{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T15:43:41Z","timestamp":1779205421302,"version":"3.51.4"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,11,23]],"date-time":"2018-11-23T00:00:00Z","timestamp":1542931200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2018,11,23]],"date-time":"2018-11-23T00:00:00Z","timestamp":1542931200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digital Med"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Machine learning algorithms that use data streams captured from soft wearable sensors have the potential to automatically detect PD symptoms and inform clinicians about the progression of disease. However, these algorithms must be trained with annotated data from clinical experts who can recognize symptoms, and collecting such data are costly. Understanding how many sensors and how much labeled data are required is key to successfully deploying these models outside of the clinic. Here we recorded movement data using 6 flexible wearable sensors in 20 individuals with PD over the course of multiple clinical assessments conducted on 1 day and repeated 2 weeks later. Participants performed 13 common tasks, such as walking or typing, and a clinician rated the severity of symptoms (bradykinesia and tremor). We then trained convolutional neural networks and statistical ensembles to detect whether a segment of movement showed signs of bradykinesia or tremor based on data from tasks performed by other individuals. Our results show that a single wearable sensor on the back of the hand is sufficient for detecting bradykinesia and tremor in the upper extremities, whereas using sensors on both sides does not improve performance. Increasing the amount of training data by adding other individuals can lead to improved performance, but repeating assessments with the same individuals\u2014even at different medication states\u2014does not substantially improve detection across days. Our results suggest that PD symptoms can be detected during a variety of activities and are best modeled by a dataset incorporating many individuals.<\/jats:p>","DOI":"10.1038\/s41746-018-0071-z","type":"journal-article","created":{"date-parts":[[2018,11,19]],"date-time":"2018-11-19T14:19:33Z","timestamp":1542637173000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":187,"title":["Wearable sensors for Parkinson\u2019s disease: which data are worth collecting for training symptom detection models"],"prefix":"10.1038","volume":"1","author":[{"given":"Luca","family":"Lonini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9783-5463","authenticated-orcid":false,"given":"Andrew","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas","family":"Shawen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tanya","family":"Simuni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cynthia","family":"Poon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leo","family":"Shimanovich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Margaret","family":"Daeschler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roozbeh","family":"Ghaffari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John A.","family":"Rogers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arun","family":"Jayaraman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,11,23]]},"reference":[{"key":"71_CR1","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1007\/s00702-017-1686-y","volume":"124","author":"OB Tysnes","year":"2017","unstructured":"Tysnes, O. B. & Storstein, A. Epidemiology of Parkinson\u2019s disease. J. Neural Transm. 124, 901\u2013905 (2017).","journal-title":"J. Neural Transm."},{"key":"71_CR2","doi-asserted-by":"publisher","first-page":"1583","DOI":"10.1002\/mds.25945","volume":"29","author":"T Pringsheim","year":"2014","unstructured":"Pringsheim, T., Jette, N., Frolkis, A. & Steeves, T. D. L. The prevalence of Parkinson\u2019s disease: a systematic review and meta-analysis. Mov. Disord. 29, 1583\u20131590 (2014).","journal-title":"Mov. Disord."},{"key":"71_CR3","doi-asserted-by":"publisher","first-page":"368 LP","DOI":"10.1136\/jnnp.2007.131045","volume":"79","author":"J Jankovic","year":"2008","unstructured":"Jankovic, J. Parkinson\u2019s disease: clinical features and diagnosis. J. Neurol. Neurosurg. 79, 368 LP\u2013368376 (2008).","journal-title":"J. Neurol. Neurosurg."