Relationships of language features from spontaneous speech to objective and subjective cognition in people with...

Language dysfunction is common in multiple sclerosis (MS). Speech analysis utilizing automated techniques offers potential for detecting subtle cognitive changes through quantification of language features derived from spontaneous speech, an easily acquired, naturalistic measure that may be a proxy of general cognitive function.

To determine associations of language features to objective and subjective cognition (primary), mood and fatigue (secondary), and evaluate discriminability.

Participants with MS and controls completed objective and subjective cognitive measures and provided a 2-min spontaneous speech sample that was analyzed using natural language processing. Convergent validity was assessed by calculating correlations of derived language features to objective and subjective cognition. Correlations of language features to fatigue, anxiety, and depression were also evaluated. Finally, validity of language features to discriminate individuals with MS from controls was assessed.

In the full sample, three language features- N-grams, content words, and function words- were correlated with objective cognitive test performance (r's from 0.3 to 0.4). In the MS group, language features were associated with subjective cognition (r=-0.361, p=.007) and three objective tests (r's from 0.3 to 0.5), and showed no association to fatigue, anxiety, or depression. Compared to controls, the MS group produced a lower number of adverbs (p=.001).

Semi-automated speech analysis to derive language variables may provide early indications of cognitive changes in MS, potentially enhancing diagnosis and patient management strategies.