Automated linguistic analysis in speech samples of Turkish-speaking patients with schizophrenia-spectrum disorders.

Modern natural language processing (NLP) methods provide ways to objectively quantify language disturbances for potential use in diagnostic classification. We performed computerized language analysis in speech samples of 82 Turkish-speaking subjects, including 44 patients with schizophrenia spectrum disorders (SSD) and 38 healthy controls (HC). Exploratory analysis of speech samples involved 16 sentence-level semantic similarity features using SBERT (Sentence Bidirectional Encoder Representation from Text) as well as 8 generic and 8 part-of-speech (POS) features. The random forest classifier using SBERT-derived semantic similarity features achieved a mean accuracy of 85.6 % for the classification of SSD and HC. When semantic similarity features were combined with generic and POS features, the classifier's mean accuracy reached to 86.8 %. Our analysis reflected increased sentence-level semantic similarity scores in SSD. Generic and POS analyses revealed an increase in the use of verbs, proper nouns and pronouns in SSD while our results showed a decrease in the utilization of conjunctions, determiners, and both average and maximum sentence length in SSD compared to HC. Quantitative language features were correlated with the expressive deficit domain of BNSS (Brief Negative Symptom Scale) as well as with the duration of illness. These findings from Turkish-speaking interviews contribute to the growing evidence-based NLP-derived assessments in non-English-speaking patients.

Computational analysis of linguistic features in speech samples of first-episode bipolar disorder and psychosis.

BACKGROUND: In recent years, automated analyses using novel NLP methods have been used to investigate language abnormalities in schizophrenia. In contrast, only a few studies used automated language analyses in bipolar disorder. To our knowledge, no previous research compared automated language characteristics of first-episode psychosis (FEP) and bipolar disorder (FEBD) using NLP methods. METHODS: Our study included 53 FEP, 40 FEBD and 50 healthy control participants who are native Turkish speakers. Speech samples of the participants in the Thematic Apperception Test (TAT) underwent automated generic and part-of-speech analyses, as well as sentence-level semantic similarity analysis based on SBERT. RESULTS: Both FEBD and FEP were associated with the use of shorter sentences and increased sentence-level semantic similarity but less semantic alignment with the TAT pictures. FEP also demonstrated reduced verbosity and syntactic complexity. FEP differed from FEBD in reduced verbosity, decreased first-person singular pronouns, fewer conjunctions, increased semantic similarity as well as shorter sentence and word length. The mean classification accuracy was 82.45 % in FEP vs HC, 71.1 % in FEBD vs HC, and 73 % in FEP vs FEBD. After Bonferroni correction, the severity of negative symptoms in FEP was associated with reduced verbal output and increased 5th percentile of semantic similarity. LIMITATIONS: The main limitation of this study was the cross-sectional nature. CONCLUSION: Our findings demonstrate that both patient groups showed language abnormalities, which were more severe and widespread in FEP compared to FEBD. Our results suggest that NLP methods reveal transdiagnostic linguistic abnormalities in FEP and FEBD.

Automated linguistic analysis in youth at clinical high risk for psychosis.

Identifying individuals at clinical high risk for psychosis (CHRP) is crucial for preventing psychosis and improving the prognosis for schizophrenia. Individuals at CHR-P may exhibit mild forms of formal thought disorder (FTD), making it possible to identify them using natural language processing (NLP) methods. In this study, speech samples of 62 CHR-P individuals and 45 healthy controls (HCs) were elicited using Thematic Apperception Test images. The evaluation involved various NLP measures such as semantic similarity, generic, and part-of-speech (POS) features. The CHR-P group demonstrated higher sentence-level semantic similarity and reduced mean image-to-text similarity. Regarding generic analysis, they demonstrated reduced verbosity and produced shorter sentences with shorter words. The POS analysis revealed a decrease in the utilization of adverbs, conjunctions, and first-person singular pronouns, alongside an increase in the utilization of adjectives in the CHR-P group compared to HC. In addition, we developed a machine-learning model based on 30 NLP-derived features to distinguish between the CHR-P and HC groups. The model demonstrated an accuracy of 79.6 % and an AUC-ROC of 0.86. Overall, these findings suggest that automated language analysis of speech could provide valuable information for characterizing FTD during the clinical high-risk phase and has the potential to be applied objectively for early intervention for psychosis.

Neural correlates of mental state decoding and mental state reasoning in schizophrenia.

