{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:58:46Z","timestamp":1781816326523,"version":"3.54.5"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"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. Physiol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Hypokinetic dysarthria in Parkinson\u2019s disease provides an accessible non-invasive biomarker, but multi-class severity grading remains difficult because of overlapping acoustic patterns and limited long-range temporal modeling in existing approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a hybrid CNN-Mamba framework using multimodal speech features transformed into 2D representations. The model was trained and validated on speaker-disjoint PC-GITA Spanish data and tested on an independent Mandarin clinical cohort, with additional external evaluation on a public Parkinsonian speech corpus. Speaker-level results were obtained by aggregating segment predictions within each subject.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Segment-level accuracy reached 97.8% on PC-GITA and 95.4% on the Mandarin cohort. Speaker-level accuracy reached 94.0% and 91.2% using majority voting, improving to 94.8% and 91.9% with mean-probability aggregation. SHAP analysis supported physiological interpretability, and ablation studies showed advantages over CNN-BiLSTM, Transformer, and SVM baselines.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The proposed CNN-Mamba framework provides an interpretable, computationally efficient, and non-invasive approach for Parkinson\u2019s disease severity assessment and remote monitoring, with promising cross-lingual transfer under structured clinical speech tasks.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphys.2026.1806415","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T04:17:37Z","timestamp":1779077857000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Physiological classification of Parkinson\u2019s disease severity using multimodal speech biomarkers with a hybrid CNN-Mamba framework"],"prefix":"10.3389","volume":"17","author":[{"given":"Taisheng","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Mathematics and Computer Science, Quanzhou Normal University","place":["Quanzhou, China"]},{"name":"Fujian Provincial Key Laboratory of Data-Intensive Computing, Quanzhou Normal University","place":["Quanzhou, China"]},{"name":"Key Laboratory of Intelligent Computing and Information Processing (Quanzhou Normal University), Fujian Province University","place":["Quanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuguang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Quanzhou Normal University","place":["Quanzhou, China"]},{"name":"Fujian Provincial Key Laboratory of Data-Intensive Computing, Quanzhou Normal University","place":["Quanzhou, China"]},{"name":"Key Laboratory of Intelligent Computing and Information Processing (Quanzhou Normal University), Fujian Province University","place":["Quanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunyi","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Information Technology, The Education University of Hong Kong","place":["Hong Kong, Hong Kong SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianshe","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology, Huaqiao University Affiliated Strait Hospital","place":["Quanzhou, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology, Huaqiao University Affiliated Strait Hospital","place":["Quanzhou, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bijiao","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Information Technology, The Education University of Hong Kong","place":["Hong Kong, Hong Kong SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kavimbi","family":"Chipusu","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Division of Biomedical Engineering, University of Saskatchewan","place":["Saskatoon, SK, Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianlong","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Science, Quanzhou Normal University","place":["Quanzhou, China"]},{"name":"Fujian Provincial Key Laboratory of Data-Intensive Computing, Quanzhou Normal University","place":["Quanzhou, China"]},{"name":"Key Laboratory of Intelligent Computing and Information Processing (Quanzhou Normal University), Fujian Province University","place":["Quanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering12111279","article-title":"Voice-based detection of Parkinson's disease using machine and deep learning approaches: a systematic review","volume":"12","author":"Alaskar","year":"2025","journal-title":"Bioengineering (Basel)"},{"key":"B2","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1001\/jama.2019.22360","article-title":"Diagnosis and treatment of Parkinson disease: a review","volume":"323","author":"Armstrong","year":"2020","journal-title":"JAMA"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2023.102295","article-title":"HViT: hybrid vision inspired transformer