Latent Factors of Language Disturbance and Relationships to Quantitative Speech Features.

BACKGROUND AND HYPOTHESIS: Quantitative acoustic and textual measures derived from speech ("speech features") may provide valuable biomarkers for psychiatric disorders, particularly schizophrenia spectrum disorders (SSD). We sought to identify cross-diagnostic latent factors for speech disturbance with relevance for SSD and computational modeling. STUDY DESIGN: Clinical ratings for speech disturbance were generated across 14 items for a cross-diagnostic sample (N = 334), including SSD (n = 90). Speech features were quantified using an automated pipeline for brief recorded samples of free speech. Factor models for the clinical ratings were generated using exploratory factor analysis, then tested with confirmatory factor analysis in the cross-diagnostic and SSD groups. The relationships between factor scores and computational speech features were examined for 202 of the participants. STUDY RESULTS: We found a 3-factor model with a good fit in the cross-diagnostic group and an acceptable fit for the SSD subsample. The model identifies an impaired expressivity factor and 2 interrelated disorganized factors for inefficient and incoherent speech. Incoherent speech was specific to psychosis groups, while inefficient speech and impaired expressivity showed intermediate effects in people with nonpsychotic disorders. Each of the 3 factors had significant and distinct relationships with speech features, which differed for the cross-diagnostic vs SSD groups. CONCLUSIONS: We report a cross-diagnostic 3-factor model for speech disturbance which is supported by good statistical measures, intuitive, applicable to SSD, and relatable to linguistic theories. It provides a valuable framework for understanding speech disturbance and appropriate targets for modeling with quantitative speech features.

Clinical and computational speech measures are associated with social cognition in schizophrenia spectrum disorders.

In this study, we compared three domains of social cognition (emotion processing, mentalizing, and attribution bias) to clinical and computational language measures in 63 participants with schizophrenia spectrum disorders. Based on the active inference model for discourse, we hypothesized that emotion processing and mentalizing, but not attribution bias, would be related to language disturbances. Clinical ratings for speech disturbance assessed disorganized and underproductive dimensions. Computational features included speech graph metrics, use of modal verbs, use of first-person pronouns, cosine similarity of adjacent utterances, and measures of sentiment; these were represented by four principal components. We found that higher clinical ratings for disorganized speech were predicted by greater impairments in both emotion processing and mentalizing, and that these relationships remained significant when accounting for demographic variables, overall psychosis symptoms, and verbal ability. Similarly, a computational speech component reflecting insular speech was consistently predicted by impairment in emotion processing. There were notable trends for computational speech components reflecting underproductive speech and decreased content-rich speech predicting mentalizing ability. Exploratory longitudinal analyses in a small subset of participants (n = 17) found that improvements in both emotion processing and mentalizing predicted improvements in disorganized speech. Attribution bias did not demonstrate strong relationships with language measures. Altogether, our findings are consistent with the active inference model of discourse and suggest greater emphasis on treatments that target social cognitive and language systems.

Who does what to whom? graph representations of action-predication in speech relate to psychopathological dimensions of psychosis.

Graphical representations of speech generate powerful computational measures related to psychosis. Previous studies have mostly relied on structural relations between words as the basis of graph formation, i.e., connecting each word to the next in a sequence of words. Here, we introduced a method of graph formation grounded in semantic relationships by identifying elements that act upon each other (action relation) and the contents of those actions (predication relation). Speech from picture descriptions and open-ended narrative tasks were collected from a cross-diagnostic group of healthy volunteers and people with psychotic or non-psychotic disorders. Recordings were transcribed and underwent automated language processing, including semantic role labeling to identify action and predication relations. Structural and semantic graph features were computed using static and dynamic (moving-window) techniques. Compared to structural graphs, semantic graphs were more strongly correlated with dimensional psychosis symptoms. Dynamic features also outperformed static features, and samples from picture descriptions yielded larger effect sizes than narrative responses for psychosis diagnoses and symptom dimensions. Overall, semantic graphs captured unique and clinically meaningful information about psychosis and related symptom dimensions. These features, particularly when derived from semi-structured tasks using dynamic measurement, are meaningful additions to the repertoire of computational linguistic methods in psychiatry.