{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:51:21Z","timestamp":1775746281802,"version":"3.50.1"},"reference-count":39,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,4,30]],"date-time":"2021-04-30T00:00:00Z","timestamp":1619740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Innovative Medical Research Fund (Innovative Medizinische Forschung), University of M\u00fcnster","award":["I-VA111809"],"award-info":[{"award-number":["I-VA111809"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Smartwatches provide technology-based assessments in Parkinson\u2019s disease (PD). It is necessary to evaluate their reliability and accuracy in order to include those devices in an assessment. We present unique results for sensor validation and disease classification via machine learning (ML). A comparison setup was designed with two different series of Apple smartwatches, one Nanometrics seismometer and a high-precision shaker to measure tremor-like amplitudes and frequencies. Clinical smartwatch measurements were acquired from a prospective study including 450 participants with PD, differential diagnoses (DD) and healthy participants. All participants wore two smartwatches throughout a 15-min examination. Symptoms and medical history were captured on the paired smartphone. The amplitude error of both smartwatches reaches up to 0.005 g, and for the measured frequencies, up to 0.01 Hz. A broad range of different ML classifiers were cross-validated. The most advanced task of distinguishing PD vs. DD was evaluated with 74.1% balanced accuracy, 86.5% precision and 90.5% recall by Multilayer Perceptrons. Deep-learning architectures significantly underperformed in all classification tasks. Smartwatches are capable of capturing subtle tremor signs with low noise. Amplitude and frequency differences between smartwatches and the seismometer were under the level of clinical significance. This study provided the largest PD sample size of two-hand smartwatch measurements and our preliminary ML-evaluation shows that such a system provides powerful means for diagnosis classification and new digital biomarkers, but it remains challenging for distinguishing similar disorders.<\/jats:p>","DOI":"10.3390\/s21093139","type":"journal-article","created":{"date-parts":[[2021,4,30]],"date-time":"2021-04-30T10:53:29Z","timestamp":1619780009000},"page":"3139","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Sensor Validation and Diagnostic Potential of Smartwatches in Movement Disorders"],"prefix":"10.3390","volume":"21","author":[{"given":"Julian","family":"Varghese","sequence":"first","affiliation":[{"name":"Institute of Medical Informatics, University of M\u00fcnster, 48149 M\u00fcnster, Germany"}]},{"given":"Catharina Marie van","family":"Alen","sequence":"additional","affiliation":[{"name":"Institute of Geophysics, University of M\u00fcnster, 48149 M\u00fcnster, Germany"}]},{"given":"Michael","family":"Fujarski","sequence":"additional","affiliation":[{"name":"Institute of Medical Informatics, University of M\u00fcnster, 48149 M\u00fcnster, Germany"}]},{"given":"Georg Stefan","family":"Schlake","sequence":"additional","affiliation":[{"name":"Institute of Medical Informatics, University of M\u00fcnster, 48149 M\u00fcnster, Germany"}]},{"given":"Julitta","family":"Sucker","sequence":"additional","affiliation":[{"name":"Institute of Medical Informatics, University of M\u00fcnster, 48149 M\u00fcnster, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8979-5900","authenticated-orcid":false,"given":"Tobias","family":"Warnecke","sequence":"additional","affiliation":[{"name":"Department of Neurology, University Hospital M\u00fcnster, 48149 M\u00fcnster, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7845-5385","authenticated-orcid":false,"given":"Christine","family":"Thomas","sequence":"additional","affiliation":[{"name":"Institute of Geophysics, University of M\u00fcnster, 48149 M\u00fcnster, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2021,4,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Mahmood, M., Jalal, A., and Kim, K. (2019). WHITE STAG model: Wise human interaction tracking and estimation (WHITE) using spatio-temporal and angular-geometric (STAG) descriptors. Multimed. Tools Appl., 1\u201332.","DOI":"10.1007\/s11042-019-08527-8"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"579","DOI":"10.3390\/e22050579","article-title":"Wearable inertial sensors for daily activity analysis based on adam optimization and the maximum entropy Markov model","volume":"22","author":"Jalal","year":"2020","journal-title":"Entropy"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Yaacob, N.I., and Tahir, N.M. (2012, January 24\u201327). Feature selection for gait recognition. Proceedings of the 2012 IEEE Symposium on Humanities, Science and Engineering Research, Kuala Lumpur, Malaysia.","DOI":"10.1109\/SHUSER.2012.6268871"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1272","DOI":"10.1002\/mds.26642","article-title":"Technology in Parkinson\u2019s disease","volume":"31","author":"Espay","year":"2016","journal-title":"Mov. Disord. Off. J. Mov. Disord. Soc."