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.

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.

Longitudinal clinical and functional outcome in distinct cognitive subgroups of first-episode psychosis: a cluster analysis

BACKGROUND

Cognitive deficits may be characteristic for only a subgroup of first-episode psychosis (FEP) and the link with clinical and functional outcomes is less profound than previously thought. This study aimed to identify cognitive subgroups in a large sample of FEP using a clustering approach with healthy controls as a reference group, subsequently linking cognitive subgroups to clinical and functional outcomes.

METHODS

204 FEP patients were included. Hierarchical cluster analysis was performed using baseline brief assessment of cognition in schizophrenia (BACS). Cognitive subgroups were compared to 40 controls and linked to longitudinal clinical and functional outcomes (PANSS, GAF, self-reported WHODAS 2.0) up to 12-month follow-up.

RESULTS

Three distinct cognitive clusters emerged: relative to controls, we found one cluster with preserved cognition (n = 76), one moderately impaired cluster (n = 74) and one severely impaired cluster (n = 54). Patients with severely impaired cognition had more severe clinical symptoms at baseline, 6- and 12-month follow-up as compared to patients with preserved cognition. General functioning (GAF) in the severely impaired cluster was significantly lower than in those with preserved cognition at baseline and showed trend-level effects at 6- and 12-month follow-up. No significant differences in self-reported functional outcome (WHODAS 2.0) were present.

CONCLUSIONS

Current results demonstrate the existence of three distinct cognitive subgroups, corresponding with clinical outcome at baseline, 6- and 12-month follow-up. Importantly, the cognitively preserved subgroup was larger than the severely impaired group. Early identification of discrete cognitive profiles can offer valuable information about the clinical outcome but may not be relevant in predicting self-reported functional outcomes.

Natural Language Processing Markers for Psychosis and Other Psychiatric Disorders: Emerging Themes and Research Agenda From a Cross-Linguistic Workshop

This workshop summary on natural language processing (NLP) markers for psychosis and other psychiatric disorders presents some of the clinical and research issues that NLP markers might address and some of the activities needed to move in that direction. We propose that the optimal development of NLP markers would occur in the context of research efforts to map out the underlying mechanisms of psychosis and other disorders. In this workshop, we identified some of the challenges to be addressed in developing and implementing NLP markers-based Clinical Decision Support Systems (CDSSs) in psychiatric practice, especially with respect to psychosis. Of note, a CDSS is meant to enhance decision-making by clinicians by providing additional relevant information primarily through software (although CDSSs are not without risks). In psychiatry, a field that relies on subjective clinical ratings that condense rich temporal behavioral information, the inclusion of computational quantitative NLP markers can plausibly lead to operationalized decision models in place of idiosyncratic ones, although ethical issues must always be paramount.

Syntactic Network Analysis in Schizophrenia-Spectrum Disorders

BACKGROUND

Language anomalies are a hallmark feature of schizophrenia-spectrum disorders (SSD). Here, we used network analysis to examine possible differences in syntactic relations between patients with SSD and healthy controls. Moreover, we assessed their relationship with sociodemographic factors, psychotic symptoms, and cognitive functioning, and we evaluated whether the quantification of syntactic network measures has diagnostic value.

STUDY DESIGN

Using a semi-structured interview, we collected speech samples from 63 patients with SSD and 63 controls. Per sentence, a syntactic representation (ie, parse tree) was obtained and used as input for network analysis. The resulting syntactic networks were analyzed for 11 local and global network measures, which were compared between groups using multivariate analysis of covariance, considering the effects of age, sex, and education.

RESULTS

Patients with SSD and controls significantly differed on most syntactic network measures. Sex had a significant effect on syntactic measures, and there was a significant interaction between sex and group, as the anomalies in syntactic relations were most pronounced in women with SSD. Syntactic measures were correlated with negative symptoms (Positive and Negative Syndrome Scale) and cognition (Brief Assessment of Cognition in Schizophrenia). A random forest classifier based on the best set of network features distinguished patients from controls with 74% cross-validated accuracy.

CONCLUSIONS

Examining syntactic relations from a network perspective revealed robust differences between patients with SSD and healthy controls, especially in women. Our results support the validity of linguistic network analysis in SSD and have the potential to be used in combination with other automated language measures as a marker for SSD.

