{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:32:12Z","timestamp":1775842332218,"version":"3.50.1"},"reference-count":43,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T00:00:00Z","timestamp":1699228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Wearable sensors provide a tool for at-home monitoring of motor impairment progression in neurological conditions such as Parkinson\u2019s disease (PD). This study examined the ability of deep learning approaches to grade the motor impairment severity in a modified version of the Movement Disorders Society-sponsored revision of the Unified Parkinson\u2019s Disease Rating Scale (MDS-UPDRS) using low-cost wearable sensors. We hypothesized that expanding training datasets with motion data from healthy older adults (HOAs) and initializing classifiers with weights learned from unsupervised pre-training would lead to an improvement in performance when classifying lower vs. higher motor impairment relative to a baseline deep learning model (XceptionTime). This study evaluated the change in classification performance after using expanded training datasets with HOAs and transferring weights from unsupervised pre-training compared to a baseline deep learning model (XceptionTime) using both upper extremity (finger tapping, hand movements, and pronation\u2013supination movements of the hands) and lower extremity (toe tapping and leg agility) tasks consistent with the MDS-UPDRS. Overall, we found a 12.2% improvement in accuracy after expanding the training dataset and pre-training using max-vote inference on hand movement tasks. Moreover, we found that the classification performance improves for every task except toe tapping after the addition of HOA training data. These findings suggest that learning from HOA motion data can implicitly improve the representations of PD motion data for the purposes of motor impairment classification. Further, our results suggest that unsupervised pre-training can improve the performance of motor impairment classifiers without any additional annotated PD data, which may provide a viable solution for a widely deployable telemedicine solution.<\/jats:p>","DOI":"10.3390\/s23219004","type":"journal-article","created":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T13:24:53Z","timestamp":1699277093000},"page":"9004","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["A Deep Learning Approach for Automatic and Objective Grading of the Motor Impairment Severity in Parkinson\u2019s Disease for Use in Tele-Assessments"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9698-0565","authenticated-orcid":false,"given":"Mehar","family":"Singh","sequence":"first","affiliation":[{"name":"Computer Science and Engineering Division, University of Michigan, Ann-Arbor, MI 48109, USA"},{"name":"Department of Computer Science, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prithvi","family":"Prakash","sequence":"additional","affiliation":[{"name":"School of Information Sciences, University of Illinois Urbana-Champaign, Champaign, IL 61820, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9223-4546","authenticated-orcid":false,"given":"Rachneet","family":"Kaur","sequence":"additional","affiliation":[{"name":"Department of Industrial and Enterprise Systems Engineering, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Sowers","sequence":"additional","affiliation":[{"name":"Department of Industrial and Enterprise Systems Engineering, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3948-4853","authenticated-orcid":false,"given":"James Robert","family":"Bra\u0161i\u0107","sequence":"additional","affiliation":[{"name":"Section of High Resolution Brain Positron Emission Tomography Imaging, Division of Nuclear Medicine and Molecular Imaging, Russell H. Morgan Department of Radiology and Radiological Sciences, The Johns Hopkins University School of Medicine, Baltimore, MD 21205, USA"},{"name":"Department of Behavioral Health, New York City Health + Hospitals\/Bellevue, 462 First Avenue, New York, NY 10016, USA"},{"name":"Department of Psychiatry, New York University Grossman School of Medicine, New York University Langone Health, New York University, 550 First Avenue, New York, NY 10016, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3501-9508","authenticated-orcid":false,"given":"Manuel Enrique","family":"Hernandez","sequence":"additional","affiliation":[{"name":"Neuroscience Program, Beckman Institute, College of Liberal Arts & Sciences, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA"},{"name":"Department of Biomedical and Translational Sciences, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA"},{"name":"Department of Kinesiology and Community Health, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1016\/S1474-4422(06)70471-9","article-title":"Epidemiology of Parkinson\u2019s disease","volume":"5","author":"Breteler","year":"2006","journal-title":"Lancet Neurol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1591","DOI":"10.1002\/mds.26424","article-title":"MDS clinical diagnostic criteria for Parkinson\u2019s disease","volume":"30","author":"Postuma","year":"2015","journal-title":"Mov. Disord."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1016\/j.parkreldis.2011.02.012","article-title":"Moving towards patient-centered healthcare for patients with Parkinson\u2019s disease","volume":"17","author":"Faber","year":"2011","journal-title":"Park. Relat. Disord."