{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:43:36Z","timestamp":1761061416023,"version":"build-2065373602"},"reference-count":34,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2021,5,20]],"date-time":"2021-05-20T00:00:00Z","timestamp":1621468800000},"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>Parkinson\u2019s disease medication treatment planning is generally based on subjective data obtained through clinical, physician-patient interactions. The Personal KinetiGraph\u2122 (PKG) and similar wearable sensors have shown promise in enabling objective, continuous remote health monitoring for Parkinson\u2019s patients. In this proof-of-concept study, we propose to use objective sensor data from the PKG and apply machine learning to cluster patients based on levodopa regimens and response. The resulting clusters are then used to enhance treatment planning by providing improved initial treatment estimates to supplement a physician\u2019s initial assessment. We apply k-means clustering to a dataset of within-subject Parkinson\u2019s medication changes\u2014clinically assessed by the MDS-Unified Parkinson\u2019s Disease Rating Scale-III (MDS-UPDRS-III) and the PKG sensor for movement staging. A random forest classification model was then used to predict patients\u2019 cluster allocation based on their respective demographic information, MDS-UPDRS-III scores, and PKG time-series data. Clinically relevant clusters were partitioned by levodopa dose, medication administration frequency, and total levodopa equivalent daily dose\u2014with the PKG providing similar symptomatic assessments to physician MDS-UPDRS-III scores. A random forest classifier trained on demographic information, MDS-UPDRS-III scores, and PKG time-series data was able to accurately classify subjects of the two most demographically similar clusters with an accuracy of 86.9%, an F1 score of 90.7%, and an AUC of 0.871. A model that relied solely on demographic information and PKG time-series data provided the next best performance with an accuracy of 83.8%, an F1 score of 88.5%, and an AUC of 0.831, hence further enabling fully remote assessments. These computational methods demonstrate the feasibility of using sensor-based data to cluster patients based on their medication responses with further potential to assist with medication recommendations.<\/jats:p>","DOI":"10.3390\/s21103553","type":"journal-article","created":{"date-parts":[[2021,5,20]],"date-time":"2021-05-20T06:13:45Z","timestamp":1621491225000},"page":"3553","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Improving Medication Regimen Recommendation for Parkinson\u2019s Disease Using Sensor Technology"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9573-264X","authenticated-orcid":false,"given":"Jeremy","family":"Watts","sequence":"first","affiliation":[{"name":"Department of Industrial and Systems Engineering, University of Tennessee, Knoxville, TN 37996, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6818-2048","authenticated-orcid":false,"given":"Anahita","family":"Khojandi","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering, University of Tennessee, Knoxville, TN 37996, USA"}]},{"given":"Rama","family":"Vasudevan","sequence":"additional","affiliation":[{"name":"Center for Nanophase Materials Science, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA"}]},{"given":"Fatta B.","family":"Nahab","sequence":"additional","affiliation":[{"name":"Department of Neurosciences, University of California San Diego, La Jolla, CA 92093, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0695-0707","authenticated-orcid":false,"given":"Ritesh A.","family":"Ramdhani","sequence":"additional","affiliation":[{"name":"Department of Neurology, Donald and Barbara School of Medicine at Hofstra\/Northwell, Hempstead, NY 11549, USA"}]}],"member":"1968","published-online":{"date-parts":[[2021,5,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1038\/nrn.2017.62","article-title":"Non-motor features of Parkinson disease","volume":"18","author":"Schapira","year":"2017","journal-title":"Nat. Rev. Neurosci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1016\/S1474-4422(17)30299-5","article-title":"Global, regional, and national burden of neurological disorders during 1990\u20132015: A systematic analysis for the Global Burden of Disease Study 2015","volume":"16","author":"Feigin","year":"2017","journal-title":"Lancet Neurol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1989","DOI":"10.1212\/WNL.0b013e318293e2ce","article-title":"The coming crisis: Obtaining care for the growing burden of neurodegenerative conditions","volume":"80","author":"Dorsey","year":"2013","journal-title":"Neurology"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1558","DOI":"10.1212\/WNL.38.10.1558","article-title":"Parkinsonism death rates by race, sex, and geography","volume":"38","author":"Kurtzke","year":"1988","journal-title":"Neurology"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/S0022-510X(97)05371-9","article-title":"The geographic distribution of Parkinson\u2019s disease mortality in the United States","volume":"150","author":"Lanska","year":"1997","journal-title":"J. Neurol. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1093\/oxfordjournals.aje.a117721","article-title":"The frequency of idiopathic Parkinson\u2019s disease by age, ethnic group, and sex in northern Manhattan, 1988\u20131993","volume":"142","author":"Mayeux","year":"1995","journal-title":"Am. J. Epidemiol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1001\/jamaneurol.2013.123","article-title":"Randomized controlled clinical trial of \u201cvirtual house calls\u201d for Parkinson disease","volume":"70","author":"Dorsey","year":"2013","journal-title":"JAMA Neurol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1212\/WNL.0b013e31822c9123","article-title":"Neurologist care in Parkinson disease: A utilization, outcomes, and survival study","volume":"77","author":"Willis","year":"2011","journal-title":"Neurology"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1159\/000324935","article-title":"Delayed Parkinson\u2019s disease diagnosis among African-Americans: The role of reporting of disability","volume":"36","author":"Dahodwala","year":"2011","journal-title":"Neuroepidemiology"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.genm.2011.05.002","article-title":"Diagnosis and referral delay in women with Parkinson\u2019s disease","volume":"8","author":"Wang","year":"2011","journal-title":"Gend. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1016\/S1474-4422(06)70521-X","article-title":"Continuous dopamine-receptor treatment of Parkinson\u2019s disease: Scientific rationale and clinical implications","volume":"5","author":"Olanow","year":"2006","journal-title":"Lancet Neurol."},{"key":"ref_12","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_13","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1097\/01.WNF.0000229546.81245.7F","article-title":"Patient evaluation of a home diary to assess duration and severity of dyskinesia in Parkinson disease","volume":"29","author":"Hauser","year":"2006","journal-title":"Clin. Neuropharmacol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"72","DOI":"10.3389\/fncom.2018.00072","article-title":"Optimizing clinical assessments in Parkinson\u2019s disease through the use of wearable sensors and data driven modeling","volume":"12","author":"Ramdhani","year":"2018","journal-title":"Front. Comput. Neurosci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1002\/mds.26673","article-title":"A clinical view on the development of technology-based tools in managing Parkinson\u2019s disease","volume":"31","author":"Maetzler","year":"2016","journal-title":"Mov. Disord."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1002\/mds.20633","article-title":"Ambulatory motor assessment in Parkinson\u2019s disease","volume":"21","author":"Keijsers","year":"2006","journal-title":"Mov. Disord. Off. J. Mov. Disord. Soc."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Tsipouras, M.G., Tzallas, A.T., Rigas, G., Bougia, P., Fotiadis, D.I., and Konitsiotis, S. (September, January 31). Automated levodopa-induced dyskinesia assessment. Proceedings of the 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, Buenos Aires, Argentina.","DOI":"10.1109\/IEMBS.2010.5626130"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"47","DOI":"10.3233\/JPD-2012-11071","article-title":"Automated assessment of bradykinesia and dyskinesia in Parkinson\u2019s disease","volume":"2","author":"Griffiths","year":"2012","journal-title":"J. Parkinsons Dis."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1109\/TBME.2017.2697764","article-title":"Continuous assessment of levodopa response in Parkinson\u2019s disease using wearable motion sensors","volume":"65","author":"Pulliam","year":"2017","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1016\/j.parkreldis.2014.02.011","article-title":"Daytime sleep in Parkinson\u2019s disease measured by episodes of immobility","volume":"20","author":"Kotschet","year":"2014","journal-title":"Parkinsonism Relat. Disord."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Horne, M.K., McGregor, S., and Bergquist, F. (2015). An objective fluctuation score for Parkinson\u2019s disease. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0124522"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"723","DOI":"10.3233\/JPD-160898","article-title":"An ambulatory tremor score for Parkinson\u2019s disease","volume":"6","author":"Braybrook","year":"2016","journal-title":"J. Parkinsons Dis."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"42","DOI":"10.4236\/apd.2019.83005","article-title":"Evaluation of clinical utility of the Personal KinetiGraph\u00ae in the management of Parkinson\u2019s disease","volume":"8","author":"Nahab","year":"2019","journal-title":"Adv. Parkinsons Dis."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1366","DOI":"10.1007\/s13311-020-00894-7","article-title":"Therapy of Parkinson\u2019s disease subtypes","volume":"17","author":"Marras","year":"2020","journal-title":"Neurotherapeutics"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"804","DOI":"10.1038\/nrd.2018.136","article-title":"Therapeutic strategies for Parkinson disease: Beyond dopaminergic drugs","volume":"17","author":"Charvin","year":"2018","journal-title":"Nat. Rev. Drug Discov."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"969","DOI":"10.1002\/mds.23116","article-title":"The identification of Parkinson\u2019s disease subtypes using cluster analysis: A systematic review","volume":"25","author":"Heiser","year":"2010","journal-title":"Mov. Disord."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1002\/acm2.12139","article-title":"Using k-means clustering to determine the number and position of isocenters in MLC-based multiple target intracranial radiosurgery","volume":"18","author":"Yock","year":"2017","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_29","first-page":"18","article-title":"Classification and regression by randomForest","volume":"2","author":"Liaw","year":"2002","journal-title":"R News"},{"key":"ref_30","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_31","unstructured":"Tan, P., Steinbach, M., and Kumar, V. (2006). Introduction to Data Mining, Pearson Education."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1080\/14737175.2018.1503948","article-title":"Role of the Personal KinetiGraph in the routine clinical assessment of Parkinson\u2019s disease: Recommendations from an expert panel","volume":"18","author":"Pahwa","year":"2018","journal-title":"Expert Rev. Neurother."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"301","DOI":"10.3389\/fnagi.2017.00301","article-title":"Parkinson\u2019s disease subtypes identified from cluster analysis of motor and non-motor symptoms","volume":"9","author":"Mu","year":"2017","journal-title":"Front. Aging Neurosci."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.parkreldis.2016.04.026","article-title":"Clinical clusters and dopaminergic dysfunction in de-novo Parkinson disease","volume":"28","author":"Erro","year":"2016","journal-title":"Parkinsonism Relat. Disord."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/10\/3553\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:04:28Z","timestamp":1760162668000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/10\/3553"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,20]]},"references-count":34,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["s21103553"],"URL":"https:\/\/doi.org\/10.3390\/s21103553","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2021,5,20]]}}}