},{"key":"71_CR4","doi-asserted-by":"publisher","first-page":"5981","DOI":"10.1111\/febs.12335","volume":"280","author":"PMA Antony","year":"2013","unstructured":"Antony, P. M. A., Diederich, N. J., Kr\u00fcger, R. & Balling, R. The hallmarks of Parkinson\u2019s disease. FEBS J. 280, 5981\u20135993 (2013).","journal-title":"FEBS J."},{"key":"71_CR5","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.pneurobio.2015.07.002","volume":"132","author":"MF Bastide","year":"2015","unstructured":"Bastide, M. F. et al. Pathophysiology of L-dopa-induced motor and non-motor complications in Parkinson\u2019s disease. Prog. Neurobiol. 132, 96\u2013168 (2015).","journal-title":"Prog. Neurobiol."},{"key":"71_CR6","doi-asserted-by":"crossref","unstructured":"The Unified Parkinson\u2019s Disease Rating Scale (UPDRS. Status and recommendations. Mov. Disord. 18, 738\u2013750 (2003).","DOI":"10.1002\/mds.10473"},{"key":"71_CR7","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1097\/00002826-200003000-00003","volume":"23","author":"RA Hauser","year":"2000","unstructured":"Hauser, R. A. et al. A home diary to assess functional status in patients with Parkinson\u2019s disease with motor fluctuations and dyskinesia. Clin. Neuropharmacol. 23, 75\u201381 (2000).","journal-title":"Clin. Neuropharmacol."},{"key":"71_CR8","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1136\/jnnp.2003.022780","volume":"75","author":"J Reimer","year":"2004","unstructured":"Reimer, J., Grabowski, M., Lindvall, O. & Hagell, P. Use and interpretation of on\/off diaries in Parkinson\u2019s disease. J. Neurol. Neurosurg. Psychiatry 75, 396\u2013400 (2004).","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"71_CR9","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1097\/00005053-199010000-00004","volume":"178","author":"GK MONTGOMERY","year":"1990","unstructured":"MONTGOMERY, G. K. & REYNOLDS, N. C. Compliance, reliability, and validity of self-monitoring for physical disturbances of Parkinson\u2019s disease: the Parkinson\u2019s symptom diary. J. Nerv. Ment. Dis. 178, 636\u2013641 (1990).","journal-title":"J. Nerv. Ment. Dis."},{"key":"71_CR10","doi-asserted-by":"publisher","first-page":"1628","DOI":"10.1002\/mds.25628","volume":"28","author":"W Maetzler","year":"2013","unstructured":"Maetzler, W., Domingos, J., Srulijes, K., Ferreira, J. J. & Bloem, B. R. Quantitative wearable sensors for objective assessment of Parkinson\u2019s disease. Mov. Disord. 28, 1628\u20131637 (2013).","journal-title":"Mov. Disord."},{"key":"71_CR11","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/j.jneumeth.2007.08.023","volume":"167","author":"S Moore","year":"2008","unstructured":"Moore, S., MacDougall, H. & Ondo, W. Ambulatory monitoring of freezing of gait in Parkinson\u2019s disease. J. Neurosci. Methods 167, 340\u2013348 (2008).","journal-title":"J. Neurosci. Methods"},{"key":"71_CR12","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1109\/TITB.2009.2033471","volume":"13","author":"S Patel","year":"2009","unstructured":"Patel, S. et al. Monitoring motor fluctuations in patients with Parkinson\u2019s disease using wearable sensors. IEEE Trans. Inf. Technol. Biomed. 13, 864\u2013873 (2009).","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"71_CR13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0056956","volume":"8","author":"J Klucken","year":"2013","unstructured":"Klucken, J. et al. Unbiased and mobile gait analysis detects motor impairment in Parkinson\u2019s disease. PLoS ONE 8, e56956 (2013).","journal-title":"PLoS ONE"},{"key":"71_CR14","doi-asserted-by":"publisher","unstructured":"Eskofier, B. et al. Recent machine learning advancements in sensor-based mobility analysis: deep learning for Parkinson\u2019s disease assessment. 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. submitted (2016). https:\/\/doi.org\/10.1109\/EMBC.2016.7590787","DOI":"10.1109\/EMBC.2016.7590787"},{"key":"71_CR15","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1002\/1531-8257(200101)16:1<58::AID-MDS1018>3.0.CO;2-9","volume":"16","author":"JI Hoff","year":"2001","unstructured":"Hoff, J. I., Plas, A. A., Wagemans, E. A. H. & van Hilten, J. J. Accelerometric assessment of levodopa-induced dyskinesias in Parkinson\u2019s disease. Mov. Disord. 16, 58\u201361 (2001).","journal-title":"Mov. Disord."