Complement component 4A protein levels are negatively related to frontal volumes in patients with schizophrenia spectrum disorders.

BACKGROUND: Excessive C4A-gene expression may result in increased microglia-mediated synaptic pruning. As C4A overexpression is observed in schizophrenia spectrum disorders (SSD), this mechanism may account for the altered brain morphology (i.e. reduced volume and cortical thickness) and cognitive symptoms that characterize SSD. Therefore, this study investigates the association of C4A serum protein levels with brain morphology and cognition, and in particular whether this association differs between recent-onset SSD (n = 69) and HC (n = 40). METHODS: Serum C4A protein levels were compared between groups. Main outcomes included total gray matter volume, mean cortical thickness and cognitive performance. Regression analysis on these outcomes included C4A level, group (SSD vs. HC), and C4A*Group interactions. All statistical tests were corrected for age, sex, BMI, and antipsychotic medication dose. Follow-up analyses were performed on separate brain regions and scores on cognitive sub-tasks. RESULTS: The group difference in C4A levels was not statistically significant (p = 0.86). The main outcomes did not show a significant interaction effect (p > 0.13) or a C4A main effect (p > 0.27). Follow-up analyses revealed significant interaction effects for the left medial orbitofrontal and left frontal pole volumes (p < 0.001): C4A was negatively related to these volumes in SSD, but positively in HC. CONCLUSION: This study demonstrated that C4A was negatively related to - specifically - frontal brain volumes in SSD, but this relation was inverse for HC. The results support the hypothesis of complement-mediated brain volume reduction in SSD. The results also suggest that C4A has a differential association with brain morphology in SSD compared to HC.

Combining automatic speech recognition with semantic natural language processing in schizophrenia.

Natural language processing (NLP) tools are increasingly used to quantify semantic anomalies in schizophrenia. Automatic speech recognition (ASR) technology, if robust enough, could significantly speed up the NLP research process. In this study, we assessed the performance of a state-of-the-art ASR tool and its impact on diagnostic classification accuracy based on a NLP model. We compared ASR to human transcripts quantitatively (Word Error Rate (WER)) and qualitatively by analyzing error type and position. Subsequently, we evaluated the impact of ASR on classification accuracy using semantic similarity measures. Two random forest classifiers were trained with similarity measures derived from automatic and manual transcriptions, and their performance was compared. The ASR tool had a mean WER of 30.4%. Pronouns and words in sentence-final position had the highest WERs. The classification accuracy was 76.7% (sensitivity 70%; specificity 86%) using automated transcriptions and 79.8% (sensitivity 75%; specificity 86%) for manual transcriptions. The difference in performance between the models was not significant. These findings demonstrate that using ASR for semantic analysis is associated with only a small decrease in accuracy in classifying schizophrenia, compared to manual transcripts. Thus, combining ASR technology with semantic NLP models qualifies as a robust and efficient method for diagnosing schizophrenia.

[Antipsychotic drugs for women: a narrative review and clinical guidelines]. / Antipsychotica voor vrouwen: overzicht van de literatuur en praktijkadviezen.

BACKGROUND: It has long been thought that women with a schizophrenia spectrum disorder have a more favorable course than men. However, this is not the case, even though they become ill later in life and are less likely to have comorbid drug abuse. Guidelines for prescribing antipsychotics are based on research with mostly male participants, and by following these guidelines we are doing our female patients a disservice. Gender and sex differences lead to differences in preferences, pharmacokinetics and pharmacodynamics. AIM: Providing an overview of antipsychotics for women with a schizophrenia spectrum disorder and discuss the consequences for practice. METHOD: A clinically oriented study of the literature. RESULTS: Women reach higher plasma levels than men when they receive the same dose of antipsychotic drugs (except for lurasidone and quetiapine). The effect of antipsychotics is also greater in women, because estrogens increase the brain’s dopamine sensitivity. This leads to higher risks of side effects. Clinical guidelines differ for women at different stages of life because estrogens greatly contribute to the sex differences seen in the efficacy and tolerability of antipsychotics. CONCLUSION: Clinicians should be aware that women should be treated differently with antipsychotics than men.

