Speech disturbances in schizophrenia: Assessing cross-linguistic generalizability of NLP automated measures of coherence

Parola, Alberto; Lin, Jessica Mary; Simonsen, Arndis; Bliksted, Vibeke; Zhou, Yuan; Wang, Huiling; Inoue, Lana; Koelkebeck, Katja; Fusaroli, Riccardo

doi:10.1016/j.schres.2022.07.002

Cited by 38 publications

(22 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such NLP tools do not rely on a clinician's inferential skill to assess the cognitive-linguistic health status (Voleti et al, 2020) of patients from early stages of psychosis (Delvecchio et al, 2019) and are able to predict psychosis onset in individuals at clinical high-risk (CHR) (Bedi et al, 2015). These approaches have broadly focused on syntactic (Thomas et al, 1990;Thomas, 1996;Covington et al, 2005;Delvecchio et al, 2019) and semantic indices (Corcoran et al, 2018;Bar et al, 2019;Alonso-Sánchez et al, 2022;Parola et al, 2022) as the affected domains in psychosis.…”

Section: Introductionmentioning

confidence: 99%

Widespread cortical thinning, excessive glutamate and impaired linguistic functioning in schizophrenia: A cluster analytic approach

Liang

Silva

Jeon

et al. 2022

Front. Hum. Neurosci.

View full text Add to dashboard Cite

IntroductionSymptoms of schizophrenia are closely related to aberrant language comprehension and production. Macroscopic brain changes seen in some patients with schizophrenia are suspected to relate to impaired language production, but this is yet to be reliably characterized. Since heterogeneity in language dysfunctions, as well as brain structure, is suspected in schizophrenia, we aimed to first seek patient subgroups with different neurobiological signatures and then quantify linguistic indices that capture the symptoms of “negative formal thought disorder” (i.e., fluency, cohesion, and complexity of language production).MethodsAtlas-based cortical thickness values (obtained with a 7T MRI scanner) of 66 patients with first-episode psychosis and 36 healthy controls were analyzed with hierarchical clustering algorithms to produce neuroanatomical subtypes. We then examined the generated subtypes and investigated the quantitative differences in MRS-based glutamate levels [in the dorsal anterior cingulate cortex (dACC)] as well as in three aspects of language production features: fluency, syntactic complexity, and lexical cohesion.ResultsTwo neuroanatomical subtypes among patients were observed, one with near-normal cortical thickness patterns while the other with widespread cortical thinning. Compared to the subgroup of patients with relatively normal cortical thickness patterns, the subgroup with widespread cortical thinning was older, with higher glutamate concentration in dACC and produced speech with reduced mean length of T-units (complexity) and lower repeats of content words (lexical cohesion), despite being equally fluent (number of words).ConclusionWe characterized a patient subgroup with thinner cortex in first-episode psychosis. This subgroup, identifiable through macroscopic changes, is also distinguishable in terms of neurochemistry (frontal glutamate) and language behavior (complexity and cohesion of speech). This study supports the hypothesis that glutamate-mediated cortical thinning may contribute to a phenotype that is detectable using the tools of computational linguistics in schizophrenia.

show abstract

Section: Introductionmentioning

confidence: 99%

Widespread cortical thinning, excessive glutamate and impaired linguistic functioning in schizophrenia: A cluster analytic approach

Liang

Silva

Jeon

et al. 2022

Front. Hum. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Overall, we found scarce evidence for a universal, distinctive vocal pattern that characterizes schizophrenia: vocal patterns are highly heterogeneous with different sources of heterogeneity interacting with each other at different levels. These results raise some questions on generalizability of previous findings and on the possibility to cumulatively build on them 81 . However, they also indicate where future attempts may be directed: a larger shared multilingual corpus representative of the heterogeneity of the schizophrenic spectrum, a more explicit focus on multidimensional acoustic patterns and their relations with speech tasks, and a self-correcting cumulative approach.…”

Section: Discussionmentioning

confidence: 80%

Section: Discussionmentioning

confidence: 80%

Voice patterns as markers of schizophrenia: building a cumulative generalizable approach via a cross-linguistic and meta-analysis based investigation

Parola

Simonsen

Lin

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Background and HypothesisVoice atypicalities are potential markers of clinical features of schizophrenia (e.g., negative symptoms). A recent meta-analysis identified an acoustic profile associated with schizophrenia (reduced pitch variability and increased pauses), but also highlighted shortcomings in the field: small sample sizes, little attention to the heterogeneity of the disorder, and to generalizing findings to diverse samples and languages.Study DesignWe provide a critical cumulative approach to vocal atypicalities in schizophrenia, where we conceptually and statistically build on previous studies. We aim at identifying a cross-linguistically reliable acoustic profile of schizophrenia and assessing sources of heterogeneity (symptomatology, pharmacotherapy, clinical and social characteristics). We relied on previous meta-analysis to build and analyze a large cross-linguistic dataset of audio recordings of 231 patients with schizophrenia and 238 matched controls (>4.000 recordings in Danish, German, Mandarin and Japanese). We used multilevel Bayesian modeling contrasting meta-analytically informed and skeptical inferences.Study ResultsWe found only a minimal generalizable acoustic profile of schizophrenia (reduced pitch variability), while duration atypicalities replicated only in some languages. We identified reliable associations between acoustic profile and individual differences in clinical ratings of negative symptoms, medication, age and gender. However, these associations vary across languages.ConclusionsThe findings indicate that a strong cross-linguistically reliable acoustic profile of schizophrenia is unlikely. Rather, if we are to devise effective clinical applications able to target different ranges of patients, we need first to establish larger and more diverse cross-linguistic datasets, focus on individual differences, and build self-critical cumulative approaches.

