{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:16:36Z","timestamp":1790748996876,"version":"4.1.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T00:00:00Z","timestamp":1735516800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T00:00:00Z","timestamp":1735516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["112-2221-E-002 -188 -MY3"],"award-info":[{"award-number":["112-2221-E-002 -188 -MY3"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"publisher","award":["RS-2023-00265517"],"award-info":[{"award-number":["RS-2023-00265517"]}],"id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004332","name":"Seoul National University Hospital","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004332","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Neural Transm"],"published-print":{"date-parts":[[2025,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Speech change is a biometric marker for Parkinson\u2019s disease (PD). However, evaluating speech variability across diverse languages is challenging. We aimed to develop a cross-language algorithm differentiating between PD patients and healthy controls using a Taiwanese and Korean speech data set. We recruited 299 healthy controls and 347 patients with PD from Taiwan and Korea. Participants with PD underwent smartphone-based speech recordings during the \u201con\u201d phase. Each Korean participant performed various speech texts, while the Taiwanese participant read a standardized, fixed-length article. Korean short-speech (\u226615 syllables) and long-speech (&gt;\u200915 syllables) recordings were combined with the Taiwanese speech dataset. The merged dataset was split into a training set (controls vs. early-stage PD) and a validation set (controls vs. advanced-stage PD) to evaluate the model's effectiveness in differentiating PD patients from controls across languages based on speech length. Numerous acoustic and linguistic speech features were extracted and combined with machine learning algorithms to distinguish PD patients from controls. The area under the receiver operating characteristic (AUROC) curve was calculated to assess diagnostic performance. Random forest and AdaBoost classifiers showed an AUROC 0.82 for distinguishing patients with early-stage PD from controls. In the validation cohort, the random forest algorithm maintained this value (0.90) for discriminating advanced-stage PD patients. The model showed superior performance in the combined language cohort (AUROC 0.90) than either the Korean (AUROC 0.87) or Taiwanese (AUROC 0.88) cohorts individually. However, with another merged speech data set of short-speech recordings\u2009&lt;\u200925 characters, the diagnostic performance to identify early-stage PD patients from controls dropped to 0.72 and showed a further limited ability to discriminate advanced-stage patients. Leveraging multifaceted speech features, including both acoustic and linguistic characteristics, could aid in distinguishing PD patients from healthy individuals, even across different languages.<\/jats:p>","DOI":"10.1007\/s00702-024-02874-z","type":"journal-article","created":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T03:30:51Z","timestamp":1735529451000},"page":"579-590","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["A cross-language speech model for detection of Parkinson\u2019s disease"],"prefix":"10.1007","volume":"132","author":[{"given":"Wee Shin","family":"Lim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu-I","family":"Chiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei-Ling","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jyh-Shing Roger","family":"Jang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sol-Hee","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chin-Hsien","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8219-9663","authenticated-orcid":false,"given":"Han-Joon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,30]]},"reference":[{"issue":"1","key":"2874_CR1","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1038\/s41531-023-00494-0","volume":"9","author":"H Alfalahi","year":"2023","unstructured":"Alfalahi H, Dias SB, Khandoker AH, Chaudhuri KR, Hadjileontiadis LJ (2023) A scoping review of neurodegenerative manifestations in explainable digital phenotyping. NPJ Parkinsons Dis 9(1):49","journal-title":"NPJ Parkinsons Dis"},{"issue":"6","key":"2874_CR2","doi-asserted-by":"publisher","first-page":"766.e761","DOI":"10.1016\/j.jvoice.2015.10.014","volume":"30","author":"A Bandini","year":"2016","unstructured":"Bandini A, Orlandi S, Giovannelli F et al (2016) Markerless analysis of articulatory movements in patients with Parkinson\u2019s disease. J Voice 30(6):766.e761-766.e711","journal-title":"J Voice"},{"key":"2874_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2023.10.018","author":"E Barrientos","year":"2023","unstructured":"Barrientos E, Cataldo E (2023) Estimating formant frequencies of vowels sung by Sopranos using weighted linear prediction. J Voice. https:\/\/doi.org\/10.1016\/j.jvoice.2023.10.018","journal-title":"J Voice"},{"key":"2874_CR4","doi-asserted-by":"publisher","first-page":"1386608","DOI":"10.3389\/fneur.2024.1386608","volume":"15","author":"R Bhidayasiri","year":"2024","unstructured":"Bhidayasiri R, Sringean J, Phumphid S et al (2024) The rise of Parkinson\u2019s disease is a global challenge, but efforts to tackle this must begin at a national level: a protocol for national digital screening and \u201ceat, move, sleep\u201d lifestyle interventions to prevent or slow the rise of non-communicable diseases in Thailand. Front Neurol 15:1386608","journal-title":"Front Neurol"},{"key":"2874_CR5","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45:5\u201332","journal-title":"Mach Learn"},{"key":"2874_CR6","unstructured":"Buitinck L, Louppe G, Blondel M et al (2013) API design for machine learning software: experiences from the scikit-learn project. arXiv preprint arXiv:13090238"},{"key":"2874_CR7","doi-asserted-by":"publisher","first-page":"1142642","DOI":"10.3389\/fneur.2023.1142642","volume":"14","author":"A Favaro","year":"2023","unstructured":"Favaro A, Moro-Vel\u00e1zquez L, Butala A et al (2023) Multilingual evaluation of interpretable biomarkers to represent language and speech patterns in Parkinson\u2019s disease. Front Neurol 14:1142642","journal-title":"Front Neurol"},{"issue":"1","key":"2874_CR8","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1006\/jcss.1997.1504","volume":"55","author":"Y Freund","year":"1997","unstructured":"Freund Y, Schapire RE (1997) A desicion-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119\u2013139","journal-title":"J Comput Syst Sci"},{"key":"2874_CR9","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/j.cmpb.2015.12.011","volume":"127","author":"Z Galaz","year":"2016","unstructured":"Galaz Z, Mekyska J, Mzourek Z et al (2016) Prosodic analysis of neutral, stress-modified and rhymed speech in patients with Parkinson\u2019s disease. Comput Methods Programs Biomed 127:301\u2013317","journal-title":"Comput Methods Programs Biomed"},{"key":"2874_CR10","unstructured":"Google (2023a) Google Cloud Speech API - Speech-to-Text Solution. 2023: https:\/\/cloud.google.com\/speech-to-text\/docshttps:\/\/cloud.google.com\/speech-to-text\/docs"},{"key":"2874_CR11","unstructured":"Google (2023b) Google Cloud Speech API - Speech-to-Text Supported Languages. 2023:https:\/\/cloud.google.com\/speech-to-text\/docs\/speech-to-text-supported-languages."},{"issue":"3","key":"2874_CR12","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1155\/1999\/327643","volume":"11","author":"AK Ho","year":"1998","unstructured":"Ho AK, Iansek R, Marigliani C, Bradshaw JL, Gates S (1998) Speech impairment in a large sample of patients with Parkinson\u2019s disease. Behav Neurol 11(3):131\u2013137","journal-title":"Behav Neurol"},{"issue":"3","key":"2874_CR13","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1136\/jnnp.55.3.181","volume":"55","author":"AJ Hughes","year":"1992","unstructured":"Hughes AJ, Daniel SE, Kilford L, Lees AJ (1992) Accuracy of clinical diagnosis of idiopathic Parkinson\u2019s disease: a clinico-pathological study of 100 cases. J Neurol Neurosurg Psychiatry 55(3):181\u2013184","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"2874_CR14","doi-asserted-by":"publisher","DOI":"10.2196\/46105","volume":"25","author":"A Idrisoglu","year":"2023","unstructured":"Idrisoglu A, Dallora AL, Anderberg P, Berglund JS (2023) Applied machine learning techniques to diagnose voice-affecting conditions and disorders: systematic literature