{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T14:30:47Z","timestamp":1786113047218,"version":"build-2736575974"},"reference-count":55,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    Parkinson\u2019s disease (PD) is a progressive neurological disorder characterized by motor impairments whose severity is commonly assessed using the Unified Parkinson\u2019s Disease Rating Scale (UPDRS). Although clinically established, UPDRS assessment is inherently subjective, requiring in-person evaluation by trained specialists, limiting its suitability for frequent monitoring. Speech production is affected early in PD and provides a non-invasive modality for remote symptom assessment. In this study, an uncertainty-aware personalized framework is proposed for estimating PD severity from speech signals. The approach integrates longitudinal temporal modeling of longitudinal speech recordings with patient-specific representations and a probabilistic latent disease state. Continuous motor UPDRS scores are jointly estimated with data-driven ordinal disease severity stages, enabling both fine-grained regression and auxiliary ordinal prediction. Predictive uncertainty is explicitly quantified to characterize predictive variability within the proposed framework. The method is evaluated on a longitudinal speech dataset using a strict patient-wise split, ensuring that all test subjects are unseen during training. On the held-out test set, the proposed model achieves promising predictive accuracy (mean absolute error 0.56 UPDRS points, root mean squared error 0.74, and coefficient of determination\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    \u2009=\u20090.99) for motor UPDRS estimation. Ordinal severity classification attained an accuracy of 0.92 across three stages. Comparative experiments against classical machine learning methods and global temporal baselines demonstrate consistent performance improvements. These results demonstrate the potential of personalized, uncertainty-aware speech modeling for longitudinal PD severity estimation.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0343191","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T17:35:23Z","timestamp":1785951323000},"page":"e0343191","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty-aware personalized estimation of Parkinson\u2019s disease severity from longitudinal speech"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2571-7485","authenticated-orcid":true,"given":"Khondakar Ashik","family":"Shahriar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"issue":"10423","key":"pone.0343191.ref001","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/S0140-6736(23)01419-8","article-title":"The epidemiology of Parkinson\u2019s disease","volume":"403","author":"Y Ben-Shlomo","year":"2024","journal-title":"Lancet"},{"issue":"10291","key":"pone.0343191.ref002","doi-asserted-by":"crossref","first-page":"2284","DOI":"10.1016\/S0140-6736(21)00218-X","article-title":"Parkinson\u2019s disease","volume":"397","author":"BR Bloem","year":"2021","journal-title":"Lancet"},{"issue":"6","key":"pone.0343191.ref003","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1136\/jnnp.57.6.672","article-title":"Parkinson\u2019s disease","volume":"57","author":"CD Marsden","year":"1994","journal-title":"J Neurol Neurosurg Psychiatry"},{"issue":"7","key":"pone.0343191.ref004","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1002\/mds.10473","article-title":"The unified Parkinson\u2019s disease rating scale (UPDRS): status and recommendations","volume":"18","author":"Movement Disorder Society Task Force on Rating Scales for Parkinson\u2019s Disease","year":"2003","journal-title":"Movement Disorders"},{"key":"pone.0343191.ref005","doi-asserted-by":"crossref","unstructured":"Sveinbjornsdottir S. The clinical symptoms of Parkinson\u2019s disease. J Neurochem. 2016;139 Suppl 1:318\u201324. https:\/\/doi.org\/10.1111\/jnc.13691 27401947","DOI":"10.1111\/jnc.13691"},{"key":"pone.0343191.ref006","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/S0072-9752(07)83013-2","article-title":"Motor symptoms in Parkinson\u2019s disease","volume":"83","author":"J Shahed","year":"2007","journal-title":"Handb Clin Neurol"},{"issue":"11","key":"pone.0343191.ref007","first-page":"1669","article-title":"Clinical tests for the evaluation of postural instability in patients with parkinson\u2019s disease","volume":"84","author":"M Visser","year":"2003","journal-title":"Arch Phys Med Rehabil"},{"issue":"1","key":"pone.0343191.ref008","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1001\/archneurol.2009.295","article-title":"The clinically important difference on the unified Parkinson\u2019s disease rating scale","volume":"67","author":"LM Shulman","year":"2010","journal-title":"Arch Neurol"},{"issue":"1","key":"pone.0343191.ref009","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.parkreldis.2014.10.026","article-title":"Parkinson\u2019s disease severity levels and MDS-Unified Parkinson\u2019s Disease Rating Scale","volume":"21","author":"P Mart\u00ednez-Mart\u00edn","year":"2015","journal-title":"Parkinsonism Relat Disord"},{"key":"pone.0343191.ref010","doi-asserted-by":"crossref","unstructured":"Tsanas A, Little M, McSharry P, Ramig L. Accurate telemonitoring of Parkinson\u2019s disease progression by non-invasive speech tests. Nat Prec. 2009. https:\/\/doi.org\/10.1038\/npre.2009.3920.1","DOI":"10.1038\/npre.2009.3920.1"},{"key":"pone.0343191.ref011","doi-asserted-by":"crossref","unstructured":"Tsanas A, Little MA, McSharry PE, Ramig LO. Enhanced classical dysphonia measures and sparse regression for telemonitoring of Parkinson\u2019s disease progression. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, 2010. 594\u20137. https:\/\/doi.org\/10.1109\/icassp.2010.5495554","DOI":"10.1109\/ICASSP.2010.5495554"},{"issue":"7","key":"pone.0343191.ref012","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1002\/mds.25903","article-title":"The past, present, and future of telemedicine for Parkinson\u2019s disease","volume":"29","author":"M Achey","year":"2014","journal-title":"Mov Disord"},{"key":"pone.0343191.ref013","doi-asserted-by":"crossref","first-page":"1415970","DOI":"10.3389\/fneur.2024.1415970","article-title":"Paradigm shift in Parkinson\u2019s disease: using continuous telemonitoring to improve symptoms control. Results from a 2-years journey","volume":"15","author":"S Konitsiotis","year":"2024","journal-title":"Front Neurol"},{"key":"pone.0343191.ref014","doi-asserted-by":"crossref","first-page":"166370","DOI":"10.1109\/ACCESS.2021.3135626","article-title":"Speech Impairment in Parkinson\u2019s Disease: Acoustic Analysis of Unvoiced Consonants in Italian Native Speakers","volume":"9","author":"F Amato","year":"2021","journal-title":"IEEE Access"},{"key":"pone.0343191.ref015","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.patrec.2019.04.005","article-title":"Detecting Parkinson\u2019s disease with sustained phonation and speech signals using machine learning techniques","volume":"125","author":"JS Almeida","year":"2019","journal-title":"Pattern Recognition Letters"},{"key":"pone.0343191.ref016","doi-asserted-by":"crossref","first-page":"831428","DOI":"10.3389\/fneur.2022.831428","article-title":"Voice in Parkinson\u2019s Disease: A Machine Learning Study","volume":"13","author":"A Suppa","year":"2022","journal-title":"Front Neurol"},{"key":"pone.0343191.ref017","first-page":"5201","article-title":"Predicting severity of Parkinson\u2019s disease from speech","volume":"2010","author":"M Asgari","year":"2010","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"issue":"1","key":"pone.0343191.ref018","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1016\/j.csl.2013.12.001","article-title":"Fully Automated Assessment of the Severity of Parkinson\u2019s Disease from Speech","volume":"29","author":"A Bayestehtashk","year":"2015","journal-title":"Comput Speech Lang"},{"issue":"2","key":"pone.0343191.ref019","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1002\/mds.30056","article-title":"Digital Outcomes as Biomarkers of Disease Progression in Early Parkinson\u2019s Disease: A Systematic Review","volume":"40","author":"P R\u00e1bano-Su\u00e1rez","year":"2025","journal-title":"Mov Disord"},{"issue":"8","key":"pone.0343191.ref020","doi-asserted-by":"crossref","DOI":"10.2196\/37100","article-title":"Telehealth for the Longitudinal Management of Chronic Conditions: Systematic Review","volume":"24","author":"AA Lewinski","year":"2022","journal-title":"J Med Internet Res"},{"issue":"6","key":"pone.0343191.ref021","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1007\/s00702-023-02635-4","article-title":"The heterogeneity of Parkinson\u2019s disease","volume":"130","author":"U W\u00fcllner","year":"2023","journal-title":"J Neural Transm (Vienna)"},{"issue":"3","key":"pone.0343191.ref022","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1111\/ejn.14094","article-title":"The clinical heterogeneity of Parkinson\u2019s disease and its therapeutic implications","volume":"49","author":"JC Greenland","year":"2019","journal-title":"Eur J Neurosci"},{"issue":"3","key":"pone.0343191.ref023","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1155\/1999\/327643","article-title":"Speech impairment in a large sample of patients with Parkinson\u2019s disease","volume":"11","author":"AK Ho","year":"1999","journal-title":"Behav Neurol"},{"key":"pone.0343191.ref024","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.bandl.2018.08.002","article-title":"Communication impairment in Parkinson\u2019s disease: Impact of motor and cognitive symptoms on speech and language","volume":"185","author":"KM Smith","year":"2018","journal-title":"Brain