Happy thoughts: What computational assessment of connectedness and emotional words can inform about early stages of psychosis

Quantifying abnormal emotion processing: A novel computational assessment method and application in schizophrenia

Abnormal emotion processing is a core feature of schizophrenia spectrum disorders (SSDs) that encompasses multiple operations. While deficits in some areas have been well-characterized, we understand less about abnormalities in the emotion processing that happens through language, which is highly relevant for social life. Here, we introduce a novel method using deep learning to estimate emotion processing rapidly from spoken language, testing this approach in male-identified patients with SSDs (n = 37) and healthy controls (n = 51). Using free responses to evocative stimuli, we derived a measure of appropriateness, or "emotional alignment" (EA). We examined psychometric characteristics of EA and its sensitivity to a single-dose challenge of oxytocin, a neuropeptide shown to enhance the salience of socioemotional information in SSDs. Patients showed impaired EA relative to controls, and impairment correlated with poorer social cognitive skill and more severe motivation and pleasure deficits. Adding EA to a logistic regression model with language-based measures of formal thought disorder (FTD) improved classification of patients versus controls. Lastly, oxytocin administration improved EA but not FTD among patients. While additional validation work is needed, these initial results suggest that an automated assay using spoken language may be a promising approach to assess emotion processing in SSDs.

Natural language processing for mental health interventions: a systematic review and research framework

Neuropsychiatric disorders pose a high societal cost, but their treatment is hindered by lack of objective outcomes and fidelity metrics. AI technologies and specifically Natural Language Processing (NLP) have emerged as tools to study mental health interventions (MHI) at the level of their constituent conversations. However, NLP's potential to address clinical and research challenges remains unclear. We therefore conducted a pre-registered systematic review of NLP-MHI studies using PRISMA guidelines (osf.io/s52jh) to evaluate their models, clinical applications, and to identify biases and gaps. Candidate studies (n = 19,756), including peer-reviewed AI conference manuscripts, were collected up to January 2023 through PubMed, PsycINFO, Scopus, Google Scholar, and ArXiv. A total of 102 articles were included to investigate their computational characteristics (NLP algorithms, audio features, machine learning pipelines, outcome metrics), clinical characteristics (clinical ground truths, study samples, clinical focus), and limitations. Results indicate a rapid growth of NLP MHI studies since 2019, characterized by increased sample sizes and use of large language models. Digital health platforms were the largest providers of MHI data. Ground truth for supervised learning models was based on clinician ratings (n = 31), patient self-report (n = 29) and annotations by raters (n = 26). Text-based features contributed more to model accuracy than audio markers. Patients' clinical presentation (n = 34), response to intervention (n = 11), intervention monitoring (n = 20), providers' characteristics (n = 12), relational dynamics (n = 14), and data preparation (n = 4) were commonly investigated clinical categories. Limitations of reviewed studies included lack of linguistic diversity, limited reproducibility, and population bias. A research framework is developed and validated (NLPxMHI) to assist computational and clinical researchers in addressing the remaining gaps in applying NLP to MHI, with the goal of improving clinical utility, data access, and fairness.

Speech as a Graph: Developmental Perspectives on the Organization of Spoken Language

Language has been used as a privileged window to investigate mental processes. More recently, descriptions of psychopathological symptoms have been analyzed with the help of natural language processing tools. An example is the study of speech organization using graph theoretical approaches that began approximately 10 years ago. After its application in different areas, there is a need to better characterize what aspects can be associated with typical and atypical behavior throughout the lifespan, given the variables related to aging as well as biological and social contexts. The precise quantification of mental processes assessed through language may allow us to disentangle biological/social markers by looking at naturalistic protocols in different contexts. In this review, we discuss 10 years of studies in which word recurrence graphs were adopted to characterize the chain of thoughts expressed by individuals while producing discourse. Initially developed to understand formal thought disorder in the context of psychotic syndromes, this line of research has been expanded to understand the atypical development in different stages of psychosis and differential diagnosis (such as dementia) as well as the typical development of thought organization in school-age children/teenagers in naturalistic and school-based protocols. We comment on the effects of environmental factors, such as education and reading habits (in monolingual and bilingual contexts), in clinical and nonclinical populations at different developmental stages (from childhood to older adulthood, considering aging effects on cognition). Looking toward the future, there is an opportunity to use word recurrence graphs to address complex questions that consider biological/social factors within a developmental perspective in typical and atypical contexts.