[Automated speech analysis can distinguish frontotemporal dementia from depression: a pilot study]. / Geautomatiseerde spraakanalyse bij onderscheiden van frontotemporale dementie en depressie.

BACKGROUND: Differentiating the behavioural variant of frontotemporal dementia from a depression is challenging. Recent development of automated speech analyses might add to diagnostic. AIM: To investigate the value of automated speech analyses in differentiating bvFTD from a depressive disorder. METHOD: A semistructured interview was recorded in 15 patients with bvFTD, 15 patients with a depressive disorder and 15 healthy controls, which was transcribed and analysed. Acoustic and semantic values were extracted and classified using machine learning. RESULTS: Acoustic values showed an 80% accuracy for differentiating bvFTD from depressive disorder and semantic values showed an 70.8% accuracy. CONCLUSION: Acoustic as well as semantic values show significant differences between bvFTD and depressive disorder. In automated speech analyses researches should consider privacy matters as well as possible confounders like age, sex and ethnicity. This study should be repeated in a larger population.

[Recognizing depression through computational language analysis]. / Herkennen van depressie met computationele taalanalyse.

BACKGROUND: Currently, clinical practice lacks a usable biomarker for the detection and differentiation of depression. Such a biomarker may be found in speech, from which important information can be distilled using automated speech analysis. AIM: To provide an overview of the fast-developing field of automated speech analysis for depression. METHOD: We summarize the current literature on speech features in depression. RESULTS: Current computational models can detect depression with high accuracy, rendering them applicable for diagnostic tools based on automatic speech analysis. Such tools are developing at a fast rate. CONCLUSION: Some challenges are still in the way of clinical implementation. For example, results differ largely between studies due to much variation in methodology. Furthermore, privacy and ethical issues need to be addressed before tools can be used.

Assessing coherence through linguistic connectives: Analysis of speech in patients with schizophrenia-spectrum disorders.

BACKGROUND: Incoherent speech is a core diagnostic symptom of schizophrenia-spectrum disorders (SSD) that can be studied using semantic space models. Since linguistic connectives signal relations between words, they and their surrounding words might represent linguistic loci to detect unusual coherence in speech. Therefore, we investigated whether connectives' measures are useful to assess incoherent speech in SSD. METHODS: Connectives and their surrounding words were extracted from transcripts of spontaneous speech of 50 SSD-patients and 50 control participants. Using word2vec, two different cosine similarities were calculated: those of connectives and their surrounding words (connectives-related similarity), and those of free-of-connectives words-chunks (non-connectives similarity). Differences between groups in proportion of five types of connectives were assessed using generalized logistic models, and connectives-related similarity was analyzed through non-parametric multivariate analysis of variance. These features were evaluated in classification tasks to differentiate between groups. RESULTS: SSD-patients used less contingency (e.g., because) (p = .008) and multiclass connectives (e.g., as) (p < .001) than control participants. SSD-patients had higher minimum similarity of multiclass (adj-p = .04) and temporality connectives (e.g., after) (adj-p < .001), narrower similarity-range of expansion (e.g., and) (adj-p = .002) and multiclass connectives (adj-p = .04), and lower maximum similarity of expansion connectives (adj-p = .005). Using connectives' features alone, SSD-patients and controls could be distinguished with 85 % accuracy. DISCUSSION: Our results show that SSD-speech can be distinguished from speech of control participants with high accuracy, based solely on connectives' features. We conclude that including connectives could strengthen computational models to categorize SSD.

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

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.

[Improving care for women with schizophrenia-spectrum disorders]. / Vrouwen met schizofreniespectrum-stoornissen verdienen betere zorg.

Background   Women with a schizophrenia-spectrum disorder (SSD) have a better clinical profile than men at the start of their illness but lose this advantage within the first few years of living with SSD. There are benefits to be gained across different areas in the care currently offered to women with psychosis. Aim   To describe point of improvement in the care for women with SSD. Method   Review or relevant literature. Results   An important point for improvement is the early detection of female-specific signs of a first episode of psychosis, to shorten the duration of untreated psychosis, with prompt access to early intervention services. Special attention should be paid to sexual health, and to any history of childhood trauma. Antipsychotics clearly require dosing and prescription tailored to the female body, considering hormonal life phases such as menopause. Switching to prolactin-sparing medications can benefit both mental and somatic health. Finally, hormone replacement therapy should be considered for postmenopausal women. Conclusion   By providing female-specific care, women with SSD can live up to their full potential.

A data-driven linguistic characterization of hallucinated voices in clinical and non-clinical voice-hearers.

BACKGROUND: Auditory verbal hallucinations (AVHs) are heterogeneous regarding phenomenology and etiology. This has led to the proposal of AVHs subtypes. Distinguishing AVHs subtypes can inform AVHs neurocognitive models and also have implications for clinical practice. A scarcely studied source of heterogeneity relates to the AVHs linguistic characteristics. Therefore, in this study we investigate whether linguistic features distinguish AVHs subtypes, and whether linguistic AVH-subtypes are associated with phenomenology and voice-hearers' clinical status. METHODS: Twenty-one clinical and nineteen non-clinical voice-hearers participated in this study. Participants were instructed to repeat verbatim their AVHs just after experiencing them. AVH-repetitions were audio-recorded and transcribed. AVHs phenomenology was assessed using the Auditory Hallucinations Rating Scale of the Psychotic Symptom Rating Scales. Hierarchical clustering analyses without a priori group dichotomization were performed using quantitative measures of sixteen linguistic features to distinguish sets of AVHs. RESULTS: A two-AVHs-cluster solution best partitioned the data. AVHs-clusters significantly differed in linguistic features (p < .001); AVHs phenomenology (p < .001); and distribution of clinical voice-hearers (p < .001). The "expanded-AVHs" cluster was characterized by more determiners, more prepositions, longer utterances (all p < .01), and mainly contained non-clinical voice-hearers. The "compact-AVHs" cluster had fewer determiners and prepositions, shorter utterances (all p < .01), more negative content, higher degree of negativity (both p < .05), and predominantly came from clinical voice-hearers. DISCUSSION: Two voice-speech clusters were recognized, differing in syntactic-grammatical complexity and negative phenomenology. Our results suggest clinical voice-hearers often hear negative, "compact-voices", understandable under Broca's right hemisphere homologue and memory-based mechanisms. Conversely, non-clinical voice-hearers experience "expanded-voices", better accounted by inner speech AVHs models.

The neurobiological characterization of distinct cognitive subtypes in early-phase schizophrenia-spectrum disorders.

INTRODUCTION: Cognitive deficits are present in some, but not all patients with schizophrenia-spectrum disorders (SSD). We and others have demonstrated three cognitive clusters: cognitively intact patients, patients with deficits in a few domains and those with global cognitive deficits. This study aimed to identify cognitive subtypes of early-phase SSD with matched controls as a reference group, and evaluated cognitive subgroups regarding clinical and brain volumetric measures. METHODS: Eighty-six early-phase SSD patients were included. Hierarchical cluster analysis was conducted using global performance on the Brief Assessment of Cognition in Schizophrenia (BACS). Cognitive subgroups were subsequently related to clinical and brain volumetric measures (cortical, subcortical and cortical thickness) using ANCOVA. RESULTS: Three distinct cognitive clusters emerged: relative to controls we found one cluster of patients with preserved cognition (n = 25), one moderately impaired cluster (n = 38) and one severely impaired cluster (n = 23). Cognitive subgroups were characterized by differences in volume of the left postcentral gyrus, left middle caudal frontal gyrus and left insula, while differences in cortical thickness were predominantly found in fronto-parietal regions. No differences were demonstrated in subcortical brain volume. DISCUSSION: Current results replicate the existence of three distinct cognitive subgroups including one relatively large group with preserved cognitive function. Cognitive subgroups were characterized by differences in cortical regional brain volume and cortical thickness, suggesting associations with cortical, but not subcortical development and cognitive functioning such as attention, executive functions and speed of processing.