Lang"},{"issue":"10","key":"pone.0343191.ref025","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0185613","article-title":"Detecting Parkinson\u2019s disease from sustained phonation and speech signals","volume":"12","author":"E Vaiciukynas","year":"2017","journal-title":"PLoS One"},{"issue":"6","key":"pone.0343191.ref026","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1007\/s12559-017-9497-x","article-title":"Parkinson\u2019s Disease and Aging: Analysis of Their Effect in Phonation and Articulation of Speech","volume":"9","author":"T Arias-Vergara","year":"2017","journal-title":"Cogn Comput"},{"key":"pone.0343191.ref027","doi-asserted-by":"crossref","unstructured":"Little M, McSharry P, Roberts S, Costello D, Moroz I. Exploiting Nonlinear Recurrence and Fractal Scaling Properties for Voice Disorder Detection. Nat Prec. 2007. https:\/\/doi.org\/10.1038\/npre.2007.326.1","DOI":"10.1038\/npre.2007.326.1"},{"issue":"1","key":"pone.0343191.ref028","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1186\/s40708-020-00113-1","article-title":"Telemonitoring Parkinson\u2019s disease using machine learning by combining tremor and voice analysis","volume":"7","author":"MSR Sajal","year":"2020","journal-title":"Brain Inform"},{"key":"pone.0343191.ref029","first-page":"3801","article-title":"Speech features for telemonitoring of Parkinson\u2019s disease symptoms","volume":"2017","author":"H Ramezani","year":"2017","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"pone.0343191.ref030","doi-asserted-by":"crossref","first-page":"109565","DOI":"10.1016\/j.compbiomed.2024.109565","article-title":"A pilot study for speech assessment to detect the severity of Parkinson\u2019s disease: An ensemble approach","volume":"185","author":"GC Oliveira","year":"2025","journal-title":"Comput Biol Med"},{"key":"pone.0343191.ref031","doi-asserted-by":"crossref","first-page":"188243","DOI":"10.1109\/ACCESS.2020.3031646","article-title":"MonParLoc: A Speech-Based System for Parkinson\u2019s Disease Analysis and Monitoring","volume":"8","author":"D Palacios-Alonso","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0343191.ref032","volume-title":"Parkinsons Telemonitoring","author":"A Tsanas","year":"2009"},{"issue":"11","key":"pone.0343191.ref033","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1002\/gps.1015","article-title":"A longitudinal study of neuropsychological change in individuals with Parkinson\u2019s disease","volume":"18","author":"T Azuma","year":"2003","journal-title":"Int J Geriatr Psychiatry"},{"issue":"2","key":"pone.0343191.ref034","doi-asserted-by":"crossref","first-page":"906","DOI":"10.21037\/qims-21-425","article-title":"Longitudinal clustering analysis and prediction of Parkinson\u2019s disease progression using radiomics and hybrid machine learning","volume":"12","author":"MR Salmanpour","year":"2022","journal-title":"Quant Imaging Med Surg"},{"key":"pone.0343191.ref035","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/978-1-0716-0826-5_2","article-title":"Machine Learning for Biomedical Time Series Classification: From Shapelets to Deep Learning","volume":"2190","author":"C Bock","year":"2021","journal-title":"Methods Mol Biol"},{"issue":"5","key":"pone.0343191.ref036","doi-asserted-by":"crossref","first-page":"5523","DOI":"10.1016\/j.eswa.2011.11.067","article-title":"A comparison of regression methods for remote tracking of Parkinson\u2019s disease progression","volume":"39","author":"\u00d6 Eskidere","year":"2012","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"pone.0343191.ref037","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1109\/TASE.2018.2874233","article-title":"A Novel Positive Transfer Learning Approach for Telemonitoring of Parkinson\u2019s Disease","volume":"16","author":"H Yoon","year":"2019","journal-title":"IEEE Trans Automat Sci Eng"},{"issue":"1","key":"pone.0343191.ref038","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1038\/s41746-022-00568-y","article-title":"Co-evolution of machine learning and digital technologies to improve monitoring of Parkinson\u2019s disease motor symptoms","volume":"5","author":"AS Chandrabhatla","year":"2022","journal-title":"NPJ Digit Med"},{"key":"pone.0343191.ref039","first-page":"28","article-title":"Noninvasive biomarkers of neurobehavioral performance","volume":"24","author":"TF Quatieri","year":"2020","journal-title":"Linc Lab J"},{"key":"pone.0343191.ref040","doi-asserted-by":"crossref","first-page":"108210","DOI":"10.1016\/j.ymssp.2021.108210","article-title":"From inference to design: A comprehensive framework for uncertainty quantification in engineering with limited information","volume":"165","author":"A Gray","year":"2022","journal-title":"Mechanical Systems and Signal Processing"},{"issue":"4","key":"pone.0343191.ref041","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1002\/mds.22379","article-title":"Testing objective measures of motor impairment in early Parkinson\u2019s disease: Feasibility study of an at-home testing device","volume":"24","author":"CG Goetz","year":"2009","journal-title":"Mov Disord"},{"issue":"7","key":"pone.0343191.ref042","doi-asserted-by":"crossref","first-page":"3797","DOI":"10.1109\/TIT.2014.2320500","article-title":"R\u00e9nyi Divergence and Kullback-Leibler Divergence","volume":"60","author":"T van Erven","year":"2014","journal-title":"IEEE Trans Inform Theory"},{"key":"pone.0343191.ref043","unstructured":"Shahriar K. Lightweight Resolution-Aware Audio Deepfake Detection via Cross-Scale Attention and Consistency Learning. arXiv preprint arXiv:260106560. 