BACKGROUND AND OBJECTIVES: Patients with synucleinopathies such as multiple system atrophy (MSA) and Parkinson's disease (PD) frequently display speech and language abnormalities. We explore the diagnostic potential of automated linguistic analysis of natural spontaneous speech to differentiate MSA and PD. METHODS: Spontaneous speech of 39 participants with MSA compared to 39 drug-naive PD and 39 healthy controls matched for age and sex was transcribed and linguistically annotated using automatic speech recognition and natural language processing. A quantitative analysis was performed using 6 lexical and syntactic and 2 acoustic features. Results were compared with human-controlled analysis to assess the robustness of the approach. Diagnostic accuracy was evaluated using sensitivity analysis. RESULTS: Despite similar disease duration, linguistic abnormalities were generally more severe in MSA than in PD, leading to high diagnostic accuracy with an area under the curve of 0.81. Compared to controls, MSA showed decreased grammatical component usage, more repetitive phrases, shorter sentences, reduced sentence development, slower articulation rate, and increased duration of pauses, whereas PD had only shorter sentences, reduced sentence development, and longer pauses. Only slower articulation rate was distinctive for MSA while unchanged for PD relative to controls. The highest correlation was found between bulbar/pseudobulbar clinical score and sentence length (r = -0.49, p = 0.002). Despite the relatively high severity of dysarthria in MSA, a strong agreement between manually and automatically computed results was achieved. DISCUSSION: Automated linguistic analysis may offer an objective, cost-effective, and widely applicable biomarker to differentiate synucleinopathies with similar clinical manifestations.

Department of Circuit Theory Faculty of Electrical Engineering Czech Technical University Prague Technická 2 Praha 6 16000 Prague Czech Republic

Department of Neurology and ARTORG Center Inselspital Bern University Hospital University of Bern Bern Switzerland

Department of Neurology and Centre of Clinical Neuroscience 1st Faculty of Medicine Charles University and General University Hospital Prague Czech Republic

See more in PubMed

Fanciulli A, Stankovic I, Krismer F, Seppi K, Levin J, Wenning GK (2019) Multiple system atrophy. Int Rev Neurobiol. 149:137–192. 10.1016/bs.irn.2019.10.004 PubMed

Wenning GK, Litvan I, Tolosa E (2011) Milestones in atypical and secondary Parkinsonisms. Mov Disord. 26(6):1083–1095. 10.1002/mds.23713 PubMed

Meco G, Gasparini M, Doricchi F (1996) Attentional functions in multiple system atrophy and Parkinson’s disease. J Neurol, Neurosurg Psychiat. 60(4):393–398. 10.1136/jnnp.60.4.393 PubMed PMC

Kao AW, Racine CA, Quitania LC, Kramer JH, Christine CW, Miller BL (2009) Cognitive and Neuropsychiatric Profile of the Synucleinopathies: Parkinson’s Disease, Dementia with Lewy Bodies and Multiple System Atrophy. Alzheimer Dis Assoc Disord. 23(4):365–370. 10.1097/WAD.0b013e3181b5065d PubMed PMC

Alario FX, Costa A, Ferreira VS, Pickering MJ (2006) Architectures, representations and processes of language production. Langu Cogn Process. 21(7–8):777–789. 10.1080/016909600824112 PubMed PMC

Santangelo G, Cuoco S, Pellecchia MT, Erro R, Barone P, Picillo M (2018) Comparative cognitive and neuropsychiatric profiles between Parkinson’s disease, multiple system atrophy and progressive supranuclear palsy. J Neurol. 265(11):2602–2613. 10.1007/s00415-018-9038-x PubMed

Cuoco S, Picillo M, Carotenuto I et al (2021) The language profile in multiple system atrophy: an exploratory study. J Neural Transm (Vienna). 128(8):1195–1203. 10.1007/s00702-021-02372-6 PubMed PMC