review. J Med Internet Res 25:e46105","journal-title":"J Med Internet Res"},{"key":"2874_CR15","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.parkreldis.2022.01.003","volume":"95","author":"L Jeancolas","year":"2022","unstructured":"Jeancolas L, Mangone G, Petrovska-Delacr\u00e9taz D et al (2022) Voice characteristics from isolated rapid eye movement sleep behavior disorder to early Parkinson\u2019s disease. Parkinsonism Relat Disord 95:86\u201391","journal-title":"Parkinsonism Relat Disord"},{"key":"2874_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109078","volume":"182","author":"SM Jeong","year":"2024","unstructured":"Jeong SM, Song YD, Seok CL et al (2024) Machine learning-based classification of Parkinson\u2019s disease using acoustic features: insights from multilingual speech tasks. Comput Biol Med 182:109078","journal-title":"Comput Biol Med"},{"issue":"5","key":"2874_CR17","doi-asserted-by":"publisher","first-page":"1573","DOI":"10.1109\/TBME.2021.3116935","volume":"69","author":"C Laganas","year":"2021","unstructured":"Laganas C, Iakovakis D, Hadjidimitriou S et al (2021) Parkinson\u2019s disease detection based on running speech data from phone calls. IEEE Trans Biomed Eng 69(5):1573\u20131584","journal-title":"IEEE Trans Biomed Eng"},{"issue":"1","key":"2874_CR18","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1038\/s41531-022-00414-8","volume":"8","author":"WS Lim","year":"2022","unstructured":"Lim WS, Chiu S-I, Wu M-C et al (2022) An integrated biometric voice and facial features for early detection of Parkinson\u2019s disease. NPJ Parkinsons Dis 8(1):145","journal-title":"NPJ Parkinsons Dis"},{"issue":"6","key":"2874_CR19","doi-asserted-by":"publisher","first-page":"765.e761","DOI":"10.1016\/j.jvoice.2015.10.012","volume":"30","author":"A Lovato","year":"2016","unstructured":"Lovato A, De Colle W, Giacomelli L et al (2016) Multi-dimensional voice program (MDVP) vs Praat for assessing euphonic subjects: a preliminary study on the gender-discriminating power of acoustic analysis software. J Voice 30(6):765.e761-765.e765","journal-title":"J Voice"},{"key":"2874_CR20","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/s11517-016-1512-y","volume":"55","author":"L Naranjo","year":"2017","unstructured":"Naranjo L, P\u00e9rez CJ, Mart\u00edn J (2017) Addressing voice recording replications for tracking Parkinson\u2019s disease progression. Med Biol Eng Comput 55:365\u2013373","journal-title":"Med Biol Eng Comput"},{"issue":"1","key":"2874_CR21","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1121\/1.4939739","volume":"139","author":"JR Orozco-Arroyave","year":"2016","unstructured":"Orozco-Arroyave JR, H\u00f6nig F, Arias-Londo\u00f1o J et al (2016) Automatic detection of Parkinson\u2019s disease in running speech spoken in three different languages. J Acoust Soc Am 139(1):481\u2013500","journal-title":"J Acoust Soc Am"},{"issue":"5","key":"2874_CR22","doi-asserted-by":"publisher","DOI":"10.1590\/2317-1782\/20182017200","volume":"30","author":"P Pinho","year":"2018","unstructured":"Pinho P, Monteiro L, Soares MFP, Tourinho L, Melo A, N\u00f3brega AC (2018) Impact of levodopa treatment in the voice pattern of Parkinson\u2019s disease patients: a systematic review and meta-analysis. Codas 30(5):e20170200","journal-title":"Codas"},{"key":"2874_CR23","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/B978-0-12-815739-8.00006-7","volume-title":"Machine learning","author":"DA Pisner","year":"2020","unstructured":"Pisner DA, Schnyer DM (2020) Support vector machine. Machine learning. Elsevier, pp 101\u2013121"},{"issue":"1","key":"2874_CR24","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1038\/s41531-021-00243-1","volume":"7","author":"J Rusz","year":"2021","unstructured":"Rusz J, Tykalov\u00e1 T, Novotn\u00fd M, R\u016f\u017ei\u010dka E, Du\u0161ek P (2021) Distinct patterns of speech disorder in early-onset and late-onset de-novo Parkinson\u2019s disease. NPJ Parkinsons Dis 7(1):98","journal-title":"NPJ Parkinsons Dis"},{"key":"2874_CR25","volume":"2013","author":"S Skodda","year":"2013","unstructured":"Skodda S, Gr\u00f6nheit W, Mancinelli N, Schlegel U (2013) Progression of voice and speech impairment in the course of Parkinson\u2019s disease: a longitudinal study. Parkinsons Dis 