Lower cohesion and altered first-person pronoun usage in the spoken life narratives of individuals with schizophrenia

Usage of computational tools to quantify language disturbances among individuals with psychosis is increasing, improving measurement efficiency and access to fine-grained constructs. However, few studies apply automated linguistic analysis to life narratives in this population. Such research could facilitate the measurement of psychosis-relevant constructs such as sense of agency, capacity to organize one's personal history, narrative richness, and perceptions of the roles that others play in one's life. Furthermore, research is needed to understand how narrative linguistic features relate to cognitive and social functioning. In the present study, individuals with schizophrenia (n = 32) and individuals without a psychotic disorder (n = 15) produced personal life narratives within the Indiana Psychiatric Illness Interview. Narratives were analyzed using the Coh-Metrix computational tool. Linguistic variables analyzed were indices of connections within causal and goal-driven speech (deep cohesion), unique word usage (lexical diversity), and pronoun usage. Individuals with schizophrenia compared to control participants produced narratives that were lower in deep cohesion, contained more first-person singular pronouns, and contained fewer first-person plural pronouns. Narratives did not significantly differ between groups in lexical diversity, third-person pronoun usage, or total word count. Cognitive-linguistic relationships emerged in the full sample, including significant correlations between greater working memory capacity and greater deep cohesion and lexical diversity. In the schizophrenia group, social problem-solving abilities did not correlate with linguistic variables but were associated with cognition. Findings highlight the relevance of psychotherapies which aim to promote recovery among individuals with psychosis through the construction of coherent life narratives and increasing agency and social connectedness.

LSD and language: Decreased structural connectivity, increased semantic similarity, changed vocabulary in healthy individuals

Language has been explored as a window into the mind. Psychedelics, known to affect perception and cognition, seem to change language, but a systematic, time-dependent exploration is lacking. Therefore, we aimed at mapping the psychedelic effects on language over the time course of the acute and sub-acute effects in an explorative manner. For this, 24 healthy volunteers (age [mean±SD, range]: 35±11, 25-61 years; 33% women) received 50 μg lysergic acid diethylamide (LSD) or inactive placebo in a randomized, double-blind, placebo-controlled, crossover study. We assessed different language productions (experience reporting, storytelling), components (structure, semantics, vocabulary) and time points (+0 h to +24 h). Language productions included 5-min experience reporting (+1.5 h, +6.5 h) and 1-min storytelling (+0 h, +2 h, +4 h, +6 h, +24 h). Language structure was assessed by computing speech topology (SpeechGraphs), semantics by semantic distances (FastText), vocabulary by word categories (LIWC). LSD, compared to placebo, changed language structure, including decreased verbosity, lexicon, global and local connectivity (+1.5 h to +4 h); decreased semantic distances between neighbouring words and overall words (+2 h to +24 h); and changed vocabulary related to grammar, persons, time, space and biological processes (+1.5 h to +24 h). In conclusion, low to moderate LSD doses changed language over diverse production types, components and time points. While simpler and disconnected structure and semantic similarity might reflect cognitive impairments, changed vocabulary might reflect subjective perceptions. Therefore, language under LSD might provide a window into the psychedelic mind and automated language quantifications should be better explored as valuable tools to yield more unconstrained insights into psychedelic perception and cognition.

How can computational tools help to understand language patterns in mental suffering considering social diversity

The complex interaction between biological and social factors challenges measuring human behavior. Language has been a crucial source of information that mirrors inner processes like thoughts. The development of a novel computational strategy that helps to understand language needs to consider social factors that could also impact human behavior. Ten years ago, I developed a computational approach based on graph theory to measure structural aspects of the narrative's mental organization expressed in spontaneous oral reports. It was possible to measure the decrease in narrative graph connectedness associated with the schizophrenia diagnosis and negative symptoms severity. However, I was worried that the psychiatric field neglected factors from diverse social realities (such as poor access to education). Formal education impacts language by mastering grammar and syntax. Changes in language structure could be related to symptoms and lack of exposure to formal education. Indeed, the same connectedness markers increase according to typical cognitive and academic development. In this paper, I describe the reasons and methods for investigating both factors (psychiatric symptoms and formal education) on language patterns. Further, I evaluate concerns and future challenges of using computational strategies that include social diversity in mental health conditions.