{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:55:44Z","timestamp":1775840144957,"version":"3.50.1"},"reference-count":46,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2021,11,23]],"date-time":"2021-11-23T00:00:00Z","timestamp":1637625600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003173","name":"Crafoord Foundation","doi-asserted-by":"publisher","award":["20180610"],"award-info":[{"award-number":["20180610"]}],"id":[{"id":"10.13039\/501100003173","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011077","name":"Sk\u00e5ne University Hospital","doi-asserted-by":"publisher","award":["#96437 and #96438"],"award-info":[{"award-number":["#96437 and #96438"]}],"id":[{"id":"10.13039\/501100011077","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"publisher","award":["2019-01757"],"award-info":[{"award-number":["2019-01757"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Swedish Government (under the Avtal om L\u00e4karutbildning och 408 Medicinsk Forskning, ALF)","award":["#I-ALF 47447 and #YF-ALF 43435"],"award-info":[{"award-number":["#I-ALF 47447 and #YF-ALF 43435"]}]},{"name":"Sparbanksstiftelsen F\u00e4rs och Frosta","award":["To AGL"],"award-info":[{"award-number":["To AGL"]}]},{"name":"Fremasons Lodge of 410 Instruction Eos in Lund","award":["To AGL"],"award-info":[{"award-number":["To AGL"]}]},{"name":"Wallenberg Artificial Intelligence, Autonomous 412 Systems and Software Program (WASP)","award":["To K\u00c5"],"award-info":[{"award-number":["To K\u00c5"]}]},{"name":"the strategic research projects ELLIIT and eSSENCE, the Swedish 411 Foundation for Strategic Research project","award":["To K\u00c5"],"award-info":[{"award-number":["To K\u00c5"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Recent advances in stroke treatment have provided effective tools to successfully treat ischemic stroke, but still a majority of patients are not treated due to late arrival to hospital. With modern stroke treatment, earlier arrival would greatly improve the overall treatment results. This prospective study was performed to asses the capability of bilateral accelerometers worn in bracelets 24\/7 to detect unilateral arm paralysis, a hallmark symptom of stroke, early enough to receive treatment. Classical machine learning algorithms as well as state-of-the-art deep neural networks were evaluated on detection times between 15 min and 120 min. Motion data were collected using triaxial accelerometer bracelets worn on both arms for 24 h. Eighty-four stroke patients with unilateral arm motor impairment and 101 healthy subjects participated in the study. Accelerometer data were divided into data windows of different lengths and analyzed using multiple machine learning algorithms. The results show that all algorithms performed well in separating the two groups early enough to be clinically relevant, based on wrist-worn accelerometers. The two evaluated deep learning models, fully convolutional network and InceptionTime, performed better than the classical machine learning models with an AUC score between 0.947\u20130.957 on 15 min data windows and up to 0.993\u20130.994 on 120 min data windows. Window lengths longer than 90 min only marginally improved performance. The difference in performance between the deep learning models and the classical models was statistically significant according to a non-parametric Friedman test followed by a post-hoc Nemenyi test. Introduction of wearable stroke detection devices may dramatically increase the portion of stroke patients eligible for revascularization and shorten the time to treatment. Since the treatment effect is highly time-dependent, early stroke detection may dramatically improve stroke outcomes.