Implementation of automatic speech analysis for early detection of psychiatric symptoms: What do patients want?

Psychiatry is in dire need of a method to aid early detection of symptoms. Recent developments in automatic speech analysis prove promising in this regard, and open avenues for implementation of speech-based applications to detect psychiatric symptoms. The current survey was conducted to assess positions with regard to speech recordings among a group (n = 675) of individuals who experience psychiatric symptoms. Overall, respondents are open to the idea of speech recordings in light of their mental welfare. Importantly, concerns with regard to privacy were raised. Given that speech recordings are privacy sensitive, this requires special attention upon implementation of automatic speech analysis techniques. Furthermore, respondents indicated a preference for speech recordings in the presence of a clinician, as opposed to a recording made at home without the clinician present. In developing a speech marker for psychiatry, close collaboration with the intended users is essential to arrive at a truly valid and implementable method.

Towards precision medicine: What are the stratification hypotheses to identify homogeneous inflammatory subgroups.

Diverse lines of research testify a link, presumably causal, between immune dysregulation and the development, course and clinical outcome of psychiatric disorders. However, there is a large heterogeneity among the patients' individual immune profile and this heterogeneity prevents the development of precise diagnostic tools and the identification of therapeutic targets. The aim of this review was to delineate possible subgroups of patients on the basis of clinical dimensions, investigating whether they could lead to particular immune signatures and tailored treatments. We discuss six clinical entry points; genetic liability to immune dysregulation, childhood maltreatment, metabolic syndrome, cognitive dysfunction, negative symptoms and treatment resistance. We describe the associated immune signature and outline the effects of anti-inflammatory drugs so far. Finally, we discuss advantages of this approach, challenges and future research directions.

Language disturbances in schizophrenia: the relation with antipsychotic medication.

Language disturbances are key aberrations in schizophrenia. Little is known about the influence of antipsychotic medication on these symptoms. Using computational language methods, this study evaluated the impact of high versus low dopamine D2 receptor (D2R) occupancy antipsychotics on language disturbances in 41 patients with schizophrenia, relative to 40 healthy controls. Patients with high versus low D2R occupancy antipsychotics differed by total number of words and type-token ratio, suggesting medication effects. Both patient groups differed from the healthy controls on percentage of time speaking and clauses per utterance, suggesting illness effects. Overall, more severe negative language disturbances (i.e. slower articulation rate, increased pausing, and shorter utterances) were seen in the patients that used high D2R occupancy antipsychotics, while less prominent disturbances were seen in low D2R occupancy patients. Language analyses successfully predicted drug type (sensitivity = 80.0%, specificity = 76.5%). Several language disturbances were more related to drug type and dose, than to other psychotic symptoms, suggesting that language disturbances may be aggravated by high D2R antipsychotics. This negative impact of high D2R occupancy drugs may have clinical implications, as impaired language production predicts functional outcome and degrades the quality of life.

Language in schizophrenia: relation with diagnosis, symptomatology and white matter tracts.

Language deviations are a core symptom of schizophrenia. With the advances in computational linguistics, language can be easily assessed in exact and reproducible measures. This study investigated how language characteristics relate to schizophrenia diagnosis, symptom, severity and integrity of the white matter language tracts in patients with schizophrenia and healthy controls. Spontaneous speech was recorded and diffusion tensor imaging was performed in 26 schizophrenia patients and 22 controls. We were able to classify both groups with a sensitivity of 89% and a specificity of 82%, based on mean length of utterance and clauses per utterance. Language disturbances were associated with negative symptom severity. Computational language measures predicted language tract integrity in patients (adjusted R2 = 0.467) and controls (adjusted R2 = 0.483). Quantitative language analyses have both clinical and biological validity, offer a simple, helpful marker of both severity and underlying pathology, and provide a promising tool for schizophrenia research and clinical practice.

An update on the efficacy of anti-inflammatory agents for patients with schizophrenia: a meta-analysis.