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"928","DOI":"10.1016\/S1474-4422(18)30355-7","article-title":"The burden of Parkinson\u2019s disease","volume":"17","author":"Rocca","year":"2018","journal-title":"Lancet Neurol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1038\/s41582-019-0215-z","article-title":"Prodromal Parkinson disease","volume":"15","author":"Postuma","year":"2019","journal-title":"Nat. Rev. Neurol."},{"key":"ref_7","unstructured":"Varghese, J., Niew\u00f6hner, S., Fujarski, M., Soto-Rey, I., Schwake, A.-L., and Warnecke, T. (2019). Smartwatch-based Examination of Movement Disorders: Early Implementation and Measurement Accuracy. EGMS."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1016\/j.parkreldis.2014.02.022","article-title":"Clinician versus machine","volume":"20","author":"Heldman","year":"2014","journal-title":"Parkinsonism Relat. Disord."},{"key":"ref_9","unstructured":"Parkinson\u2019s KinetiGraph (PKG) (2021, April 21). Dementech Neurosciences. Available online: https:\/\/dementech.com\/parkinsons-kinetigraph-pkg\/."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"de Lima, A.L.S., Hahn, T., Evers, L.J.W., Vries, N.M., Cohen, E., and Afek, M. (2017). Feasibility of large-scale deployment of multiple wearable sensors in Parkinson\u2019s disease. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0189161"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1007\/s00415-015-7671-1","article-title":"Speech disorders reflect differing pathophysiology in Parkinson\u2019s disease, progressive supranuclear palsy and multiple system atrophy","volume":"262","author":"Rusz","year":"2015","journal-title":"J. Neurol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"37718","DOI":"10.1109\/ACCESS.2019.2906350","article-title":"Feature Selection Based on L1-Norm Support Vector Machine and Effective Recognition System for Parkinson\u2019s disease Using Voice Recordings","volume":"7","author":"Haq","year":"2019","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1604","DOI":"10.1007\/s00115-011-3329-0","article-title":"Mobile biometrische Ganganalyse","volume":"82","author":"Klucken","year":"2011","journal-title":"Der. Nervenarzt."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1007\/s00115-019-0753-z","article-title":"\u201cWearables\u201d in der Behandlung neurologischer Erkrankungen\u2014wo stehen wir heute?","volume":"90","author":"Klucken","year":"2019","journal-title":"Der. Nervenarzt."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12883-015-0447-5","article-title":"Association between vestibulo-ocular reflex suppression, balance, gait, and fall risk in ageing and neurodegenerative disease","volume":"15","author":"Srulijes","year":"2015","journal-title":"BMC Neurol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.jneumeth.2017.02.006","article-title":"Analysis of facial expressions in parkinson\u2019s disease through video-based automatic methods","volume":"281","author":"Bandini","year":"2017","journal-title":"J. Neurosci. Methods"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"101984","DOI":"10.1016\/j.artmed.2020.101984","article-title":"Cartesian genetic programming for diagnosis of Parkinson disease through handwriting analysis: Performance vs. interpretability issues","volume":"111","author":"Parziale","year":"2021","journal-title":"Artif. Intell. Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"48","DOI":"10.3389\/fneur.2019.00048","article-title":"A Smart Device System to Identify New Phenotypical Characteristics in Movement Disorders","volume":"10","author":"Varghese","year":"2019","journal-title":"Front. Neurol."},{"key":"ref_19","unstructured":"(2021, January 22). Non-Motor Symptoms Questionnaire (NMSQ) by the International Parkinson and Movement Disorder Society. Available online: https:\/\/www.movementdisorders.org\/MDS\/MDS-Rating-Scales\/Non-Motor-Symptoms-Questionnaire.htm."},{"key":"ref_20","first-page":"889","article-title":"The Smart Device System for Movement Disorders: Preliminary Evaluation of Diagnostic Accuracy in a Prospective Study","volume":"270","author":"Varghese","year":"2020","journal-title":"Stud. Health Technol. Inform."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"317","DOI":"10.3389\/fnins.2018.00317","article-title":"A Novel Posture for Better Differentiation Between Parkinson\u2019s Tremor and Essential Tremor","volume":"12","author":"Zhang","year":"2018","journal-title":"Front. Neurosci."