<\/jats:p>","DOI":"10.3390\/s21237784","type":"journal-article","created":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T01:45:02Z","timestamp":1638323102000},"page":"7784","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Detection of Unilateral Arm Paresis after Stroke by Wearable Accelerometers and Machine Learning"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1896-381X","authenticated-orcid":false,"given":"Johan","family":"Wasselius","sequence":"first","affiliation":[{"name":"Department of Medical Imaging and Physiology, Sk\u00e5ne University Hospital, 22185 Lund, Sweden"},{"name":"Department of Clinical Sciences, Lund University, 22185 Lund, Sweden"}]},{"given":"Eric","family":"Lyckeg\u00e5rd Finn","sequence":"additional","affiliation":[{"name":"Uman Sense AB, 22381 Lund, Sweden"},{"name":"Centre for Mathematical Sciences, Lund University, P.O. Box 118, 22100 Lund, Sweden"}]},{"given":"Emma","family":"Persson","sequence":"additional","affiliation":[{"name":"Centre for Mathematical Sciences, Lund University, P.O. Box 118, 22100 Lund, Sweden"}]},{"given":"Petter","family":"Ericson","sequence":"additional","affiliation":[{"name":"Uman Sense AB, 22381 Lund, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9249-9421","authenticated-orcid":false,"given":"Christina","family":"Brog\u00e5rdh","sequence":"additional","affiliation":[{"name":"Department of Neurology, Rehabilitation Medicine, Memory and Geriatrics, Sk\u00e5ne University Hospital, 22185 Lund, Sweden"},{"name":"Department of Health Sciences, Lund University, 22185 Lund, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1942-7330","authenticated-orcid":false,"given":"Arne G.","family":"Lindgren","sequence":"additional","affiliation":[{"name":"Department of Clinical Sciences, Lund University, 22185 Lund, Sweden"},{"name":"Department of Neurology, Sk\u00e5ne University Hospital, 22185 Lund, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6717-0915","authenticated-orcid":false,"given":"Teresa","family":"Ullberg","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging and Physiology, Sk\u00e5ne University Hospital, 22185 Lund, Sweden"},{"name":"Department of Clinical Sciences, Lund University, 22185 Lund, Sweden"}]},{"given":"Kalle","family":"\u00c5str\u00f6m","sequence":"additional","affiliation":[{"name":"Centre for Mathematical Sciences, Lund University, P.O. Box 118, 22100 Lund, Sweden"}]}],"member":"1968","published-online":{"date-parts":[[2021,11,23]]},"reference":[{"key":"ref_1","first-page":"10470","article-title":"Ambient assisted living technologies for older adults with cognitive and physical impairments: A review","volume":"23","author":"Ganesan","year":"2019","journal-title":"Eur. Rev. Med Pharmacol. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Nakaoku, Y., Ogata, S., Murata, S., Nishimori, M., Ihara, M., Iihara, K., Takegami, M., and Nishimura, K. (2021). AI-Assisted In-House Power Monitoring for the Detection of Cognitive Impairment in Older Adults. Sensors, 21.","DOI":"10.3390\/s21186249"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Taylor, A.G., Mielke, C., and Mongan, J. (2018). Automated detection of moderate and large pneumothorax on frontal chest X-rays using deep convolutional neural networks: A retrospective study. PLOS Med., 15.","DOI":"10.1371\/journal.pmed.1002697"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e14857","DOI":"10.2196\/14857","article-title":"Use of a Smart Watch for Early Detection of Paroxysmal Atrial Fibrillation: Validation Study","volume":"4","author":"Inui","year":"2020","journal-title":"JMIR Cardio"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e26167","DOI":"10.2196\/26167","article-title":"Diagnostic Accuracy of Ambulatory Devices in Detecting Atrial Fibrillation: Systematic Review and Meta-analysis","volume":"9","author":"Yang","year":"2021","journal-title":"JMIR Mhealth Uhealth"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2365","DOI":"10.1016\/j.jacc.2019.08.019","article-title":"Mobile Photoplethysmographic Technology to Detect Atrial Fibrillation","volume":"74","author":"Guo","year":"2019","journal-title":"J. Am. Coll. Cardiol."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Schrumpf, F., Frenzel, P., Aust, C., Osterhoff, G., and Fuchs, M. (2021). Assessment of Non-Invasive Blood Pressure Prediction from PPG and rPPG Signals Using Deep Learning. Sensors, 21.","DOI":"10.3390\/s21186022"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2573","DOI":"10.1161\/STROKEAHA.119.027479","article-title":"Artificial Intelligence Applications in Stroke","volume":"51","author":"Mouridsen","year":"2020","journal-title":"Stroke"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2","DOI":"10.3174\/ajnr.A6883","article-title":"Artificial Intelligence and Acute Stroke Imaging","volume":"42","author":"Soun","year":"2020","journal-title":"AJNR Am. J. Neuroradiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"105826","DOI":"10.1016\/j.jstrokecerebrovasdis.2021.105826","article-title":"Automatic Acute Stroke Symptom Detection and Emergency Medical Systems Alerting by Mobile Health Technologies: A Review","volume":"30","author":"Saver","year":"2021","journal-title":"J. Stroke Cerebrovasc. Dis."