParkinson’s diseasePostural abnormalitiesKinectMachine learningNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENJournal of NeuroEngineering and Rehabilitation, Vol 18, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Parkinson’s disease Postural abnormalities Kinect Machine learning Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	Parkinson’s disease Postural abnormalities Kinect Machine learning Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Zhuoyu Zhang Ronghua Hong Ao Lin Xiaoyun Su Yue Jin Yichen Gao Kangwen Peng Yudi Li Tianyu Zhang Hongping Zhi Qiang Guan LingJing Jin Automated and accurate assessment for postural abnormalities in patients with Parkinson’s disease based on Kinect and machine learning
description	Abstract Background Automated and accurate assessment for postural abnormalities is necessary to monitor the clinical progress of Parkinson’s disease (PD). The combination of depth camera and machine learning makes this purpose possible. Methods Kinect was used to collect the postural images from 70 PD patients. The collected images were processed to extract three-dimensional body joints, which were then converted to two-dimensional body joints to obtain eight quantified coronal and sagittal features (F1-F8) of the trunk. The decision tree classifier was carried out over a data set established by the collected features and the corresponding doctors’ MDS-UPDRS-III 3.13 (the 13th item of the third part of Movement Disorder Society-Sponsored Revision of the Unified Parkinson’s Disease Rating Scale) scores. An objective function was implanted to further improve the human–machine consistency. Results The automated grading of postural abnormalities for PD patients was realized with only six selected features. The intraclass correlation coefficient (ICC) between the machine’s and doctors’ score was 0.940 (95%CI, 0.905–0.962), meaning the machine was highly consistent with the doctors’ judgement. Besides, the decision tree classifier performed outstandingly, reaching 90.0% of accuracy, 95.7% of specificity and 89.1% of sensitivity in rating postural severity. Conclusions We developed an intelligent evaluation system to provide accurate and automated assessment of trunk postural abnormalities in PD patients. This study demonstrates the practicability of our proposed method in the clinical scenario to help making the medical decision about PD.
format	article
author	Zhuoyu Zhang Ronghua Hong Ao Lin Xiaoyun Su Yue Jin Yichen Gao Kangwen Peng Yudi Li Tianyu Zhang Hongping Zhi Qiang Guan LingJing Jin
author_facet	Zhuoyu Zhang Ronghua Hong Ao Lin Xiaoyun Su Yue Jin Yichen Gao Kangwen Peng Yudi Li Tianyu Zhang Hongping Zhi Qiang Guan LingJing Jin
author_sort	Zhuoyu Zhang
title	Automated and accurate assessment for postural abnormalities in patients with Parkinson’s disease based on Kinect and machine learning
title_short	Automated and accurate assessment for postural abnormalities in patients with Parkinson’s disease based on Kinect and machine learning
title_full	Automated and accurate assessment for postural abnormalities in patients with Parkinson’s disease based on Kinect and machine learning
title_fullStr	Automated and accurate assessment for postural abnormalities in patients with Parkinson’s disease based on Kinect and machine learning
title_full_unstemmed	Automated and accurate assessment for postural abnormalities in patients with Parkinson’s disease based on Kinect and machine learning
title_sort	automated and accurate assessment for postural abnormalities in patients with parkinson’s disease based on kinect and machine learning
publisher	BMC
publishDate	2021
url	https://doaj.org/article/bbfb35c0b43e4991ab0d06267f4a261a
work_keys_str_mv	AT zhuoyuzhang automatedandaccurateassessmentforposturalabnormalitiesinpatientswithparkinsonsdiseasebasedonkinectandmachinelearning AT ronghuahong automatedandaccurateassessmentforposturalabnormalitiesinpatientswithparkinsonsdiseasebasedonkinectandmachinelearning AT aolin automatedandaccurateassessmentforposturalabnormalitiesinpatientswithparkinsonsdiseasebasedonkinectandmachinelearning AT xiaoyunsu automatedandaccurateassessmentforposturalabnormalitiesinpatientswithparkinsonsdiseasebasedonkinectandmachinelearning AT yuejin automatedandaccurateassessmentforposturalabnormalitiesinpatientswithparkinsonsdiseasebasedonkinectandmachinelearning AT yichengao automatedandaccurateassessmentforposturalabnormalitiesinpatientswithparkinsonsdiseasebasedonkinectandmachinelearning AT kangwenpeng automatedandaccurateassessmentforposturalabnormalitiesinpatientswithparkinsonsdiseasebasedonkinectandmachinelearning AT yudili automatedandaccurateassessmentforposturalabnormalitiesinpatientswithparkinsonsdiseasebasedonkinectandmachinelearning AT tianyuzhang automatedandaccurateassessmentforposturalabnormalitiesinpatientswithparkinsonsdiseasebasedonkinectandmachinelearning AT hongpingzhi automatedandaccurateassessmentforposturalabnormalitiesinpatientswithparkinsonsdiseasebasedonkinectandmachinelearning AT qiangguan automatedandaccurateassessmentforposturalabnormalitiesinpatientswithparkinsonsdiseasebasedonkinectandmachinelearning AT lingjingjin automatedandaccurateassessmentforposturalabnormalitiesinpatientswithparkinsonsdiseasebasedonkinectandmachinelearning
_version_	1718371981827506176

Automated and accurate assessment for postural abnormalities in patients with Parkinson’s disease based on Kinect and machine learning

Ejemplares similares