Catricalà E, Gobbi E, Battista P et al (2017) SAND: a Screening for Aphasia in NeuroDegeneration Development and normative data. Neurol Sci : Off J Ital Neurol Soc Ital Soc Clin Neurophysiol. 10.1007/s10072-017-3001-y PubMed

Gilman S, Wenning GK, Low PA et al (2008) Second consensus statement on the diagnosis of multiple system atrophy. Neurology. 71(9):670–676. 10.1212/01.wnl.0000324625.00404.15 PubMed PMC

Postuma RB, Berg D, Stern M et al (2015) MDS clinical diagnostic criteria for Parkinson’s disease. Mov Disord. 30(12):1591–1601. 10.1002/mds.26424 PubMed

Dusek P, Bezdicek O, Brozová H et al (2020) Clinical characteristics of newly diagnosed Parkinson’s disease patients included in the longitudinal BIO-PD study. Ceska a Slovenska Neurologie a Neurochirurgie. 83(116):633–639. 10.48095/cccsnn2020633

Payan CAM, Viallet F, Landwehrmeyer BG et al (2011) Disease severity and progression in progressive supranuclear palsy and multiple system atrophy: validation of the NNIPPS–Parkinson Plus Scale. PLoS One. 6(8):e22293. 10.1371/journal.pone.0022293 PubMed PMC

Goetz CG, Fahn S, Martinez-Martin P et al (2007) Movement Disorder Society-sponsored revision of the Unified Parkinson’s Disease Rating Scale (MDS-UPDRS): Process, format, and clinimetric testing plan. Mov Disord. 22(1):41–47. 10.1002/mds.21198 PubMed

Bezdicek O, Červenková M, Moore TM et al (2020) Determining a Short Form Montreal Cognitive Assessment (s-MoCA) Czech Version: Validity in Mild Cognitive Impairment Parkinson’s Disease and Cross-Cultural Comparison. Assessment. 27(8):1960–1970. 10.1177/1073191118778896 PubMed PMC

Kopecek M, Stepankova H, Lukavsky J, Ripova D, Nikolai T, Bezdicek O (2017) Montreal cognitive assessment (MoCA): Normative data for old and very old Czech adults. Appl Neuropsychol Adult. 24(1):23–29. 10.1080/23279095.2015.1065261 PubMed

Šubert M, Šimek M, Novotný M et al (2022) Linguistic Abnormalities in Isolated Rapid Eye Movement Sleep Behavior Disorder. Move Dis. 10.1002/mds.29140 PubMed

Subert M, Novotný M, Tykalová T et al (2023) Spoken language alterations can predict phenoconversion in isolated REM sleep behavior disorder: a multicentric study. Ann Neurol. 10.1002/ana.26835 PubMed

Radford A, Kim JW, Xu T, Brockman G, McLeavey C, Sutskever I (2022) Robust speech recognition via large-scale weak supervision. In: Proceedings of the 40th International Conference on Machine Learning (ICML'23), Vol. 202. JMLR.org, Article 1182, pp 28492–28518

Qi P, Zhang Y, Zhang Y, Bolton J, Manning CD. (2020) Stanza: A Python Natural Language Processing Toolkit for Many Human Languages. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. https://nlp.stanford.edu/pubs/qi2020stanza.pdf

Illner V, Tykalová T, Novotný M, Klempíř J, Dušek P, Rusz J (2022) Toward Automated Articulation Rate Analysis via Connected Speech in Dysarthrias. J Speech Lang Hear Res. 65(4):1386–1401. 10.1044/2021_JSLHR-21-00549 PubMed

Hlavnička J, Čmejla R, Tykalová T, Šonka K, Růžička E, Rusz J (2017) Automated analysis of connected speech reveals early biomarkers of Parkinson’s disease in patients with rapid eye movement sleep behaviour disorder. Sci Rep. 7(1):12. 10.1038/s41598-017-00047-5 PubMed PMC