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1161\/01.STR.13.5.629","article-title":"Epidemiology of stroke in Tilburg, the Netherlands. The population-based stroke incidence register: 2. Incidence, initial clinical picture and medical care, and three-week case fatality","volume":"13","author":"Herman","year":"1982","journal-title":"Stroke"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1136\/jnnp.48.1.7","article-title":"Recovery after stroke\u2013the first 3 months","volume":"48","author":"Wade","year":"1985","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1161\/01.STR.19.9.1083","article-title":"The Lausanne Stroke Registry: Analysis of 1000 consecutive patients with first stroke","volume":"19","author":"Bogousslavsky","year":"1988","journal-title":"Stroke"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1080\/10903129808958878","article-title":"Design and retrospective analysis of the Los Angeles prehospital stroke screen (LAPSS)","volume":"2","author":"Kidwell","year":"1998","journal-title":"Prehospital Emerg. Care"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1929","DOI":"10.1016\/S0140-6736(14)60584-5","article-title":"Effect of treatment delay, age, and stroke severity on the effects of intravenous thrombolysis with alteplase for acute ischaemic stroke: A meta-analysis of individual patient data from randomised trials","volume":"384","author":"Emberson","year":"2014","journal-title":"Lancet"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1723","DOI":"10.1016\/S0140-6736(16)00163-X","article-title":"Endovascular thrombectomy after large-vessel ischaemic stroke: A meta-analysis of individual patient data from five randomised trials","volume":"387","author":"Goyal","year":"2016","journal-title":"Lancet"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1001\/jama.2016.13647","article-title":"Time to Treatment With Endovascular Thrombectomy and Outcomes From Ischemic Stroke: A Meta-analysis","volume":"316","author":"Saver","year":"2016","journal-title":"JAMA"},{"key":"ref_19","unstructured":"Riksstroke\u2014The Swedish Stroke Register (2021, September 15). Quality of Swedish Stroke Care. Available online: riksstroke.org."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1056\/NEJMoa1706442","article-title":"Thrombectomy 6 to 24 Hours after Stroke with a Mismatch between Deficit and Infarct","volume":"378","author":"Nogueira","year":"2018","journal-title":"N. Engl. J. Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1056\/NEJMoa1713973","article-title":"Thrombectomy for Stroke at 6 to 16 Hours with Selection by Perfusion Imaging","volume":"378","author":"Albers","year":"2018","journal-title":"N. Engl. J. Med."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1498","DOI":"10.1016\/j.apmr.2005.01.010","article-title":"Ambulatory Monitoring of Arm Movement Using Accelerometry: An Objective Measure of Upper-Extremity Rehabilitation in Persons With Chronic Stroke","volume":"86","author":"Uswatte","year":"2005","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1016\/j.apmr.2007.06.005","article-title":"The Stroke Upper-Limb Activity Monitor: Its Sensitivity to Measure Hemiplegic Upper-Limb Activity During Daily Life","volume":"88","author":"Bussmann","year":"2007","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1589\/jpts.26.1009","article-title":"Comparison of Upper Extremity Motor Recovery of Stroke Patients with Actual Physical Activity in Their Daily Lives Measured with Accelerometers","volume":"26","author":"Shim","year":"2014","journal-title":"J. Phys. Ther. Sci."