2013:389195","journal-title":"Parkinsons Dis"},{"key":"2874_CR26","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1109\/OJEMB.2022.3151233","volume":"3","author":"S-S Wang","year":"2022","unstructured":"Wang S-S, Wang C-T, Lai C-C, Tsao Y, Fang S-H (2022) Continuous speech for improved learning pathological voice disorders. IEEE Open J Eng Med Biol 3:25\u201333","journal-title":"IEEE Open J Eng Med Biol"},{"issue":"2","key":"2874_CR27","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1121\/10.0013410","volume":"152","author":"DH Whalen","year":"2022","unstructured":"Whalen DH, Chen WR, Shadle CH, Fulop SA (2022) Formants are easy to measure; resonances, not so much: lessons from Klatt (1986). J Acoust Soc Am 152(2):933","journal-title":"J Acoust Soc Am"},{"key":"2874_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.parkreldis.2023.105411","volume":"113","author":"K Yokoi","year":"2023","unstructured":"Yokoi K, Iribe Y, Kitaoka N et al (2023) Analysis of spontaneous speech in Parkinson\u2019s disease by natural language processing. Parkinsonism Relat Disord 113:105411","journal-title":"Parkinsonism Relat Disord"},{"issue":"1","key":"2874_CR29","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1097\/AUD.0000000000000743","volume":"41","author":"Y Zaltz","year":"2020","unstructured":"Zaltz Y, Goldsworthy RL, Eisenberg LS, Kishon-Rabin L (2020) Children with normal hearing are efficient users of fundamental frequency and vocal tract length cues for voice discrimination. Ear Hear 41(1):182\u2013193","journal-title":"Ear Hear"},{"key":"2874_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119650","volume":"219","author":"T Zhang","year":"2023","unstructured":"Zhang T, Lin L, Xue Z (2023) A voice feature extraction method based on fractional attribute topology for Parkinson\u2019s disease detection. Expert Syst Appl 219:119650","journal-title":"Expert Syst Appl"}],"container-title":["Journal of Neural Transmission"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00702-024-02874-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00702-024-02874-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00702-024-02874-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T15:14:21Z","timestamp":1741965261000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00702-024-02874-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,30]]},"references-count":30,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["2874"],"URL":"https:\/\/doi.org\/10.1007\/s00702-024-02874-z","relation":{},"ISSN":["0300-9564","1435-1463"],"issn-type":[{"value":"0300-9564","type":"print"},{"value":"1435-1463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,30]]},"assertion":[{"value":"18 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"HJK received research grants from Seoul National University Hospital, National Information Society Agency, Ministry of Science and ICT, Ministry of Health and Welfare, Samil Pharmaceutical, Emocog, GemVax & KAEL, and Bukwang Pharm Co Ltd; travel grant from International Parkinson and Movement Disorder Society. JH Shin received research grants support from National Research Foundation of Korea,\u00a0Seoul National University Hospital and Seoul National University College of Medicine, Received travel grant from Movement disorder Society and Global Parkinson project. CHL received research grants from National Taiwan University Hospital and National Science and Technology Council. JSR Jang received grants from National Taiwan University and National Science and Technology Council. Other authors have nothing to disclose. The authors report no competing interests related to this study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This research was carried out in accordance with the principles outlined in the Declaration of Helsinki and was approved by the Institutional Review Board (IRB) of\u00a0Seoul National University Hospital\u00a0(IRB number: 2211\u2013079-1378) and National Taiwan University Hospital (201912112RIND). Since this study was retrospective in nature, written consent from the patients was waived.\u00a0We confirm that we have read the Journal\u2019s position on issues involved in ethical publication and affirm that this work is consistent with those guidelines.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}