{"title":"Feasibility of differentiating gait in Parkinson's disease and spinocerebellar degeneration using a pose estimation algorithm in two-dimensional video","authors":"","doi":"10.1016/j.jns.2024.123158","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><p>Although pose estimation algorithms have been used to analyze videos of patients with Parkinson's disease (PD) to assess symptoms, their feasibility for differentiating PD from other neurological disorders that cause gait disturbances has not been evaluated yet. We aimed to determine whether it was possible to differentiate between PD and spinocerebellar degeneration (SCD) by analyzing video recordings of patient gait using a pose estimation algorithm.</p></div><div><h3>Methods</h3><p>We videotaped 82 patients with PD and 61 patients with SCD performing the timed up-and-go test. A pose estimation algorithm was used to extract the coordinates of 25 key points of the participants from these videos. A transformer-based deep neural network (DNN) model was trained to predict PD or SCD using the extracted coordinate data. We employed a leave-one-participant-out cross-validation method to evaluate the predictive performance of the trained model using accuracy, sensitivity, and specificity. As there were significant differences in age, weight, and body mass index between the PD and SCD groups, propensity score matching was used to perform the same experiment in a population that did not differ in these clinical characteristics.</p></div><div><h3>Results</h3><p>The accuracy, sensitivity, and specificity of the trained model were 0.86, 0.94, and 0.75 for all participants and 0.83, 0.88, and 0.78 for the participants extracted by propensity score matching.</p></div><div><h3>Conclusion</h3><p>The differentiation of PD and SCD using key point coordinates extracted from gait videos and the DNN model was feasible and could be used as a collaborative tool in clinical practice and telemedicine.</p></div>","PeriodicalId":17417,"journal":{"name":"Journal of the Neurological Sciences","volume":null,"pages":null},"PeriodicalIF":3.6000,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the Neurological Sciences","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0022510X24002934","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Background
Although pose estimation algorithms have been used to analyze videos of patients with Parkinson's disease (PD) to assess symptoms, their feasibility for differentiating PD from other neurological disorders that cause gait disturbances has not been evaluated yet. We aimed to determine whether it was possible to differentiate between PD and spinocerebellar degeneration (SCD) by analyzing video recordings of patient gait using a pose estimation algorithm.
Methods
We videotaped 82 patients with PD and 61 patients with SCD performing the timed up-and-go test. A pose estimation algorithm was used to extract the coordinates of 25 key points of the participants from these videos. A transformer-based deep neural network (DNN) model was trained to predict PD or SCD using the extracted coordinate data. We employed a leave-one-participant-out cross-validation method to evaluate the predictive performance of the trained model using accuracy, sensitivity, and specificity. As there were significant differences in age, weight, and body mass index between the PD and SCD groups, propensity score matching was used to perform the same experiment in a population that did not differ in these clinical characteristics.
Results
The accuracy, sensitivity, and specificity of the trained model were 0.86, 0.94, and 0.75 for all participants and 0.83, 0.88, and 0.78 for the participants extracted by propensity score matching.
Conclusion
The differentiation of PD and SCD using key point coordinates extracted from gait videos and the DNN model was feasible and could be used as a collaborative tool in clinical practice and telemedicine.
期刊介绍:
The Journal of the Neurological Sciences provides a medium for the prompt publication of original articles in neurology and neuroscience from around the world. JNS places special emphasis on articles that: 1) provide guidance to clinicians around the world (Best Practices, Global Neurology); 2) report cutting-edge science related to neurology (Basic and Translational Sciences); 3) educate readers about relevant and practical clinical outcomes in neurology (Outcomes Research); and 4) summarize or editorialize the current state of the literature (Reviews, Commentaries, and Editorials).
JNS accepts most types of manuscripts for consideration including original research papers, short communications, reviews, book reviews, letters to the Editor, opinions and editorials. Topics considered will be from neurology-related fields that are of interest to practicing physicians around the world. Examples include neuromuscular diseases, demyelination, atrophies, dementia, neoplasms, infections, epilepsies, disturbances of consciousness, stroke and cerebral circulation, growth and development, plasticity and intermediary metabolism.