Multimodal Correlates of Cannabis Use among U.S. Veterans with Bipolar Disorder: An Integrated Study of Clinical, Cognitive, and Functional Outcomes.

Objective: Cannabis use (CU) is common among persons with bipolar disorder (BD). Evidence suggests that CU is associated with poorer outcomes among persons with BD; however, these findings remain inconsistent. The present exploratory study aims to examine clinical, functional, and cognitive correlates of CU among persons with BD. Methods: U.S. veterans with BD type I who participated in a large-scale, nationwide study were categorized into four groups: current CU, past CU, past other drug use, and no drug use. Bivariate analyses, univariate analyses of covariance, and Levene's Test for Equality of Variance were used to compare groups on clinical, cognitive, and functional measures. Results: Of 254 (84.6% male) veterans with BD type I included in the analyses, 13 (5.1%) had current CU, 37 (14.5%) past CU, 77 (30.3%) past other drug use, and 127 (50%) reported no drug use. BD with CU was associated with post-traumatic stress disorder (PTSD) and experiencing lifetime suicidal ideation. Notably, current CU was associated with higher working memory performance, compared to both past CU and no drug use. Likewise, current CU was associated with higher functional capacity, compared to past CU as well as no drug use. Conclusions: These findings contribute to the growing literature on the complex effects of cannabis on BD. As the commercialization and legalization of cannabis increases, further research in this area is warranted to quantify posed risks to this population, and thereby guide clinical decision-making.

ChatGPT and Bard exhibit spontaneous citation fabrication during psychiatry literature search.

ChatGPT (Generative Pre-Trained Transformer) is a large language model (LLM), which comprises a neural network that has learned information and patterns of language use from large amounts of text on the internet. ChatGPT, introduced by OpenAI, responds to human queries in a conversational manner. Here, we aimed to assess whether ChatGPT could reliably produce accurate references to supplement the literature search process. We describe our March 2023 exchange with ChatGPT, which generated thirty-five citations, two of which were real. 12 citations were similar to actual manuscripts (e.g., titles with incorrect author lists, journals, or publication years) and the remaining 21, while plausible, were in fact a pastiche of multiple existent manuscripts. In June 2023, we re-tested ChatGPT's performance and compared it to that of Google's GPT counterpart, Bard 2.0. We investigated performance in English, as well as in Spanish and Italian. Fabrications made by LLMs, including erroneous citations, have been called "hallucinations"; we discuss reasons for which this is a misnomer. Furthermore, we describe potential explanations for citation fabrication by GPTs, as well as measures being taken to remedy this issue, including reinforcement learning. Our results underscore that output from conversational LLMs should be verified.

Study protocol for a multi-level cross-sectional study on the equitable reach and implementation of coordinated specialty care for early psychosis.

BACKGROUND: Approximately 115,000 young adults will experience their first episode of psychosis (FEP) each year in the USA. Coordinated specialty care (CSC) for early psychosis is an evidence-based early intervention model that has demonstrated effectiveness by improving quality of life and reducing psychiatric symptoms for many individuals. Over the last decade, there has significant increase in the implementation of CSC programs throughout the USA. However, prior research has revealed difficulties among individuals and their family members accessing CSC. Research has also shown that CSC programs often report the limited reach of their program to underserved populations and communities (e.g., ethnoracial minorities, rural and low socioeconomic neighborhoods). Dissemination and implementation research focused on the equitable reach and implementation of CSC is needed to address disparities at the individual level. METHODS: The proposed study will create a novel integrative multi-level geospatial database of CSC programs implemented throughout the USA that will include program-level data (e.g., geocoded location, capacity, setting, role availability), provider-level data (race, ethnicity, professional credentials), and neighborhood-level census data (e.g., residential segregation, ethnic density, area deprivation, rural-urban continua, public transit time). This database will be used to characterize variations in CSC programs by geographical location and examine the overall reach CSC programs to specific communities. The quantitative data will be combined with qualitative data from state administrators, providers, and service users that will inform the development of dissemination tools, such as an interactive dashboard, that can aid decision making. DISCUSSION: Findings from this study will highlight the impact of outer contextual determinants on implementation and reach of mental health services, and will serve to inform the future implementation of CSC programs with a primary focus on equity.

Linguistic correlates of suicidal ideation in youth at clinical high-risk for psychosis.

Suicidal ideation (SI) is prevalent among individuals at clinical high-risk for psychosis (CHR). Natural language processing (NLP) provides an efficient method to identify linguistic markers of suicidality. Prior work has demonstrated that an increased use of "I", as well as words with semantic similarity to "anger", "sadness", "stress" and "lonely", are correlated with SI in other cohorts. The current project analyzes data collected in an SI supplement to an NIH R01 study of thought disorder and social cognition in CHR. This study is the first to use NLP analyses of spoken language to identify linguistic correlates of recent suicidal ideation among CHR individuals. The sample included 43 CHR individuals, 10 with recent suicidal ideation and 33 without, as measured by the Columbia-Suicide Severity Rating Scale, as well as 14 healthy volunteers without SI. NLP methods include part-of-speech (POS) tagging, a GoEmotions-trained BERT Model, and Zero-Shot Learning. As hypothesized, individuals at CHR for psychosis who endorsed recent SI utilized more words with semantic similarity to "anger" compared to those who did not. Words with semantic similarity to "stress", "loneliness", and "sadness" were not significantly different between the two CHR groups. Contrary to our hypotheses, CHR individuals with recent SI did not use the word "I" more than those without recent SI. As anger is not characteristic of CHR, findings have implications for the consideration of subthreshold anger-related sentiment in suicidal risk assessment. As NLP is scalable, findings suggest that language markers may improve suicide screening and prediction in this population.

Differential Expression of Anomalous Self-Experiences in Spontaneous Speech in Clinical High-Risk and Early-Course Psychosis Quantified by Natural Language Processing.

BACKGROUND: Basic self-disturbance, or anomalous self-experiences (ASEs), is a core feature of the schizophrenia spectrum. We propose a novel method of natural language processing to quantify ASEs in spoken language by direct comparison to an inventory of self-disturbance, the Inventory of Psychotic-Like Anomalous Self-Experiences (IPASE). We hypothesized that there would be increased similarity in open-ended speech to the IPASE items in individuals with early-course psychosis (PSY) compared with healthy individuals, with clinical high-risk (CHR) individuals intermediate in similarity. METHODS: Open-ended interviews were obtained from 170 healthy control participants, 167 CHR participants, and 89 PSY participants. We calculated the semantic similarity between IPASE items and "I" sentences from transcribed speech samples using S-BERT (Sentence Bidirectional Encoder Representation from Text). Kolmogorov-Smirnov tests were used to compare distributions across groups. A nonnegative matrix factorization of cosine similarity was performed to rank IPASE items. RESULTS: Spoken language of CHR individuals had the greatest semantic similarity to IPASE items when compared to both healthy control (s = 0.44, p < 10-14) and PSY (s = 0.36, p < 10-6) individuals, while IPASE scores were higher among PSY than CHR group participants. In addition, the nonnegative matrix factorization approach produced a data-driven domain that differentiated the CHR group from the others. CONCLUSIONS: We found that open-ended interviews elicited language with increased semantic similarity to the IPASE by participants in the CHR group compared with patients with psychosis. This demonstrates the utility of these methods for differentiating patients from healthy control participants. This complementary approach has the capacity to scale to large studies investigating phenomenological features of schizophrenia and potentially other clinical populations.