BACKGROUND: Accumulating evidence shows that a propensity towards a pro-inflammatory status in the brain plays an important role in schizophrenia. Anti-inflammatory drugs might compensate this propensity. This study provides an update regarding the efficacy of agents with some anti-inflammatory actions for schizophrenia symptoms tested in randomized controlled trials (RCTs). METHODS: PubMed, Embase, the National Institutes of Health website (http://www.clinicaltrials.gov), and the Cochrane Database of Systematic Reviews were systematically searched for RCTs that investigated clinical outcomes. RESULTS: Our search yielded 56 studies that provided information on the efficacy of the following components on symptom severity: aspirin, bexarotene, celecoxib, davunetide, dextromethorphan, estrogens, fatty acids, melatonin, minocycline, N-acetylcysteine (NAC), pioglitazone, piracetam, pregnenolone, statins, varenicline, and withania somnifera extract. The results of aspirin [mean weighted effect size (ES): 0.30; n = 270; 95% CI (CI) 0.06-0.54], estrogens (ES: 0.78; n = 723; CI 0.36-1.19), minocycline (ES: 0.40; n = 946; CI 0.11-0.68), and NAC (ES: 1.00; n = 442; CI 0.60-1.41) were significant in meta-analysis of at least two studies. Subgroup analysis yielded larger positive effects for first-episode psychosis (FEP) or early-phase schizophrenia studies. Bexarotene, celecoxib, davunetide, dextromethorphan, fatty acids, pregnenolone, statins, and varenicline showed no significant effect. CONCLUSIONS: Some, but not all agents with anti-inflammatory properties showed efficacy. Effective agents were aspirin, estrogens, minocycline, and NAC. We observed greater beneficial results on symptom severity in FEP or early-phase schizophrenia.

Musical hallucinations and their relation with epilepsy.

Musical hallucinations are poorly understood phenomena. Their relation with epilepsy was first described over a century ago, but never systematically explored. We, therefore, reviewed the literature, and assessed all descriptions of musical hallucinations attributed to epileptic activity. Our search yielded 191 articles, which together describe 983 unique patients, with 24 detailed descriptions of musical hallucinations related to epilepsy. We also describe six of our own patients. Based on the phenomenological descriptions and neurophysiological data, we distinguish four subgroups of epilepsy-related musical hallucination, comprising auras/ictal, inter-ictal and post-ictal phenomena, and phenomena related to brain stimulation. The case descriptions suggest that musical hallucinations in epilepsy can be conceptualised as lying on a continuum with other auditory hallucinations, including verbal auditory hallucinations, and-notably-tinnitus. To account for the underlying mechanism we propose a Bayesian model involving top-down and bottom-up prediction errors within the auditory network that incorporates findings from EEG and MEG studies. An analysis of phenomenological characteristics, pharmacological triggers, and treatment effects suggests wider ramifications for understanding musical hallucinations. We, therefore, conclude that musical hallucinations in epilepsy open a window to understanding these phenomena in a variety of conditions.

Hallucinations in patients with borderline personality disorder: characteristics, severity, and relationship with schizotypy and loneliness.

OBJECTIVE: In patients with borderline personality disorder (BPD), data are lacking on characteristics and severity of hallucinations in modalities other than the auditory (verbal) type. The same applies to relationships between hallucinations and the severity of depression, anxiety, schizotypy, and loneliness. METHODS: In 60 female patients with BPD (37 also with hallucinations), this cross-sectional study explored characteristics and severity of (i) hallucinations and (ii) schizotypal features, (iii) severity of depression and anxiety, and (iv) loneliness, and the relationships between hallucinations and the other characteristics. RESULTS: In patients with hallucinations, 80% experienced hallucinations in more than one modality; in the different modalities, the characteristics of the hallucinations were similar. The criteria for loneliness were fulfilled in 81% and 48% of patients with and without hallucinations. Compared to patients with BPD without hallucinations, the presence of hallucinations was associated with higher scores for depression, anxiety, loneliness, and schizotypy. Furthermore, the severity of hallucinations showed a positive correlation with the severity of loneliness and schizotypy. CONCLUSION: Patients with BPD experienced hallucinations with characteristics similar to the more frequently studied auditory (verbal) hallucinations. Higher scores for schizotypy and loneliness indicate that patients with hallucinations had more characteristics of cluster A personality disorders.

