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

Journal of NeuroEngineering and Rehabilitation

Yue Jin¹  Yudi Li¹  Hongping Zhi¹  Xiaoyun Su¹  Yichen Gao¹  Ronghua Hong²  Zhuoyu Zhang²  Qiang Guan²  Kangwen Peng²  Tianyu Zhang²  Ao Lin²  LingJing Jin³ 

[1] IFLYTEK Suzhou Research Institute, E4, Artificial Intelligence Industrial Park, Suzhou Industrial Park, Suzhou, China;Neurological Department of Tongji Hospital, Tongji University School of Medicine, Shanghai, China;Neurological Department of Tongji Hospital, Tongji University School of Medicine, Shanghai, China;Department of Neurorehabilitation, Yangzhi Rehabilitation Hospital (Shanghai Sunshine Rehabilitation Center), Tongji University School of Medicine, Shanghai, China;

关键词: Parkinson’s disease;    Postural abnormalities;    Kinect;    Machine learning;   

DOI  :  10.1186/s12984-021-00959-4

来源: Springer

【 摘 要 】

BackgroundAutomated 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.MethodsKinect 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.ResultsThe 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.ConclusionsWe 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.

【 授权许可】

CC BY