Abstract

Written informed consent was obtained from each participant, including consent to the use and publication of pictures and videos.149 PD patients treated at Shanghai Jiao Tong University School of Medicine Ruijin Hospital from September 2020 to May 2021 were included in our study. Three machine rating models, Rigidity–UE, Rigidity–LE, and Rigidity–neck, were built in this process. Since few samples had a rigidity score of 4 in our study, samples that scored 4 were merged with samples that scored 3. See Supplementary Method 7, http://links.lww.com/CM9/B514 for statistical analysis, Supplementary Method 8, http://links.lww.com/CM9/B514 for data availability, and Supplementary Figure 1 for a flow chart of the entire study protocol. In the model of Rigidity–UE, consistency between the ratings of the model and those of expert raters achieved moderate performance (ICC = 0.66, 95% confidence interval [CI]: 0.45–0.79, P <0.01).

Details

Title
Contactless evaluation of rigidity in Parkinson's disease by machine vision and machine learning
Author
Zhu, Xue 1 ; Shi Weikun 2 ; Ling, Yun 2 ; Luo Ningdi 1 ; Yin Qianyi 1 ; Zhang Yichi 1 ; Zhao Aonan 1 ; Ye Guanyu 1 ; Zhou, Haiyan 1 ; Pan, Jing 1 ; Zhou Liche 1 ; Cao Linghao 1 ; Huang, Pei 1 ; Zhang Pingchen 1 ; Chen, Zhonglue 2 ; Chen, Cheng 2 ; Lin Shinuan 2 ; Zhao, Jin 3 ; Kang, Ren 2 ; Tan Yuyan 1 ; Liu, Jun 1 

 Department of Neurology and Institute of Neurology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China 
 GYENNO SCIENCE CO., LTD., Shenzhen, Guangdong 518000, China; HUST-GYENNO CNS Intelligent Digital Medicine Technology Center, Wuhan, Hubei 430074, China 
 HUST-GYENNO CNS Intelligent Digital Medicine Technology Center, Wuhan, Hubei 430074, China; School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China 
Pages
2254-2256
Section
Correspondence
Publication year
2023
Publication date
Sep 2023
Publisher
Lippincott Williams & Wilkins Ovid Technologies
ISSN
03666999
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2866184489
Copyright
Copyright © 2023 The Chinese Medical Association, produced by Wolters Kluwer, Inc. under the CC-BY-NC-ND license. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0 (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.