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"S146","DOI":"10.1093\/geront\/gnv004","article-title":"Implementation of an integrative holistic healthcare model for people living with Parkinson\u2019s disease","volume":"55","author":"Prettyman","year":"2015","journal-title":"Gerontologist"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1082","DOI":"10.1136\/bmj.315.7115.1082","article-title":"Population aging and health","volume":"315","author":"Butler","year":"1997","journal-title":"BMJ"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1007\/s11910-018-0834-6","article-title":"The promise of telemedicine for movement disorders: An interdisciplinary approach","volume":"18","author":"Browne","year":"2018","journal-title":"Curr. Neurol. Neurosci. Rep."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2129","DOI":"10.1002\/mds.22340","article-title":"Movement Disorder Society-sponsored revision of the Unified Parkinson\u2019s Disease Rating Scale (MDS-UPDRS): Scale presentation and clinimetric testing results","volume":"23","author":"Goetz","year":"2008","journal-title":"Mov. Disord. Off. J. Mov. Disord. Soc."},{"key":"ref_8","first-page":"S11","article-title":"Global perspective on telemedicine for Parkinson\u2019s disease","volume":"11","author":"Shalash","year":"2021","journal-title":"J. Park. Dis."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1002\/mds.25903","article-title":"The past, present, and future of telemedicine for Parkinson\u2019s disease","volume":"29","author":"Achey","year":"2014","journal-title":"Mov. Disord."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1097\/WCO.0000000000000953","article-title":"The state of telemedicine for persons with Parkinson\u2019s disease","volume":"34","author":"Bloem","year":"2021","journal-title":"Curr. Opin. Neurol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.1109\/JBHI.2018.2866873","article-title":"Multimodal Assessment of Parkinson\u2019s Disease: A Deep Learning Approach","volume":"23","author":"Eskofier","year":"2019","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1016\/j.bspc.2016.08.003","article-title":"Machine learning-based classification of simple drawing movements in Parkinson\u2019s disease","volume":"31","author":"Kotsavasiloglou","year":"2017","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1109\/JBHI.2022.3208077","article-title":"A Vision-Based Framework for Predicting Multiple Sclerosis and Parkinson\u2019s Disease Gait Dysfunctions-A Deep Learning Approach","volume":"27","author":"Kaur","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hu, Y., Bishnoi, A., Kaur, R., Sowers, R., and Hernandez, M.E. (2020, January 20\u201324). Exploration of machine learning to identify community dwelling older adults with balance dysfunction using short duration accelerometer data. Proceedings of the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Montreal, QC, Canada.","DOI":"10.1109\/EMBC44109.2020.9175871"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2666","DOI":"10.1109\/TBME.2020.3048142","article-title":"Predicting multiple sclerosis from gait dynamics using an instrumented treadmill: A machine learning approach","volume":"68","author":"Kaur","year":"2020","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1148\/radiol.2020192224","article-title":"Preparing Medical Imaging Data for Machine Learning","volume":"295","author":"Willemink","year":"2020","journal-title":"Radiology"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A comprehensive survey on transfer learning","volume":"109","author":"Zhuang","year":"2020","journal-title":"Proc. IEEE"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/j.mex.2018.12.017","article-title":"A low-cost quantitative continuous measurement of movements in the extremities of people with Parkinson\u2019s disease","volume":"6","author":"McKay","year":"2019","journal-title":"MethodsX"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"105876","DOI":"10.1016\/j.dib.2020.105876","article-title":"Dataset of quantitative structured office measurements of movements in the extremities","volume":"31","author":"Harrigan","year":"2020","journal-title":"Data Brief"},{"key":"ref_20","unstructured":"Oguiza, I. (2022). Tsai\u2014A State-of-the-Art Deep Learning Library for Time Series and Sequential Data, Github."},{"key":"ref_21","unstructured":"Howard, J., Gugger, S., Mueller, Z., Warner, B., Bird, K., Moe, M., Abraham, T., Capelle, T., Malleswaram, M., and Husian, H. (2023, January 06). Fastai. Available online: https:\/\/github.com\/fastai\/fastai."},{"key":"ref_22","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019). Advances in Neural Information Processing Systems 32, Curran Associates, Inc."},{"key":"ref_23","unstructured":"Rahimian, E., Zabihi, S., Atashzar, S.F., Asif, A., and Mohammadi, A. (2019). XceptionTime: A Novel Deep Architecture based on Depthwise Separable Convolutions for Hand Gesture Classification. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Prakash, P., Kaur, R., Levy, J., Sowers, R., Bra\u0161i\u0107, J.R., and Hernandez, M.E. (2023, January 24\u201327). A Deep Learning Approach for Grading of Motor Impairment Severity in Parkinson\u2019s Disease. Proceedings of the 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Sydney, Australia. in press.","DOI":"10.1109\/EMBC40787.2023.10341122"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zerveas, G., Jayaraman, S., Patel, D., Bhamidipaty, A., and Eickhoff, C. (2020). A Transformer-based Framework for Multivariate Time Series Representation Learning. arXiv.","DOI":"10.1145\/3447548.3467401"},{"key":"ref_26","unstructured":"Kornblith, S., Norouzi, M., Lee, H., and Hinton, G.E. (2019). Similarity of Neural Network Representations Revisited. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"30","DOI":"10.4103\/jpi.jpi_78_20","article-title":"Improving Generalization of Deep Learning Models for Diagnostic Pathology by Increasing Variability in Training Data: Experiments on Osteosarcoma Subtypes","volume":"12","author":"Tang","year":"2021","journal-title":"J. Pathol. Inform."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Rozsa, A., G\u00fcnther, M., and Boult, T.E. (2016, January 18\u201320). Are Accuracy and Robustness Correlated. Proceedings of the 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA), Anaheim, CA, USA.","DOI":"10.1109\/ICMLA.2016.0045"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Berlingerio, M., Bonchi, F., G\u00e4rtner, T., Hurley, N., and Ifrim, G. (2019, January 10\u201314). Using Supervised Pretraining to Improve Generalization of Neural Networks on Binary Classification Problems. Proceedings of the Machine Learning and Knowledge Discovery in Databases, Dublin, Ireland.","DOI":"10.1007\/978-3-030-10928-8"},{"key":"ref_30","unstructured":"Chen, S., Ma, K., and Zheng, Y. (2019). Med3D: Transfer Learning for 3D Medical Image Analysis. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Arasteh, E., Mahdizadeh, A., Mirian, M.S., Lee, S., and McKeown, M.J. (2022). Deep Transfer Learning for Parkinson\u2019s Disease Monitoring by Image-Based Representation of Resting-State EEG Using Directional Connectivity. Algorithms, 15.","DOI":"10.3390\/a15010005"},{"key":"ref_32","unstructured":"Hendrycks, D., Lee, K., and Mazeika, M. (2019). Using Pre-Training Can Improve Model Robustness and Uncertainty. arXiv."},{"key":"ref_33","unstructured":"Hendrycks, D., Mazeika, M., Kadavath, S., and Song, D. (2019). Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Djolonga, J., Yung, J., Tschannen, M., Romijnders, R., Beyer, L., Kolesnikov, A., Puigcerver, J., Minderer, M., D\u2019Amour, A., and Moldovan, D. (2021). On Robustness and Transferability of Convolutional Neural Networks. arXiv.","DOI":"10.1109\/CVPR46437.2021.01619"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Rezaee, K., Savarkar, S., Yu, X., and Zhang, J. (2022). A hybrid deep transfer learning-based approach for Parkinson\u2019s disease classification in surface electromyography signals. Biomed. Signal Process. Control, 71.","DOI":"10.1016\/j.bspc.2021.103161"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_37","unstructured":"El-Nouby, A., Izacard, G., Touvron, H., Laptev, I., Jegou, H., and Grave, E. (2021). Are Large-scale Datasets Necessary for Self-Supervised Pre-training?. arXiv."},{"key":"ref_38","unstructured":"Neyshabur, B., Sedghi, H., and Zhang, C. (2020). What is being transferred in transfer learning?. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Weyhenmeyer, J., Hernandez, M.E., Lainscsek, C., Poizner, H., and Sejnowski, T.J. (2020, January 16\u201319). Multimodal classification of Parkinson\u2019s disease using delay differential analysis. Proceedings of the 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Seoul, Republic of Korea.","DOI":"10.1109\/BIBM49941.2020.9313394"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"013119","DOI":"10.1063\/1.3683444","article-title":"Finger tapping movements of Parkinson\u2019s disease patients automatically rated using nonlinear delay differential equations","volume":"22","author":"Lainscsek","year":"2012","journal-title":"Chaos Interdiscip. J. Nonlinear Sci."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.jse.2007.05.017","article-title":"Forearm rotation in healthy adults of all ages and both sexes","volume":"17","author":"Rickert","year":"2008","journal-title":"J. Shoulder Elb. Surg."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1859","DOI":"10.1002\/mds.23740","article-title":"The modified bradykinesia rating scale for Parkinson\u2019s disease: Reliability and comparison with kinematic measures","volume":"26","author":"Heldman","year":"2011","journal-title":"Mov. Disord."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"26895","DOI":"10.1109\/ACCESS.2018.2835463","article-title":"Quantification of parkinsonian bradykinesia based on axis-angle representation and SVM multiclass classification method","volume":"6","author":"Lin","year":"2018","journal-title":"IEEE Access"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/21\/9004\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:18:19Z","timestamp":1760131099000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/21\/9004"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,6]]},"references-count":43,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["s23219004"],"URL":"https:\/\/doi.org\/10.3390\/s23219004","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,6]]}}}