2026."},{"issue":"2","key":"pone.0343191.ref044","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1177\/1740774515602688","article-title":"Fallacies of last observation carried forward analyses","volume":"13","author":"JM Lachin","year":"2016","journal-title":"Clin Trials"},{"issue":"2","key":"pone.0343191.ref045","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1109\/TITS.2011.2106209","article-title":"Prediction Intervals to Account for Uncertainties in Travel Time Prediction","volume":"12","author":"A Khosravi","year":"2011","journal-title":"IEEE Trans Intell Transport Syst"},{"key":"pone.0343191.ref046","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1016\/j.measurement.2019.01.014","article-title":"An analytical method for measuring the Parkinson\u2019s disease progression: A case on a Parkinson\u2019s telemonitoring dataset","volume":"136","author":"M Nilashi","year":"2019","journal-title":"Measurement"},{"key":"pone.0343191.ref047","doi-asserted-by":"crossref","unstructured":"Mohammadi P, Hatamlou A, Masdari M. A comparative study on remote tracking of Parkinsons disease progression using data mining methods. arXiv preprint arXiv:13122140. 2013.","DOI":"10.5121\/ijfcst.2013.3607"},{"key":"pone.0343191.ref048","unstructured":"Tang Z, Hou C, Zhang T, Tian B, Wang J, Lv H. Enhancing Noise Robustness of Parkinson\u2019s Disease Telemonitoring via Contrastive Feature Augmentation. arXiv preprint arXiv:251001588. 2025."},{"issue":"9","key":"pone.0343191.ref049","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1016\/S0895-4356(03)00207-5","article-title":"External validation is necessary in prediction research: a clinical example","volume":"56","author":"SE Bleeker","year":"2003","journal-title":"J Clin Epidemiol"},{"issue":"12","key":"pone.0343191.ref050","doi-asserted-by":"crossref","first-page":"5394","DOI":"10.1109\/TCAD.2022.3162182","article-title":"Personalized Neural Network for Patient-Specific Health Monitoring in IoT: A Metalearning Approach","volume":"41","author":"Z Jia","year":"2022","journal-title":"IEEE Trans Comput-Aided Des Integr Circuits Syst"},{"key":"pone.0343191.ref051","doi-asserted-by":"crossref","unstructured":"Yang Y, Sun Z-Q, Zhu H, Fu Y, Zhou Y, Xiong H, et al. Learning Adaptive Embedding Considering Incremental Class. IEEE Trans Knowl Data Eng. 2021;:1\u20131. https:\/\/doi.org\/10.1109\/tkde.2021.3109131","DOI":"10.1109\/TKDE.2021.3109131"},{"issue":"9","key":"pone.0343191.ref052","doi-asserted-by":"crossref","first-page":"1020","DOI":"10.1002\/mds.20213","article-title":"Movement Disorder Society Task Force report on the Hoehn and Yahr staging scale: status and recommendations the Movement Disorder Society Task Force on rating scales for Parkinson\u2019s disease","volume":"19","author":"CG Goetz","year":"2004","journal-title":"Movement disorders"},{"key":"pone.0343191.ref053","unstructured":"Tang S, Modi A, Sjoding M, Wiens J. Clinician-in-the-loop decision making: Reinforcement learning with near-optimal set-valued policies. In: International Conference on Machine Learning. PMLR. 2020. 9387\u201396."},{"key":"pone.0343191.ref054","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.artmed.2017.03.005","article-title":"Updating Markov models to integrate cross-sectional and longitudinal studies","volume":"77","author":"A Tucker","year":"2017","journal-title":"Artif Intell Med"},{"issue":"1","key":"pone.0343191.ref055","doi-asserted-by":"crossref","DOI":"10.2196\/resprot.4044","article-title":"Web-based telemonitoring and delivery of caregiver support for patients with Parkinson disease after deep brain stimulation: protocol","volume":"4","author":"S Marceglia","year":"2015","journal-title":"JMIR Res Protoc"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0343191","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T17:35:32Z","timestamp":1785951332000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0343191"}},"subtitle":[],"editor":[{"given":"Thiago P.","family":"Fernandes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":55,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0343191","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]}}}