{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T06:16:28Z","timestamp":1783664188191,"version":"3.55.0"},"reference-count":27,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Hum. Neurosci."],"abstract":"<jats:p>Parkinson\u2019s disease (PD) is a progressive neurological disorder characterized by motor symptoms, with treatment responses varying widely across patients. To address the growing need for individualized treatment strategies, this paper introduces a practical framework for constructing optimal individualized treatment strategies using weighted support vector machines (SVMs). We construct an optimal rule as a function of patients\u2019 clinical profiles and demographics using two methods: Outcome-Weighted Learning (OWL), which assumes no unmeasured confounders, and Instrumental Variable Outcome-Weighted Learning (IV-OWL), which accounts for potential unmeasured confounders. To illustrate the application of these methods, we use harmonized and curated clinical data from the NET-PD LS1 and PRECEPT\/POSTCEPT studies to estimate the optimal second-line therapy decision rule for supplementing levodopa with either monoamine oxidase B (MAO-B) inhibitors or dopamine receptor agonists (DRA) based on patient characteristics. As an illustrative application, we analyzed two cohorts of patients who initiated second-line therapy within 90 and 180\u202fdays of baseline, with sample sizes of 84 and 121, respectively. Although the estimated improvements were not statistically significant, likely due in part to the small sample sizes, the learned IV-OWL rule showed improvement in annualized UPDRS III change compared with the observed treatment strategy and other static treatment strategies. This case study demonstrates the feasibility of applying weighted support vector machines to individualized second-line therapy selection in PD and illustrates the potential value of instrumental variable-based methods in addressing unmeasured confounders.<\/jats:p>","DOI":"10.3389\/fnhum.2026.1859515","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T05:39:02Z","timestamp":1783661942000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An application of weighted support vector machines to individualized second-line therapy selection after levodopa in Parkinson\u2019s disease"],"prefix":"10.3389","volume":"20","author":[{"given":"Cuong T.","family":"Pham","sequence":"first","affiliation":[{"name":"Department of Biostatistics and Computational Biology, University of Rochester","place":["Rochester, NY, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruth B.","family":"Schneider","sequence":"additional","affiliation":[{"name":"Center for Health and Technology, University of Rochester","place":["Rochester, NY, United States"]},{"name":"Department of Neurology, University of Rochester","place":["Rochester, NY, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles S.","family":"Venuto","sequence":"additional","affiliation":[{"name":"Center for Health and Technology, University of Rochester","place":["Rochester, NY, United States"]},{"name":"Department of Neurology, University of Rochester","place":["Rochester, NY, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Greta","family":"Smith","sequence":"additional","affiliation":[{"name":"Center for Health and Technology, University of Rochester","place":["Rochester, NY, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zachary P.","family":"Brehm","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Computational Biology, University of Rochester","place":["Rochester, NY, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael P.","family":"McDermott","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Computational Biology, University of Rochester","place":["Rochester, NY, United States"]},{"name":"Center for Health and Technology, University of Rochester","place":["Rochester, NY, United States"]},{"name":"Department of Neurology, University of Rochester","place":["Rochester, NY, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashkan","family":"Ertefaie","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Computational Biology, University of Rochester","place":["Rochester, NY, United States"]},{"name":"Department of Neurology, University of Rochester","place":["Rochester, NY, United States"]},{"name":"Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania","place":["Philadelphia, PA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"2297","DOI":"10.1002\/sim.6128","article-title":"Instrumental variable methods for causal inference","volume":"33","author":"Baiocchi","year":"2014","journal-title":"Stat. Med."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1434","DOI":"10.1080\/01621459.2023.2197686","article-title":"Cross-validation: what does it estimate and how well does it do it?","volume":"119","author":"Bates","year":"2024","journal-title":"J. Am. Stat. Assoc."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"39","DOI":"10.2147\/NDT.S1660","article-title":"Optimizing levodopa therapy for Parkinson's disease with levodopa\/carbidopa\/entacapone: implications from a clinical and patient perspective","volume":"4","author":"Brooks","year":"2008","journal-title":"Neuropsychiatr. Dis. Treat."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1080\/01621459.2020.1783272","article-title":"A semiparametric instrumental variable approach to optimal treatment regimes under endogeneity","volume":"116","author":"Cui","year":"2021","journal-title":"J. Am. Stat. Assoc."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"2647","DOI":"10.1214\/18-AOAS1174","article-title":"Instrumental variable analysis with censored data in the presence of many weak instruments","volume":"12","author":"Ertefaie","year":"2018","journal-title":"Ann. Appl. Stat."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1002\/pds.4158","article-title":"A tutorial on the use of instrumental variables in pharmacoepidemiology","volume":"26","author":"Ertefaie","year":"2017","journal-title":"Pharmacoepidemiol. Drug Saf."},{"key":"ref8","first-page":"153","article-title":"Unified Parkinson's disease rating scale","volume":"18","author":"Fahn","year":"1987","journal-title":"Recent Dev. Parkinson's Dis."