Dataset Information

Acoustic speech markers for schizophrenia-spectrum disorders: a diagnostic and symptom-recognition tool.

ABSTRACT:

Background

Clinicians routinely use impressions of speech as an element of mental status examination. In schizophrenia-spectrum disorders, descriptions of speech are used to assess the severity of psychotic symptoms. In the current study, we assessed the diagnostic value of acoustic speech parameters in schizophrenia-spectrum disorders, as well as its value in recognizing positive and negative symptoms.

Methods

Speech was obtained from 142 patients with a schizophrenia-spectrum disorder and 142 matched controls during a semi-structured interview on neutral topics. Patients were categorized as having predominantly positive or negative symptoms using the Positive and Negative Syndrome Scale (PANSS). Acoustic parameters were extracted with OpenSMILE, employing the extended Geneva Acoustic Minimalistic Parameter Set, which includes standardized analyses of pitch (F0), speech quality and pauses. Speech parameters were fed into a random forest algorithm with leave-ten-out cross-validation to assess their value for a schizophrenia-spectrum diagnosis, and PANSS subtype recognition.

Results

The machine-learning speech classifier attained an accuracy of 86.2% in classifying patients with a schizophrenia-spectrum disorder and controls on speech parameters alone. Patients with predominantly positive v. negative symptoms could be classified with an accuracy of 74.2%.

Conclusions

Our results show that automatically extracted speech parameters can be used to accurately classify patients with a schizophrenia-spectrum disorder and healthy controls, as well as differentiate between patients with predominantly positive v. negatives symptoms. Thus, the field of speech technology has provided a standardized, powerful tool that has high potential for clinical applications in diagnosis and differentiation, given its ease of comparison and replication across samples.

SUBMITTER: de Boer JN

PROVIDER: S-EPMC10009369 | biostudies-literature | 2023 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Acoustic speech markers for schizophrenia-spectrum disorders: a diagnostic and symptom-recognition tool.

de Boer J N JN Voppel A E AE Brederoo S G SG Schnack H G HG Truong K P KP Wijnen F N K FNK Sommer I E C IEC

Psychological medicine 20210804 4

<h4>Background</h4>Clinicians routinely use impressions of speech as an element of mental status examination. In schizophrenia-spectrum disorders, descriptions of speech are used to assess the severity of psychotic symptoms. In the current study, we assessed the diagnostic value of acoustic speech parameters in schizophrenia-spectrum disorders, as well as its value in recognizing positive and negative symptoms.<h4>Methods</h4>Speech was obtained from 142 patients with a schizophrenia-spectrum di ...[more]

PMID: 34344490

Similar Datasets

Project description:Syntax, the grammatical structure of sentences, is a fundamental aspect of language. It remains debated whether reduced syntactic complexity is unique to schizophrenia spectrum disorder (SSD) or whether it is also present in major depressive disorder (MDD). Furthermore, the association of syntax (including syntactic complexity and diversity) with language-related neuropsychology and psychopathological symptoms across disorders remains unclear. Thirty-four SSD patients and thirty-eight MDD patients diagnosed according to DSM-IV-TR as well as forty healthy controls (HC) were included and tasked with describing four pictures from the Thematic Apperception Test. We analyzed the produced speech regarding its syntax delineating measures for syntactic complexity (the total number of main clauses embedding subordinate clauses) and diversity (number of different types of complex sentences). We performed cluster analysis to identify clusters based on syntax and investigated associations of syntactic, to language-related neuropsychological (verbal fluency and verbal episodic memory), and psychopathological measures (positive and negative formal thought disorder) using network analyses. Syntax in SSD was significantly reduced in comparison to MDD and HC, whereas the comparison of HC and MDD revealed no significant differences. No associations were present between speech measures and current medication, duration and severity of illness, age or sex; the single association accounted for was education. A cluster analysis resulted in four clusters with different degrees of syntax across diagnoses. Subjects with less syntax exhibited pronounced positive and negative symptoms and displayed poorer performance in executive functioning, global functioning, and verbal episodic memory. All cluster-based networks indicated varying degrees of domain-specific and cross-domain connections. Measures of syntactic complexity were closely related while syntactic diversity appeared to be a separate node outside of the syntactic network. Cross-domain associations were more salient in more complex syntactic production.