Corver N, van Riemsdijk H (2013) Semi-Lexical Categories: The Function of Content Words and the Content of Function Words. De Gruyter Inc, Berlin

Covington MA, McFall JD (2010) Cutting the Gordian Knot: The Moving-Average Type-Token Ratio (MATTR). J Quant Lingu. 17(2):94–100. 10.1080/09296171003643098

Beltrami D, Gagliardi G, Rossini Favretti R, Ghidoni E, Tamburini F, Calzà L (2018) Speech Analysis by Natural Language Processing Techniques: A Possible Tool for Very Early Detection of Cognitive Decline? Front Aging Neurosci. 10.3389/fnagi.2018.00369 PubMed PMC

de Lira JO, Ortiz KZ, Campanha AC, Bertolucci PHF, Minett TSC (2011) Microlinguistic aspects of the oral narrative in patients with Alzheimer’s disease. Int Psychoger. 23(3):404–412. 10.1017/S1041610210001092 PubMed

Pistono A, Pariente J, Bézy C, Lemesle B, Le Men J, Jucla M (2019) What happens when nothing happens? An investigation of pauses as a compensatory mechanism in early Alzheimer’s disease. Neuropsychologia. 124:133–143. 10.1016/j.neuropsychologia.2018.12.018 PubMed

Vogel AP, Rosen KM, Morgan AT, Reilly S (2014) Comparability of modern recording devices for speech analysis: smartphone, landline, laptop, and hard disc recorder. Folia Phoniatr Logop. 66(6):244–250. 10.1159/000368227 PubMed

Errattahi R, El Hannani A, Ouahmane H (2018) Automatic Speech Recognition Errors Detection and Correction: A Review. Proc Comp Sci. 128:32–37. 10.1016/j.procs.2018.03.005

König A, Satt A, Sorin A, Hoory R, David A, Robert P (2017) Use of Speech Analyses within a Mobile Application for the Assessment of Cognitive Impairment in Elderly People. Curr Alzhe Res. 10.2174/1567205014666170829111942 PubMed

Del Prete E, Tommasini L, Mazzucchi S et al (2021) Connected speech in progressive supranuclear palsy: a possible role in differential diagnosis. Neurol Sci. 42(4):1483–1490. 10.1007/s10072-020-04635-8 PubMed

Parjane N, Cho S, Ash S et al (2021) Digital Speech Analysis in Progressive Supranuclear Palsy and Corticobasal Syndromes. J Alzheimers Dis. 82(1):33–45. 10.3233/JAD-201132 PubMed PMC

Rusz J, Hlavnička J, Novotný M et al (2021) Speech Biomarkers in Rapid Eye Movement Sleep Behavior Disorder and Parkinson Disease. Ann Neurol. 90(1):62–75. 10.1002/ana.26085 PubMed PMC

Qiao Y, Xie XY, Lin GZ et al (2020) Computer-Assisted Speech Analysis in Mild Cognitive Impairment and Alzheimer’s Disease: A Pilot Study from Shanghai. China. J Alzheimers Dis. 75(1):211–221. 10.3233/JAD-191056 PubMed

De Looze C, Kelly F, Crosby L et al (2018) Changes in Speech Chunking in Reading Aloud is a Marker of Mild Cognitive Impairment and Mild-to-Moderate Alzheimer’s Disease. Curr Alzheimer Res. 15(9):828–847. 10.2174/1567205015666180404165017 PubMed

Ash S, McMillan C, Gross RG et al (2012) Impairments of speech fluency in Lewy body spectrum disorder. Brain Lang. 120(3):290–302. 10.1016/j.bandl.2011.09.004 PubMed PMC

Rusz J, Tykalová T, Salerno G, Bancone S, Scarpelli J, Pellecchia MT (2019) Distinctive speech signature in cerebellar and parkinsonian subtypes of multiple system atrophy. J Neurol. 266(6):1394–1404. 10.1007/s00415-019-09271-7 PubMed