},{"key":"ref9","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1007\/978-3-642-73899-9_14","volume-title":"Adverse Effects of Levodopa in Parkinson\u2019s Disease. Drugs for the Treatment of Parkinson\u2019s Disease","author":"Fahn","year":"1989"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"2498","DOI":"10.1056\/NEJMoa033447","article-title":"Levodopa and the progression of Parkinson's disease","volume":"351","author":"Fahn","year":"2004","journal-title":"N. Engl. J. Med."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"720","DOI":"10.3390\/jpm11080720","article-title":"Personalized medicine approach in treating Parkinson's disease, using Oral Administration of Levodopa\/carbidopa microtablets in clinical practice","volume":"11","author":"Gr\u00e9tarsd\u00f3ttir","year":"2021","journal-title":"J Pers Med."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1001\/jama.2015.120","article-title":"Effect of creatine monohydrate on clinical progression in patients with Parkinson disease: a randomized clinical trial","volume":"313","author":"Kieburtz","year":"2015","journal-title":"JAMA"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1186\/s41687-023-00631-6","article-title":"The effects of an individualized smartphone-based exercise program on self-defined motor tasks in Parkinson\u2019s disease: a long-term feasibility study","volume":"7","author":"L\u00fctzow","year":"2023","journal-title":"J. Patient-Rep. Outcomes."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1038\/s41531-018-0058-0","article-title":"Prevalence of Parkinson\u2019s disease across North America","volume":"4","author":"Marras","year":"2018","journal-title":"NPJ Parkinson's Dis."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"650","DOI":"10.3390\/jpm11070650","article-title":"Personalized medicine in Parkinson\u2019s disease: new options for advanced treatments","volume":"11","author":"Mishima","year":"2021","journal-title":"J. Pers. Med."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"738","DOI":"10.1002\/mds.10473","article-title":"The unified Parkinson\u2019s disease rating scale (UPDRS): status and recommendations","volume":"18","year":"2003","journal-title":"Mov. Disord."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"33","DOI":"10.2169\/internalmedicine.8940-21","article-title":"Recent advances in drug therapy for parkinson's disease","volume":"62","author":"Murakami","year":"2023","journal-title":"Intern. Med."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1212\/01.wnl.0000277648.63931.c0","article-title":"Mixed lineage kinase inhibitor CEP-1347 fails to delay disability in early Parkinson disease","volume":"69","year":"2007","journal-title":"Neurology"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1097\/00002826-200011000-00005","article-title":"Rasagiline mesylate, a new MAO-B inhibitor for the treatment of Parkinson's disease: a double-blind study as adjunctive therapy to levodopa","volume":"23","author":"Rabey","year":"2000","journal-title":"Clin. Neuropharmacol."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"199","DOI":"10.3390\/pr14020199","article-title":"AI in Parkinson\u2019s disease: a short review of machine learning approaches for diagnosis","volume":"14","author":"Sharma","year":"2026","journal-title":"PRO"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1111\/j.2517-6161.1974.tb00994.x","article-title":"Cross-Validatory choice and assessment of statistical predictions","volume":"36","author":"Stone","year":"2018","journal-title":"J. Royal Stat. Soc. Series B"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"046006","DOI":"10.1088\/1741-2552\/aabc9b","article-title":"Adaptive deep brain stimulation for Parkinson\u2019s disease using motor cortex sensing","volume":"15","author":"Swann","year":"2018","journal-title":"J. Neural Eng."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1002\/mds.27027","article-title":"Personalized medicine in Parkinson's disease: time to be precise","volume":"32","author":"Titova","year":"2017","journal-title":"Mov. Disord."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1111\/rssb.12262","article-title":"Bounded, efficient and multiply robust estimation of average treatment effects using instrumental variables","volume":"80","author":"Wang","year":"2018","journal-title":"J R Stat Soc Series B Stat Methodol."},{"key":"ref26","volume-title":"Optimizing Individualized Treatment Planning for Parkinson\u2019s Disease using deep Reinforcement Learning. 2020 42nd Annual International Conference of the IEEE Engineering in medicine and Biology Society (EMBC)","author":"Watts","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"7","DOI":"10.32614\/CRAN.package.WeightSVM","article-title":"_WeightSVM: subject weighted support vector machines","volume":"1","author":"Xu","year":"2024","journal-title":"R Package Version"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"175884","DOI":"10.1016\/j.ejphar.2023.175884","article-title":"Dopamine agonists versus levodopa monotherapy in early Parkinson's disease for the potential risks of motor complications: a network meta-analysis","volume":"954","author":"Zhang","year":"2023","journal-title":"Eur. J. Pharmacol."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1080\/01621459.2012.695674","article-title":"Estimating individualized treatment rules using outcome weighted learning","volume":"107","author":"Zhao","year":"2012","journal-title":"J. Am. Stat. Assoc."}],"container-title":["Frontiers in Human Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnhum.2026.1859515\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T05:39:04Z","timestamp":1783661944000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnhum.2026.1859515\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,10]]},"references-count":27,"alternative-id":["10.3389\/fnhum.2026.1859515"],"URL":"https:\/\/doi.org\/10.3389\/fnhum.2026.1859515","relation":{},"ISSN":["1662-5161"],"issn-type":[{"value":"1662-5161","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,10]]},"article-number":"1859515"}}