Auditory hallucinations, top-down processing and language perception: a general population study.

BACKGROUND: Studies investigating the underlying mechanisms of hallucinations in patients with schizophrenia suggest that an imbalance in top-down expectations v. bottom-up processing underlies these errors in perception. This study evaluates this hypothesis by testing if individuals drawn from the general population who have had auditory hallucinations (AH) have more misperceptions in auditory language perception than those who have never hallucinated. METHODS: We used an online survey to determine the presence of hallucinations. Participants filled out the Questionnaire for Psychotic Experiences and participated in an auditory verbal recognition task to assess both correct perceptions (hits) and misperceptions (false alarms). A hearing test was performed to screen for hearing problems. RESULTS: A total of 5115 individuals from the general Dutch population participated in this study. Participants who reported AH in the week preceding the test had a higher false alarm rate in their auditory perception compared with those without such (recent) experiences. The more recent the AH were experienced, the more mistakes participants made. While the presence of verbal AH (AVH) was predictive for false alarm rate in auditory language perception, the presence of non-verbal or visual hallucinations were not. CONCLUSIONS: The presence of AVH predicted false alarm rate in auditory language perception, whereas the presence of non-verbal auditory or visual hallucinations was not, suggesting that enhanced top-down processing does not transfer across modalities. More false alarms were observed in participants who reported more recent AVHs. This is in line with models of enhanced influence of top-down expectations in persons who hallucinate.

Clozapine as a first- or second-line treatment in schizophrenia: a systematic review and meta-analysis.

OBJECTIVE: No consensus exists on whether clozapine should be prescribed in early stages of psychosis. This systematic review and meta-analysis therefore focus on the use of clozapine as first-line or second-line treatment in non-treatment-resistant patients. METHODS: Articles were eligible if they investigated clozapine compared to another antipsychotic as a first- or second-line treatment in non-treatment-resistant schizophrenia spectrum disorders (SCZ) patients and provided data on treatment response. We performed random-effects meta-analyses. RESULTS: Fifteen articles were eligible for the systematic review (N = 314 subjects on clozapine and N = 800 on other antipsychotics). Our meta-analysis comparing clozapine to a miscellaneous group of antipsychotics revealed a significant benefit of clozapine (Hedges' g = 0.220, P = 0.026, 95% CI = 0.026-0.414), with no evidence of heterogeneity. In addition, a sensitivity analysis revealed a significant benefit of clozapine over risperidone (Hedges' g = 0.274, P = 0.030, 95% CI = 0.027-0.521). CONCLUSION: The few eligible trials on this topic suggest that clozapine may be more effective than other antipsychotics when used as first- or second-line treatment. Only large clinical trials may comprehensively probe disease stage-dependent superiority of clozapine and investigate overall tolerability.

Clinical use of semantic space models in psychiatry and neurology: A systematic review and meta-analysis.

Verbal communication disorders are a hallmark of many neurological and psychiatric illnesses. Recent developments in computational analysis provide objective characterizations of these language abnormalities. We conducted a meta-analysis assessing semantic space models as a diagnostic or prognostic tool in psychiatric or neurological disorders. Diagnostic test accuracy analyses revealed reasonable sensitivity and specificity and high overall efficacy in differentiating between patients and controls (n=1680: Hedges' g =.73, p=.001). Analyses of full sentences (Hedges' g =.95 p <.0001) revealed a higher efficacy than single words (Hedges' g = .51, p <.0001). Specifically, models examining psychotic patients (Hedges' g =.96, p=.003) and those with autism (Hedges' g = .84, p <.0001) were highly effective. Our results show semantic space models are effective as a diagnostic tool in a variety of psychiatric and neurological disorders. The field is still exploratory in nature; techniques differ and models are only used to distinguish patients from healthy controls so far. Future research should aim to distinguish between disorders and perhaps explore newer semantic space tools like word2vec.