Semantic and Acoustic Markers in Schizophrenia-Spectrum Disorders: A Combinatory Machine Learning Approach

BACKGROUND AND HYPOTHESIS

Speech is a promising marker to aid diagnosis of schizophrenia-spectrum disorders, as it reflects symptoms like thought disorder and negative symptoms. Previous approaches made use of different domains of speech for diagnostic classification, including features like coherence (semantic) and form (acoustic). However, an examination of the added value of each domain when combined is lacking as of yet. Here, we investigate the acoustic and semantic domains separately and combined.

STUDY DESIGN

Using semi-structured interviews, speech of 94 subjects with schizophrenia-spectrum disorders (SSD) and 73 healthy controls (HC) was recorded. Acoustic features were extracted using a standardized feature-set, and transcribed interviews were used to calculate semantic word similarity using word2vec. Random forest classifiers were trained for each domain. A third classifier was used to combine features from both domains; 10-fold cross-validation was used for each model.

RESULTS

The acoustic random forest classifier achieved 81% accuracy classifying SSD and HC, while the semantic domain classifier reached an accuracy of 80%. Joining features from the two domains, the combined classifier reached 85% accuracy, significantly improving on separate domain classifiers. For the combined classifier, top features were fragmented speech from the acoustic domain and variance of similarity from the semantic domain.

CONCLUSIONS

Both semantic and acoustic analyses of speech achieved ~80% accuracy in classifying SSD from HC. We replicate earlier findings per domain, additionally showing that combining these features significantly improves classification performance. Feature importance and accuracy in combined classification indicate that the domains measure different, complementing aspects of speech.

[Automated speech analysis can distinguish frontotemporal dementia from depression: a pilot study]

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]

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.

Speech as a Biomarker for Depression

BACKGROUND

Depression is a debilitating disorder that at present lacks a reliable biomarker to aid in diagnosis and early detection. Recent advances in computational analytic approaches have opened up new avenues in developing such a biomarker by taking advantage of the wealth of information that can be extracted from a person's speech.

OBJECTIVE

The current review provides an overview of the latest findings in the rapidly evolving field of computational language analysis for the detection of depression. We cover a wide range of both acoustic and content-related linguistic features, data types (i.e., spoken and written language), and data sources (i.e., lab settings, social media, and smartphone-based). We put special focus on the current methodological advances with regard to feature extraction and computational modeling techniques. Furthermore, we pay attention to potential hurdles in the implementation of automatic speech analysis.

CONCLUSION

Depressive speech is characterized by several anomalies, such as lower speech rate, less pitch variability and more self-referential speech. With current computational modeling techniques, such features can be used to detect depression with an accuracy of up to 91%. The performance of the models is optimized when machine learning techniques are implemented that suit the type and amount of data. Recent studies now work towards further optimization and generalizability of the computational language models to detect depression. Finally, privacy and ethical issues are of paramount importance to be addressed when automatic speech analysis techniques are further implemented in, for example, smartphones. Altogether, computational speech analysis is well underway towards becoming an effective diagnostic aid for depression.

Characterizing speech heterogeneity in schizophrenia-spectrum disorders

Schizophrenia-spectrum disorders (SSD) are highly heterogeneous in risk factors, symptom characteristics, and disease course outcome. Although speech anomalies have long been recognized as a core symptom of SSD, speech markers are an unexplored source of symptom heterogeneity that may be informative in recognizing relevant subtypes. This study investigated speech heterogeneity and its relation to clinical characteristics in a large sample of patients with SSD and healthy controls. Speech samples were obtained from 142 patients with SSD and 147 healthy controls by means of open-ended interviews. Speech was analyzed using standardized open-source acoustic speech software. Hierarchical clustering was conducted using acoustic speech markers. Symptom severity was rated with the Positive and Negative Syndrome Scale, and cognition was assessed with the Brief Assessment of Cognition for Schizophrenia. Three speech clusters could be distinguished in the patient group that differed regarding speech properties, independent of medication use. One cluster was characterized by mild speech disturbances, while two severely impaired clusters were recognized (fragmented speakers and prolonged pausers). Both clusters with severely impaired speech had more severe cognitive dysfunction than the mildly impaired speakers. Prolonged pausers specifically had difficulties with memory-related tasks. Prolonged pausing, as opposed to fragmented speaking, related to chronic active psychosis and refractory psychotic symptoms. Based on speech clustering, subtypes of patients emerged with distinct disease trajectories, symptomatology, and cognitive functioning. The identification of clinically relevant subgroups within SSD may help to characterize distinct profiles and benefit the tailoring of early intervention and improvement of long-term functional outcome. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

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.