show abstract

“…The combination of new powerful forms of machine learning, pervasive smartphone data collection, and other sources of big data will allegedly identify historically elusive markers for affective and psychotic disorders and therefore enable more reliable diagnoses, continuous evaluation of symptoms, and perhaps even personalized treatment [8][9][10][11][12] . However, communication is a complex phenomenon and its relation to specific disorders is not straightforward, with many potential confounders and ethical considerations 6,13,14 .…”

Section: The Confounding Role Of Medications On Communication-related...mentioning

confidence: 99%

“…Affective and psychotic disorders have long been associated with atypical communicative patterns -e.g., decreased emotional expression and flat prosody 1,2 . This awareness is widely used during the assessment of the disorders, and is increasingly investigated through automated voice and content analysis [3][4][5][6][7] . The combination of new powerful forms of machine learning, pervasive smartphone data collection, and other sources of big data will allegedly identify historically elusive markers for affective and psychotic disorders and therefore enable more reliable diagnoses, continuous evaluation of symptoms, and perhaps even personalized treatment [8][9][10][11][12] .…”

Section: The Confounding Role Of Medications On Communication-related...mentioning

confidence: 99%

Identifying medications underlying communication atypicalities in psychotic and affective disorders: A pharmacovigilance study within the FDA Adverse Event Reporting System

Fusaroli

Simonsen

Borrie

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Disruptions in language and speech are considered promising markers of affective and psychotic disorders. However, little is known about the mechanisms and confounders underlying such communicative atypicalities. Medications might have a crucial, relatively unknown role both as potential confounders and relatedly offering an insight about the mechanisms at work. The integration of regulatory documents with pharmacovigilance techniques could provide a more comprehensive picture to account for in future investigations of communication-related biomarkers. Objectives: Our aim was to identify a list of drugs potentially associated with speech and language atypicalities within psychotic and affective disorders. Methods: To structure a search for potential drug-induced communicative atypicalities on the FDA Adverse Event Reporting System (FAERS, updated June 2021), we developed a query using the Medical Dictionary for Regulatory Activities (MedDRA). We performed a Bonferroni corrected disproportionality analysis (Reporting Odds Ratio) on three separate populations: psychotic, affective, and non-neuropsychiatric disorders, to account for the confounding role of different underlying conditions. Unexpected drug adverse event associations, which were not already reported in the SIDER database of labeled adverse drug reactions, were subjected to further robustness analyzes to account for expected biases. Results: We identified a list of 291 expected and 91 unexpected potential confounding medications. We corroborated known/suspected associations: e.g., corticosteroids-related dysphonia and immunosuppressant-related stuttering. We also identified novel signals: e.g., domperidone-associated aphasia or VEGFR inhibitors-related dysphonia. Conclusions: We provide a list of medications to account for in future studies of communication-related biomarkers in affective and psychotic disorders. The methodological tools here implemented for large scale pharmacosurveillance investigations will facilitate future investigations of communication-related biomarkers in other conditions and provide a case study in more rigorous procedures for digital phenotyping in general. Objectives: Our aim was to identify a list of drugs potentially associated with speech and language atypicalities within psychotic and affective disorders, to account for in future investigations of communicative markers and to provide tools for similar future endeavors. Methods: We identified terms from the Medical Dictionary for Regulatory Activities (MedDRA) related to speech and language adverse drug reactions and clustered them by partial semantic overlap to structure a search on the FDA Adverse Event Reporting System (FAERS, updated June 2021). A Bonferroni corrected disproportionality analysis was applied to three separate populations in the FAERS: psychotic, affective, and non-neuropsychiatric disorders, to account for the confounding role of different underlying conditions. Unexpected drug adverse event associations, which were not already reported in the SIDER database of labeled adverse drug reactions, were subjected to further robustness analyzes to account for expected biases. Results: We identified a list of 291 expected and 91 unexpected potential confounding medications. We also developed methodological tools for large-scale pharmacosurveillance investigations: a MedDRA query proposal for speech and language impairments, formalization of possible biases, and related analyzes to account for them. Conclusions: We provide a list of medications to account for in future studies of communicative behavioral biomarkers in affective and psychotic disorders. The developed methodological tools will facilitate future investigations of communicative biomarkers in other conditions and provide a case study in more rigorous procedures for digital phenotyping in general.

show abstract

Speech disturbances in schizophrenia: Assessing cross-linguistic generalizability of NLP automated measures of coherence

Cited by 38 publications

References 48 publications

Widespread cortical thinning, excessive glutamate and impaired linguistic functioning in schizophrenia: A cluster analytic approach

Widespread cortical thinning, excessive glutamate and impaired linguistic functioning in schizophrenia: A cluster analytic approach

Voice patterns as markers of schizophrenia: building a cumulative generalizable approach via a cross-linguistic and meta-analysis based investigation

Identifying medications underlying communication atypicalities in psychotic and affective disorders: A pharmacovigilance study within the FDA Adverse Event Reporting System

Contact Info

Product

Resources

About