Cognitive decline is a common feature of neurologic conditions, with language functions often affected. Word finding difficulties are commonly reported to neurologists in clinic. Receptive language dysfunction (i.e., comprehension) tends to be more difficult to recognize for both the patient and the clinician. Subtle yet pervasive decrements in language may be a key feature (and potential driver) of pathological cognitive decline inherent to neurologic diseases involving a primary or secondary neurodegenerative process. While severe language impairment such as aphasia presenting in the context of stroke or dementia has been studied in detail, mild or insidious presentations remain relatively understudied. In this review, we evaluate neural substrates and clinical manifestations of language deficits noted in four neurologic populations: Alzheimer's disease (AD), stroke, multiple sclerosis (MS), and Parkinson's disease (PD). Despite differences in etiology and pathophysiology, these four neurologic populations each present with prominent language dysfunction. For each, we describe neuroanatomical substrates and networks underlying language dysfunction. We then describe current observations of language dysfunction in each population. We incorporate a discussion of emerging speech measurement tools employing machine learning (ML) and artificial intelligence (AI). Overall, we provide evidence to support a nascent hypothesis of language dysfunction as a potential driver of cognitive decline across neurologic populations with the aim of motivating novel research insights and informing clinical care.

• Keywords
• Cognition, Cognitive impairment, Language, Neurodegenerative, Neurological,
• Publication type
• Journal Article MeSH
• Review MeSH

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.

• Keywords
• Automated linguistic analysis, Language, Multiple system atrophy, Natural language processing, Spontaneous discourse,
• MeSH
• Diagnosis, Differential MeSH
• Middle Aged MeSH
• Humans MeSH
• Multiple System Atrophy * diagnosis   complications   MeSH
• Parkinson Disease * diagnosis   complications   MeSH
• Aged MeSH
• Natural Language Processing * MeSH
• Check Tag
• Middle Aged MeSH
• Humans MeSH
• Male MeSH
• Aged MeSH
• Female MeSH
• Publication type
• Journal Article MeSH