Quantified language connectedness in schizophrenia-spectrum disorders

Language abnormalities are a core symptom of schizophrenia-spectrum disorders and could serve as a potential diagnostic marker. Natural language processing enables quantification of language connectedness, which may be lower in schizophrenia-spectrum disorders. Here, we investigated connectedness of spontaneous speech in schizophrenia-spectrum patients and controls and determine its accuracy in classification. Using a semi-structured interview, speech of 50 patients with a schizophrenia-spectrum disorder and 50 controls was recorded. Language connectedness in a semantic word2vec model was calculated using consecutive word similarity in moving windows of increasing sizes (2-20 words). Mean, minimal and variance of similarity were calculated per window size and used in a random forest classifier to distinguish patients and healthy controls. Classification based on connectedness reached 85% cross-validated accuracy, with 84% specificity and 86% sensitivity. Features that best discriminated patients from controls were variance of similarity at window sizes between 5 and 10. We show impaired connectedness in spontaneous speech of patients with schizophrenia-spectrum disorders even in patients with low ratings of positive symptoms. Effects were most prominent at the level of sentence connectedness. The high sensitivity, specificity and tolerability of this method show that language analysis is an accurate and feasible digital assistant in diagnosing schizophrenia-spectrum disorders.

To continue or not to continue? Antipsychotic medication maintenance versus dose-reduction/discontinuation in first episode psychosis: HAMLETT, a pragmatic multicenter single-blind randomized controlled trial

BACKGROUND

Antipsychotic medication is effective for symptomatic treatment in schizophrenia-spectrum disorders. After symptom remission, continuation of antipsychotic treatment is associated with lower relapse rates and lower symptom severity compared to dose reduction/discontinuation. Therefore, most guidelines recommend continuation of treatment with antipsychotic medication for at least 1 year. Recently, however, these guidelines have been questioned as one study has shown that more patients achieved long-term functional remission in an early discontinuation condition-a finding that was not replicated in another recently published long-term study.

METHODS/DESIGN

The HAMLETT (Handling Antipsychotic Medication Long-term Evaluation of Targeted Treatment) study is a multicenter pragmatic single-blind randomized controlled trial in two parallel conditions (1:1) investigating the effects of continuation versus dose-reduction/discontinuation of antipsychotic medication after remission of a first episode of psychosis (FEP) on personal and social functioning, psychotic symptom severity, and health-related quality of life. In total 512 participants will be included, aged between 16 and 60 years, in symptomatic remission from a FEP for 3-6 months, and for whom psychosis was not associated with severe or life-threatening self-harm or violence. Recruitment will take place at 24 Dutch sites. Patients are randomized (1:1) to: continuation of antipsychotic medication until at least 1 year after remission (original dose allowing a maximum reduction of 25%, or another antipsychotic drug in similar dose range); or gradual dose reduction till eventual discontinuation of antipsychotics according to a tapering schedule. If signs of relapse occur in this arm, medication dose can be increased again. Measurements are conducted at baseline, at 3, and 6 months post-baseline, and yearly during a follow-up period of 4 years.

DISCUSSION

The HAMLETT study will offer evidence to guide patients and clinicians regarding questions concerning optimal treatment duration and when to taper off medication after remission of a FEP. Moreover, it may provide patient characteristics associated with safe dose reduction with a minimal risk of relapse.

TRIAL STATUS

Protocol version 1.3, October 2018. The study is active and currently recruiting patients (since September 2017), with the first 200 participants by the end of 2019. We anticipate completing recruitment in 2022 and final assessments (including follow-up 3.5 years after phase one) in 2026.

TRIAL REGISTRATION

European Clinical Trials Database, EudraCT number 2017-002406-12. Registered 7 June 2017.