Gandor F, Vogel A, Claus I et al (2020) Laryngeal Movement Disorders in Multiple System Atrophy: A Diagnostic Biomarker? Mov Disord. 35(12):2174–2183. 10.1002/mds.28220 PubMed PMC

Daoudi K, Das B, Tykalova T, Klempir J, Rusz J (2022) Speech acoustic indices for differential diagnosis between Parkinson’s disease, multiple system atrophy and progressive supranuclear palsy. NPJ Parkinsons Dis. 8(1):142. 10.1038/s41531-022-00389-6 PubMed PMC

Isozaki E, Hayashi M, Hayashida T, Oda M, Hirai S (1998) Myopathology of the intrinsic laryngeal muscles in neurodegenerative diseases, with reference to the mechanism of vocal cord paralysis. Rinsho Shinkeigaku. 38(8):711–718 PubMed

Illes J, Metter EJ, Hanson WR, Iritani S (1988) Language production in Parkinson’s disease: acoustic and linguistic considerations. Brain Lang. 33(1):146–160. 10.1016/0093-934x(88)90059-4 PubMed

Skodda S (2011) Aspects of speech rate and regularity in Parkinson’s disease. J Neurol Sci. 310(1–2):231–236. 10.1016/j.jns.2011.07.020 PubMed

Ackermann H, Konczak J, Hertrich I (1997) The temporal control of repetitive articulatory movements in Parkinson’s disease. Brain Lang. 56(2):312–319. 10.1006/brln.1997.1851 PubMed

Delval A, Rambour M, Tard C et al (2016) Freezing/festination during motor tasks in early-stage Parkinson’s disease: A prospective study. Mov Disord. 31(12):1837–1845. 10.1002/mds.26762 PubMed

Illner V, Novotný M, Kouba T et al (2024) Smartphone Voice Calls Provide Early Biomarkers of Parkinsonism in Rapid Eye Movement Sleep Behavior Disorder. Mov Disord. 39(10):1752–1762. 10.1002/mds.29921 PubMed

Rusz J, Krupička R, Vítečková S et al (2023) Speech and gait abnormalities in motor subtypes of de-novo Parkinson’s disease. CNS Neurosci Ther. 10.1111/cns.14158 PubMed PMC

Šubert M, Novotný M, Tykalová T et al (2023) Lexical and syntactic deficits analyzed via automated natural language processing: the new monitoring tool in multiple sclerosis. Ther Adv Neurol Disord. 16:17562864231180720. 10.1177/17562864231180719 PubMed PMC

Stegmann G, Hahn S, Liss J et al (2020) Repeatability of Commonly Used Speech and Language Features for Clinical Applications. Digit Biomark. 4:109–122. 10.1159/000511671 PubMed PMC

MacDonald B, Jiang PP, Cattiau J, et al (2021) Disordered speech data collection: lessons learned at 1 million utterances from project euphonia. Proc Interspeech 2021, 4833–4837. 10.21437/Interspeech.2021-697

Rusz J, Tykalova T, Novotny M et al (2021) Defining Speech Subtypes in De Novo Parkinson Disease: Response to Long-term Levodopa Therapy. Neurology. 97(21):e2124–e2135. 10.1212/WNL.0000000000012878 PubMed

Zhu Y, Li S, Lai H et al (2022) Effects of Anti-Parkinsonian Drugs on Verbal Fluency in Patients with Parkinson’s Disease: A Network Meta-Analysis. Brain Sci. 12(11):1496. 10.3390/brainsci12111496 PubMed PMC

Poewe W, Stankovic I, Halliday G et al (2022) Multiple system atrophy. Nat Rev Dis Primers. 8(1):56. 10.1038/s41572-022-00382-6 PubMed

Long-term dopaminergic therapy improves spoken language in de-novo Parkinson's disease