},{"key":"71_CR16","doi-asserted-by":"publisher","unstructured":"Daneault, J. F. et al. Estimating Bradykinesia in Parkinson\u2019 s Disease with a Minimum Number of Wearable Sensors. in 2017 IEEE\/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE) 5\u20136 (2017). https:\/\/doi.org\/10.1109\/CHASE.2017.94","DOI":"10.1109\/CHASE.2017.94"},{"key":"71_CR17","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1038\/s41531-018-0051-7","volume":"4","author":"P Odin","year":"2018","unstructured":"Odin, P. et al. Viewpoint and practical recommendations from a movement disorder specialist panel on objective measurement in the clinical management of Parkinson\u2019s disease. npj Park. Dis. 4, 14 (2018).","journal-title":"npj Park. Dis."},{"key":"71_CR18","doi-asserted-by":"publisher","first-page":"1272","DOI":"10.1002\/mds.26642","volume":"31","author":"AJ Espay","year":"2016","unstructured":"Espay, A. J. et al. Technology in Parkinson\u2019s disease: challenges and opportunities. Mov. Disord. 31, 1272\u20131282 (2016).","journal-title":"Mov. Disord."},{"key":"71_CR19","doi-asserted-by":"publisher","first-page":"1293","DOI":"10.1002\/mds.26718","volume":"31","author":"S Del Din","year":"2016","unstructured":"Del Din, S., Godfrey, A., Mazz\u00e0, C., Lord, S. & Rochester, L. Free-living monitoring of Parkinson\u2019s disease: lessons from the field. Mov. Disord. 31, 1293\u20131313 (2016).","journal-title":"Mov. Disord."},{"key":"71_CR20","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1097\/WCO.0000000000000219","volume":"28","author":"C Marras","year":"2015","unstructured":"Marras, C. Subtypes of Parkinson\u2019s disease: state of the field and future directions. Curr. Opin. Neurol. 28, 382\u2013386 (2015).","journal-title":"Curr. Opin. Neurol."},{"key":"71_CR21","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1001\/jamaneurol.2013.6233","volume":"71","author":"MA Thenganatt","year":"2014","unstructured":"Thenganatt, M. A. & Jankovic, J. Parkinson disease subtypes. JAMA Neurol. 71, 499\u2013504 (2014).","journal-title":"JAMA Neurol."},{"key":"71_CR22","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1002\/mds.23469","volume":"26","author":"MM Wickremaratchi","year":"2011","unstructured":"Wickremaratchi, M. M. et al. The motor phenotype of Parkinson\u2019s disease in relation to age at onset. Mov. Disord. 26, 457\u2013463 (2011).","journal-title":"Mov. Disord."},{"key":"71_CR23","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.parkreldis.2018.02.001","volume":"51","author":"Kelvin L. Chou","year":"2018","unstructured":"Chou, K. L. et al. The spectrum of \u2018off\u2019 in Parkinson\u2019s disease: What have we learned over 40 years? Parkinsonism Relat. Disord. (2018). https:\/\/doi.org\/10.1016\/j.parkreldis.2018.02.001","journal-title":"Parkinsonism & Related Disorders"},{"key":"71_CR24","doi-asserted-by":"crossref","unstructured":"Hammerla, N. Y. et al. PD disease state assessment in naturalistic environments using deep learning. in Proc. Twenty-Ninth AAAI Conference on Artificial Intelligence and Twenty-Seventh Innovative Applications of Artifical Intelligence Conference. 1742\u20131748 (AAAI Press, Cambridge, 2015).","DOI":"10.1609\/aaai.v29i1.9484"},{"key":"71_CR25","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.parkreldis.2016.09.009","volume":"33","author":"JM Fisher","year":"2016","unstructured":"Fisher, J. M. et al. Unsupervised home monitoring of Parkinson\u2019s disease motor symptoms using body-worn accelerometers. Park. Relat. Disord. 33, 44\u201350 (2016).","journal-title":"Park. Relat. Disord."},{"key":"71_CR26","doi-asserted-by":"publisher","first-page":"S11","DOI":"10.1002\/mds.20458","volume":"20","author":"J Jankovic","year":"2005","unstructured":"Jankovic, J. Motor fluctuations and dyskinesias in Parkinson\u2019s disease: clinical manifestations. Mov. Disord. 20, S11\u2013S16 (2005).","journal-title":"Mov. Disord."},{"key":"71_CR27","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. Random forests. Mach. Learn. 45, 5\u201332 (2001).","journal-title":"Mach. Learn."},{"issue":"2","key":"71_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3090076","volume":"1","author":"Yu Guan","year":"2017","unstructured":"Guan, Y. & Ploetz, T. Ensembles of deep LSTM learners for activity recognition using wearables. Proc. ACM Interactive, Mobile, Wearable Ubiquitous Technol. https:\/\/doi.org\/10.1145\/3090076. (2017).","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"71_CR29","doi-asserted-by":"publisher","first-page":"e1601185","DOI":"10.1126\/sciadv.1601185","volume":"2","author":"Y Liu","year":"2016","unstructured":"Liu, Y. et al. Epidermal mechano-acoustic sensing electronics for cardiovascular diagnostics and human-machine interfaces. Sci. Adv. 2, e1601185\u2013e1601185 (2016).","journal-title":"Sci. Adv."