Theory of mind skills are disrupted in schizophrenia. However, various theory of mind tasks measure different neurocognitive domains. This multimodal neuroimaging study aimed to investigate the neuroanatomical correlates of mental state decoding and reasoning components of theory of mind in schizophrenia and healthy controls (HCs) using T1-weighted and diffusion-weighted (DTI) magnetic resonance imaging (MRI). Sixty-two patients with schizophrenia and 34 HCs were included. The Reading the Mind in the Eyes (RMET) and Hinting tests were used to evaluate mental state decoding and reasoning, respectively. Correlations between social cognition and cortical parameters (thickness, volume, surface area), or DTI scalars (fractional anisotropy, axial diffusivity, radial diffusivity) were cluster-based corrected for multiple comparisons. In schizophrenia, RMET scores showed positive correlations in 3 clusters, including left insula thickness, right superior-temporal thickness, left superior-temporal-sulcus volume, and DTI analysis revealed that fractional anisotropy showed positive correlations in 3 clusters, including right inferior-fronto-occipital fasciculus, left forceps-major, left inferior-fronto-occipital fasciculus. In schizophrenia, Hinting test scores showed positive correlations in 3 clusters in T1-weighted MRI, including left superior-temporal-sulcus volume, left superior-temporal-sulcus surface area, left pars-orbitalis volume. In conclusion, this study provided evidence for the involvement of particular cortical regions and white matter tracts in mental state decoding and reasoning.

Clinical and developmental characteristics of cognitive subgroups in a transdiagnostic sample of schizophrenia spectrum disorders and bipolar disorder.

Evidence suggests that neurocognitive dysfunction is a transdiagnostic feature of individuals across the continuum between schizophrenia and bipolar disorder. However, there is significant heterogeneity of neuropsychological and social-cognitive abilities in schizophrenia, schizoaffective disorder, and bipolar disorder. The current study aimed to investigate the clinical and developmental characteristics of cognitive subgroups within the schizo-bipolar spectrum. 147 clinically stable patients with schizophrenia, schizoaffective or bipolar disorder were assessed using clinical rating scales for current psychotic and affective symptoms, and a comprehensive neuropsychological battery including measures of social cognition (Hinting and Reading the mind from the Eyes (RMET) task)). Developmental history and premorbid academic functioning were also evaluated. The study also included 36 healthy controls. Neurocognitive subgroups were investigated using latent class analysis (LCA). The optimal number of clusters was determined based on the Bayesian information criterion. A logistic regression analysis was conducted to investigate the predictors of membership to the globally impaired subgroup. LCA revealed two neurocognitive clusters including globally impaired (n = 89, 60.5%) and near-normal cognitive functioning (n = 58, 39.5%) subgroups. The near-normal cognitive functioning subgroup was not significantly different from healthy controls. The globally impaired subgroup had a higher score of developmental abnormalities (p<0.001), poorer premorbid academic functioning, mothers who were less educated and more severe disorganized speech (p = 0.001) and negative symptoms (p = 0.004) compared to the near-normal cognitive functioning group. History of developmental abnormalities and persistent disorganization rather than diagnosis are significant predictors of the subgroup of individuals with global cognitive impairment in the schizophrenia-bipolar disorder continuum.

Alterations in levels of 8-Oxo-2'-deoxyguanosine and 8-Oxoguanine DNA glycosylase 1 during a current episode and after remission in unipolar and bipolar depression.

INTRODUCTION: Previous studies showed significant increases in DNA base damage markers and significant alterations in base excision repair enzymes in patients with unipolar and bipolar depression. We aimed to investigate changes in urine 8-Oxo-2'-deoxyguanosine (8-oxo-dG) and gene expression levels of 8-Oxoguanine DNA glycosylase 1 (OGG1) during a current depressive episode and after remission in bipolar and unipolar disorders. METHODS: Twenty-four acutely depressed bipolar (BD), 33 unipolar depression (UD) patients and 61 healthy controls were included in the study. Clinical evaluations, blood and urine sampling were completed at baseline and at remission after eight weeks. The urine 8-oxo-dG levels were assessed by liquid chromatography tandem mass spectrometry and adjusted for urine creatinine levels. The gene expression levels of OGG1 were determined from cDNA extracted from blood samples, using real time-polymerase chain reaction. RESULTS: At baseline, patients presented significantly higher levels of 8-oxo-dG (p = 0.008), and lower gene expression of OGG1 (p = 0.024) compared to controls. Levels of either 8-oxo-dG or OGG1 expression did not differ between BD and UD. In patients who remitted by the 8th week (n = 30), 8-oxo-dG decreased significantly (p = 0.001), and gene expression levels of OGG1 increased by 2.95 times compared to baseline levels (p = 0.001). All comparisons were adjusted for age, sex, smoking status and body mass index. CONCLUSION: Our results suggest that patients with bipolar and unipolar mood disorders present increased 8-oxo-dG and decreased gene expression levels of OGG1 in current depressive episodes, and that these changes might be reversed by the resolution of depressive symptoms. The causal relationship between DNA damage and repair requires further exploration.