for the assessment of carotid artery plaque by addressing the cross-modality domain adaptation problem in MRI","volume":"109","author":"Ayoub","year":"2023","journal-title":"Comput. Med. Imaging Graphics"},{"key":"B1","doi-asserted-by":"publisher","first-page":"2284","DOI":"10.1016\/S0140-6736(21)00218-X","article-title":"Parkinson's disease","volume":"397","author":"Bloem","year":"2021","journal-title":"Lancet"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1038\/s41531-025-00913-4","article-title":"Speech and language biomarkers for Parkinson's disease prediction, early diagnosis and progression","volume":"11","author":"Cao","year":"2025","journal-title":"NPJ Parkinsons Dis"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.107041","article-title":"Classification of myocardial fibrosis in DE-MRI based on semi-supervised semantic segmentation and dual attention mechanism","volume":"225","author":"Ding","year":"2022","journal-title":"Comput. Methods Programs Biomed."},{"key":"B3","doi-asserted-by":"publisher","first-page":"S3","DOI":"10.3233\/JPD-181474","article-title":"The emerging evidence of the Parkinson pandemic","volume":"8","author":"Dorsey","year":"2018","journal-title":"J Parkinsons Dis"},{"key":"B16","doi-asserted-by":"publisher","first-page":"2975","DOI":"10.1109\/LSP.2024.3483009","article-title":"Audio Mamba: bidirectional state space model for audio representation learning","volume":"31","author":"Erol","year":"2024","journal-title":"IEEE Signal Process Lett"},{"key":"B17","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2022"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.00752","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv"},{"key":"B8","doi-asserted-by":"publisher","first-page":"163","DOI":"10.14744\/SEMB.2023.29560","article-title":"Hypokinetic dysarthria in Parkinson's disease: a narrative review","volume":"57","author":"Sapmaz Atalar","year":"2023","journal-title":"Med Bull Sisli Etfal Hosp"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3389\/fnetp.2025.1680069","article-title":"Early parasympathetic dysfunction in Parkinson's disease: insights from information-theoretic analysis","volume":"5","author":"Krohova","year":"2025","journal-title":"Front Netw Physiol"},{"key":"B34","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.inffus.2019.06.020","article-title":"Adjusting forwarder nodes and duty cycle using packet aggregation routing for body sensor networks","volume":"53","author":"Liu","year":"2020","journal-title":"Inf. Fusion"},{"key":"B22","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1016\/j.bbe.2022.06.007","article-title":"Diagnosis of Parkinson's disease based on SHAP value feature selection","volume":"42","author":"Liu","year":"2022","journal-title":"Biocybern Biomed Eng"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2023.1124232","article-title":"Identifying key multi-modal predictors of incipient dementia in Parkinson's disease: a machine learning analysis and TreeSHAP interpretation","volume":"15","author":"McFall","year":"2023","journal-title":"Front Aging Neurosci"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1908.08681","article-title":"Mish: a self regularized non-monotonic activation function","author":"Misra","year":"2019","journal-title":"arXiv"},{"key":"B19","doi-asserted-by":"crossref","DOI":"10.63317\/3c643i6hcfzo","article-title":"New Spanish speech corpus database for the analysis of people suffering from Parkinson's disease","author":"Orozco-Arroyave","year":"2014"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-13865-z","article-title":"Phonemes based detection of Parkinson's disease for telehealth applications","volume":"12","author":"Pah","year":"2022","journal-title":"Sci Rep"},{"key":"B21","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1111\/ene.15099","article-title":"Automated speech analysis in early untreated Parkinson's disease: relation to gender and dopaminergic transporter imaging","volume":"29","author":"Rusz","year":"2022","journal-title":"Eur J Neurol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2024.105922","article-title":"From prodromal stages to clinical trials: the promise of digital speech biomarkers in Parkinson's disease","volume":"167","author":"Rusz","year":"2024","journal-title":"Neurosci Biobehav Rev"},{"key":"B26","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1002\/mds.28465","article-title":"Guidelines for speech recording and acoustic analyses in dysarthrias of movement disorders","volume":"36","author":"Rusz","year":"2021","journal-title":"Mov. Disord."},{"key":"B6","doi-asserted-by":"publisher","first-page":"163","DOI":"10.14744\/SEMB.2023.29560","article-title":"Hypokinetic dysarthria in Parkinson's disease: a narrative review","volume":"57","author":"Sapmaz Atalar","year":"2023","journal-title":"Med Bull Sisli Etfal Hosp"},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1109\/SLT61566.2024.10832304","article-title":"SSAMBA: self-supervised audio representation learning with Mamba state space model","author":"Shams","year":"2024"},{"key":"B31","doi-asserted-by":"publisher","first-page":"6007","DOI":"10.1109\/JSEN.2025.3650493","article-title":"An improved variational autoencoder and graph attention network method for wear prediction of aerospace self-lubricating bearing using acoustic emission signal","volume":"26","author":"Shen","year":"2026","journal-title":"IEEE Sens. J."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2024-080952","article-title":"Projections for prevalence of Parkinson's disease and its driving factors in 195 countries and territories to 2050: modelling study","volume":"388","author":"Su","year":"2025","journal-title":"BMJ"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.3390\/app14177873","article-title":"Innovative speech-based deep learning approaches for Parkinson's disease classification: a systematic review","volume":"14","author":"van Gelderen","year":"2024","journal-title":"Appl Sci"},{"key":"B32","doi-asserted-by":"publisher","first-page":"6007","DOI":"10.1109\/JSEN.2025.3520098","article-title":"An improved variational autoencoder and graph attention network method for wear prediction of aerospace self-lubricating bearing using acoustic emission signal","volume":"26","author":"Shen","year":"2026","journal-title":"IEEE Sens J"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107677","article-title":"The synergy of cybernetical intelligence with medical image analysis for deep medicine: a methodological perspective","volume":"240","author":"Wong","year":"2023","journal-title":"Comput Methods Programs Biomed"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107602","article-title":"Brain image segmentation of the corpus callosum by combining bi-directional convolutional LSTM and U-Net using multi-slice CT and MRI","volume":"238","author":"Wong","year":"2023","journal-title":"Comput Methods Programs Biomed"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2023.1151421","article-title":"Functional magnetic resonance imaging providing the brain effect mechanism of acupuncture and moxibustion treatment for depression","volume":"14","author":"Wong","year":"2023","journal-title":"Front Neurol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2025.1737585","article-title":"Advancing Parkinson\u2019s disease detection through multi-dimensional machine learning: a comprehensive framework using wearable movement sensor analytics","volume":"16","author":"Xiang","year":"2025","journal-title":"Front. Physiol."},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.107055","article-title":"Unsupervised domain adaptive myocardial infarction MRI classification diagnostics model based on target domain confused sample resampling","volume":"226","author":"Xie","year":"2022","journal-title":"Comput. Methods Programs Biomed."},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2025.1586273","article-title":"Non-invasive detection of Parkinson's disease based on speech analysis and interpretable machine learning","volume":"17","author":"Xu","year":"2025","journal-title":"Front Aging Neurosci"},{"key":"B14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2024-1274","article-title":"Audio Mamba: selective state spaces for self-supervised audio representations","author":"Yadav","year":"2024"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1933","DOI":"10.1109\/TASLPRO.2025.3566210","article-title":"Mamba in speech: towards an alternative to self-attention","volume":"33","author":"Zhang","year":"2025","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"B35","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.mri.2021.10.033","article-title":"A generative adversarial network technique for high-quality super-resolution reconstruction of cardiac magnetic resonance images","volume":"85","author":"Zhao","year":"2022","journal-title":"Magn. Reson. Imaging"},{"key":"B33","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/j.jmsy.2025.09.015","article-title":"Flexible pallet automation system scheduling with limited fixture-pallets and material-pallets: a case study from an engine manufacturing enterprise","volume":"83","author":"Zhou","year":"2025","journal-title":"J. Manuf. Syst."},{"key":"B30","doi-asserted-by":"publisher","first-page":"2868","DOI":"10.1109\/TSMC.2026.3655483","article-title":"Multiresource-constrained flexible job shop scheduling with fixture pallets and setup stations under pallet automation systems","volume":"56","author":"Zhou","year":"2026","journal-title":"IEEE Trans Syst Man Cybern Syst"}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1806415\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T04:17:42Z","timestamp":1779077862000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1806415\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":38,"alternative-id":["10.3389\/fphys.2026.1806415"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2026.1806415","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]},"article-number":"1806415"}}