},{"key":"71_CR30","doi-asserted-by":"publisher","first-page":"1080","DOI":"10.1002\/mds.25391","volume":"28","author":"SH Roy","year":"2013","unstructured":"Roy, S. H. et al. High-resolution tracking of motor disorders in Parkinson\u2019s disease during unconstrained activity. Mov. Disord. 28, 1080\u20131087 (2013).","journal-title":"Mov. Disord."},{"key":"71_CR31","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.knosys.2017.10.017","volume":"139","author":"J Camps","year":"2018","unstructured":"Camps, J. et al. Deep learning for freezing of gait detection in Parkinson\u2019s disease patients in their homes using a waist-worn inertial measurement unit. Knowl. Based Syst. 139, 119\u2013131 (2018).","journal-title":"Knowl. Based Syst."},{"key":"71_CR32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0171764","volume":"12","author":"D Rodr\u00edguez-Mart\u00edn","year":"2017","unstructured":"Rodr\u00edguez-Mart\u00edn, D. et al. Home detection of freezing of gait using Support Vector Machines through a single waist-worn triaxial accelerometer. PLoS ONE 12, e0171764 (2017).","journal-title":"PLoS ONE"},{"key":"71_CR33","doi-asserted-by":"publisher","first-page":"1642","DOI":"10.1007\/s00415-017-8424-0","volume":"264","author":"AL Silva de Lima","year":"2017","unstructured":"Silva de Lima, A. L. et al. Freezing of gait and fall detection in Parkinson\u2019s disease using wearable sensors: a systematic review. J. Neurol. 264, 1642\u20131654 (2017).","journal-title":"J. Neurol."},{"key":"71_CR34","doi-asserted-by":"publisher","first-page":"2719","DOI":"10.1109\/TBME.2016.2554599","volume":"64","author":"T Pham","year":"2017","unstructured":"Pham, T. & Moore, S. Freezing of gait detection in Parkinson\u2019s disease: a subject-independent detector using anomaly scores. IEEE Trans. Biomed. Eng. 64, 2719\u20132728 (2017). S. L.-I. T. & 2017, U.","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"71_CR35","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1016\/j.parkreldis.2015.02.026","volume":"21","author":"S Arora","year":"2015","unstructured":"Arora, S. et al. Detecting and monitoring the symptoms of Parkinson\u2019s disease using smartphones: a pilot study. Park. Relat. Disord. 21, 650\u2013653 (2015).","journal-title":"Park. Relat. Disord."},{"key":"71_CR36","doi-asserted-by":"crossref","unstructured":"Zhan, A. et al. Using smartphones and machine learning to quantify Parkinson disease severity the mobile parkinson disease score. 21218, (2018).","DOI":"10.1001\/jamaneurol.2018.0809"},{"key":"71_CR37","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1109\/THMS.2015.2489688","volume":"46","author":"JH Hong","year":"2016","unstructured":"Hong, J.-H., Ramos, J. & Dey, A. K. Toward personalized activity recognition systems with a semipopulation approach. IEEE Trans. Human Mach. Syst. 46, 101\u2013112 (2016).","journal-title":"IEEE Trans. Human Mach. Syst."},{"key":"71_CR38","doi-asserted-by":"publisher","unstructured":"Lonini, L., Gupta, A., Kording, K. & Jayaraman, A. Activity recognition in patients with lower limb impairments: do we need training data from each patient? in2016 38th Annual International Conference of the IEEE Engineering in Medicine and BiologySociety (EMBC) 3265\u20133268 (IEEE, 2016). https:\/\/doi.org\/10.1109\/EMBC.2016.7591425","DOI":"10.1109\/EMBC.2016.7591425"},{"key":"71_CR39","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436\u2013444 (2015).","journal-title":"Nature"},{"key":"71_CR40","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929\u20131958 (2014).","journal-title":"J. Mach. Learn. Res."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-018-0071-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-018-0071-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-018-0071-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T12:44:18Z","timestamp":1671626658000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-018-0071-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,23]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2018,12]]}},"alternative-id":["71"],"URL":"https:\/\/doi.org\/10.1038\/s41746-018-0071-z","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,23]]},"assertion":[{"value":"15 June 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 November 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"J.A.R. and R.G. both hold equity in the company MC10 that makes wearable devices for medical applications. The remaining authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"64"}}