},{"key":"ref_22","unstructured":"(2021, February 17). Routine Data Processing in Earthquake Seismology. SpringerLink. Available online: https:\/\/link.springer.com\/book\/10.1007\/978-90-481-8697-6."},{"key":"ref_23","unstructured":"Havskov, J., Ottem\u00f6ller, L., Trnkoczy, A., and Bormann, P. (2012). Seismic Networks. New Manual of Seismological Observatory Practice 2 (NMSOP-2), Deutsches GeoForschungsZentrum GFZ."},{"key":"ref_24","unstructured":"(2021, February 17). Nanometrics Trillium Compact Manual. Available online: https:\/\/www.nanometrics.ca\/sites\/default\/files\/2018-04\/trillium_compact_data_sheet.pdf."},{"key":"ref_25","unstructured":"(2021, April 29). Taurus Portable Seismograph User Guide. Available online: http:\/\/www.ipgp.fr\/~arnaudl\/NanoCD\/software\/Taurus_2.06.03\/CD\/doc\/Taurus_UserGuide_15148R5.pdf."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Havskov, J., and Alguacil, G. (2004). Instrumentation in Earthquake Seismology, Springer. Available online: https:\/\/www.springer.com\/gp\/book\/9789401751131.","DOI":"10.1007\/978-1-4020-2969-1"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1002\/mds.27121","article-title":"Consensus Statement on the classification of tremors. from the task force on tremor of the International Parkinson and Movement Disorder Society","volume":"33","author":"Bhatia","year":"2018","journal-title":"Mov. Disord."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1017\/S0016756811000094","article-title":"Routine Data Processing in Earthquake Seismology","volume":"148","author":"Helffrich","year":"2011","journal-title":"Geol. Mag."},{"key":"ref_29","unstructured":"Dorogush, A.V., Ershov, V., and Gulin, A. (2018). CatBoost: Gradient Boosting with Categorical Features Support. arXiv, Available online: http:\/\/arxiv.org\/abs\/1810.11363."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Deisenroth, M.P., Faisal, A.A., and Ong, C.S. (2020). Mathematics for Machine Learning, Cambridge University Press.","DOI":"10.1017\/9781108679930"},{"key":"ref_31","unstructured":"Hackeling, G. (2017). Mastering Machine Learning with Scikit-Learn, Packt Publishing Ltd."},{"key":"ref_32","unstructured":"(2021, January 28). Keras: The Python Deep Learning API. Available online: https:\/\/keras.io\/."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yan, W., and Oates, T. (2017, January 14\u201319). Time series classification from scratch with deep neural networks: A strong baseline. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA.","DOI":"10.1109\/IJCNN.2017.7966039"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Brodersen, K.H., Ong, C.S., Stephan, K.E., and Buhmann, J.M. (2010, January 23\u201326). The balanced accuracy and its posterior distribution. Proceedings of the 2010 20th International Conference on Pattern Recognition, Istanbul, Turkey.","DOI":"10.1109\/ICPR.2010.764"},{"key":"ref_35","unstructured":"(2021, March 08). Sklearn Metrics Balanced Accuracy Score\u2014Scikit-Learn 0.24.1 Documentation. Available online: https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.metrics.balanced_accuracy_score.html."},{"key":"ref_36","unstructured":"Neto, E.C., Pratap, A., Perumal, T.M., Tummalacherla, M., Bot, B.M., and Mangravite, L. (2017). Detecting confounding due to subject identification in clinical machine learning diagnostic applications: A permutation test approach. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1648","DOI":"10.1109\/JBHI.2017.2762008","article-title":"Efficacy of guided spiral drawing in the classification of Parkinson\u2019s disease","volume":"22","author":"Zham","year":"2017","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Bhidayasiri, R., and Tarsy, D. (2012). Parkinson\u2019s disease: Hoehn and Yahr Scale. Movement Disorders: A Video Atlas: A Video Atlas, Humana Press. Current Clinical Neurology.","DOI":"10.1007\/978-1-60327-426-5"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1159\/000511930","article-title":"Artificial Intelligence in Medicine: Chances and Challenges for Wide Clinical Adoption","volume":"36","author":"Varghese","year":"2020","journal-title":"Visc. Med."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/9\/3139\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:56:12Z","timestamp":1760162172000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/9\/3139"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,30]]},"references-count":39,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["s21093139"],"URL":"https:\/\/doi.org\/10.3390\/s21093139","relation":{"has-preprint":[{"id-type":"doi","id":"10.20944\/preprints202103.0542.v1","asserted-by":"object"}]},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,30]]}}}