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1740","DOI":"10.1007\/s00415-018-8786-y","article-title":"Wearable sensors for clinical applications in epilepsy, Parkinson\u2019s disease, and stroke: A mixed-methods systematic review","volume":"265","author":"Johansson","year":"2018","journal-title":"J. Neurol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1186\/1743-0003-11-144","article-title":"Accelerometer measurement of upper extremity movement after stroke: A systematic review of clinical studies","volume":"11","author":"Rodgers","year":"2014","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1450036","DOI":"10.1142\/S0129065714500361","article-title":"Improving Human Activity Recognition and its Application in Early Stroke Diagnosis","volume":"25","author":"Villar","year":"2015","journal-title":"Int. J. Neural Syst."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Bailey, R.R., Klaesner, J.W., and Lang, C.E. (2014). An Accelerometry-Based Methodology for Assessment of Real-World Bilateral Upper Extremity Activity. PLoS ONE, 9.","DOI":"10.1371\/journal.pone.0103135"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1016\/j.apmr.2011.02.021","article-title":"Assessment of Arm Activity Using Triaxial Accelerometry in Patients With a Stroke","volume":"92","author":"Verbunt","year":"2011","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Jeon, S., Park, T., Lee, Y.S., Son, S.H., Lee, H., and Eun, Y. (2018, January 7\u201310). RISK-Sleep: Real-Time Stroke Early Detection System During Sleep Using Wristbands. Proceedings of the 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Miyazaki, Japan.","DOI":"10.1109\/SMC.2018.00732"},{"key":"ref_31","unstructured":"Persson, E., and Lyckeg\u00e5rd Finn, E. (2020). Investigating the Use of Machine Learning to Detect Unilateral Arm Weakness. [Master\u2019s Thesis, Lund University]."},{"key":"ref_32","unstructured":"Russell, S.J., and Norvig, P. (2021). Artificial Intelligence: A Modern Approach, Pearson Education Limited. Chapter 19."},{"key":"ref_33","unstructured":"Bishop, C.M. (2006). Pattern Recognition and Machine Learning, Springer Science+Business Media LLC. Chapter 7."},{"key":"ref_34","unstructured":"Hastie, T., Tibshirani, R., and Friedman, J. (2017). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer Science+Business Media LLC. Chapter 15.2."},{"key":"ref_35","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_37","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_38","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1007\/s10618-019-00619-1","article-title":"Deep learning for time series classification: A review","volume":"33","author":"Fawaz","year":"2019","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_39","unstructured":"Chen, Y., Keogh, E., Hu, B., Begum, N., Bagnall, A., Mueen, A., and Batista, G. (2021, September 14). The UCR Time Series Classification Archive. Available online: www.cs.ucr.edu\/eamonn\/timeseriesdata\/."},{"key":"ref_40","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1007\/s10618-020-00710-y","article-title":"Inceptiontime: Finding alexnet for time series classification","volume":"34","author":"Fawaz","year":"2020","journal-title":"Data Min. Knowl. Discov."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A.A. (2017, January 4\u20139). Inception-v4, inception-resnet and the impact of residual connections on learning. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref_43","first-page":"1","article-title":"ROC graphs: Notes and practical considerations for researchers","volume":"31","author":"Fawcett","year":"2004","journal-title":"Mach. Learn."},{"key":"ref_44","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/MCSE.2007.55","article-title":"Matplotlib: A 2D graphics environment","volume":"9","author":"Hunter","year":"2007","journal-title":"Comput. Sci. Eng."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"E112","DOI":"10.3174\/ajnr.A5853","article-title":"Standards of Practice in Acute Ischemic Stroke Intervention: International Recommendations","volume":"39","author":"Pierot","year":"2018","journal-title":"Am. J. Neuroradiol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/23\/7784\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:34:47Z","timestamp":1760168087000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/23\/7784"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,23]]},"references-count":46,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["s21237784"],"URL":"https:\/\/doi.org\/10.3390\/s21237784","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,23]]}}}