Project description:Flexible goal-directed human cognition is supported by many forms of self-directed manipulation of representations. Among them, Inner-Speech (IS; covert self-directed speech) acts on second-order representations (e.g., goals/sub-goals), empowering attention and feedback processing. Interestingly, patients with Schizophrenia Spectrum Disorders (SSD) show impaired Executive Functions (EF; e.g., cognitive flexibility) and, probably, a related IS alteration. However, fragmentary evidence and no computational modeling prevent a clear assessment of these processes and focused therapeutic interventions. Here, we address these issues by exploiting a translational approach that integrates experimental clinical data, machine learning, and computational modeling. First, we administered the Wisconsin Cards Sorting Test (WCST; a neuropsychological test probing cognitive flexibility) to 162 SSD patients and 108 healthy control participants, and we computed the clinical behavioural data with a data-driven clustering algorithm. Second, we extracted the cluster neuropsychological profiles with our theory-based validated computational model of the WCST. Finally, we exploited our model to emulate an IS-based psychotherapeutic intervention for SSD subpopulations. We identified different SSD sub-populations and global trends (e.g., a descending feedback sensitivity); however, extremely different neuropsychological profiles emerged. In particular, 'Relatively Intact' patients showed an unexpected profile (distraction/reasoning failures), quite divergent from the perseverative/rigid profile of the others. Importantly, the former showed no impact of Interfering-IS, while the others showed increased Interfering-IS strongly affecting their cognition. These differences highlight that SSD populations require a cluster-dependent individualisation of the intervention to achieve adequate cognitive performance. Overall, these results support a clear definition of neuropsychological profiles and the related Interfering-IS impact in SSD subpopulations, thus showing important implications for basic research (e.g., cognitive neuroscience) and clinical fields (clinical psychology and psychiatry).

Project description:Clozapine is the most effective antipsychotic for patients with treatment-resistant schizophrenia. However, response is highly variable and possible genetic underpinnings of this variability remain unknown. Here, we performed polygenic risk score (PRS) analyses to estimate the amount of variance in symptom severity among clozapine-treated patients explained by PRSs (R2) and examined the association between symptom severity and genotype-predicted CYP1A2, CYP2D6, and CYP2C19 enzyme activity. Genome-wide association (GWA) analyses were performed to explore loci associated with symptom severity. A multicenter cohort of 804 patients (after quality control N = 684) with schizophrenia spectrum disorder treated with clozapine were cross-sectionally assessed using the Positive and Negative Syndrome Scale and/or the Clinical Global Impression-Severity (CGI-S) scale. GWA and PRS regression analyses were conducted. Genotype-predicted CYP1A2, CYP2D6, and CYP2C19 enzyme activities were calculated. Schizophrenia-PRS was most significantly and positively associated with low symptom severity (p = 1.03 × 10-3; R2 = 1.85). Cross-disorder-PRS was also positively associated with lower CGI-S score (p = 0.01; R2 = 0.81). Compared to the lowest tertile, patients in the highest schizophrenia-PRS tertile had 1.94 times (p = 6.84×10-4) increased probability of low symptom severity. Higher genotype-predicted CYP2C19 enzyme activity was independently associated with lower symptom severity (p = 8.44×10-3). While no locus surpassed the genome-wide significance threshold, rs1923778 within NFIB showed a suggestive association (p = 3.78×10-7) with symptom severity. We show that high schizophrenia-PRS and genotype-predicted CYP2C19 enzyme activity are independently associated with lower symptom severity among individuals treated with clozapine. Our findings open avenues for future pharmacogenomic projects investigating the potential of PRS and genotype-predicted CYP-activity in schizophrenia.

Dataset Information

Acoustic speech markers for schizophrenia-spectrum disorders: a diagnostic and symptom-recognition tool.

Background

Methods

Results

Conclusions

Publications

Acoustic speech markers for schizophrenia-spectrum disorders: a diagnostic and symptom-recognition tool.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets