Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation.

Large language models (LLMs) such as Open AI's GPT-4 (which power ChatGPT) and Google's Gemini, built on artificial intelligence, hold immense potential to support, augment, or even eventually automate psychotherapy. Enthusiasm about such applications is mounting in the field as well as industry. These developments promise to address insufficient mental healthcare system capacity and scale individual access to personalized treatments. However, clinical psychology is an uncommonly high stakes application domain for AI systems, as responsible and evidence-based therapy requires nuanced expertise. This paper provides a roadmap for the ambitious yet responsible application of clinical LLMs in psychotherapy. First, a technical overview of clinical LLMs is presented. Second, the stages of integration of LLMs into psychotherapy are discussed while highlighting parallels to the development of autonomous vehicle technology. Third, potential applications of LLMs in clinical care, training, and research are discussed, highlighting areas of risk given the complex nature of psychotherapy. Fourth, recommendations for the responsible development and evaluation of clinical LLMs are provided, which include centering clinical science, involving robust interdisciplinary collaboration, and attending to issues like assessment, risk detection, transparency, and bias. Lastly, a vision is outlined for how LLMs might enable a new generation of studies of evidence-based interventions at scale, and how these studies may challenge assumptions about psychotherapy.

Key language markers of depression on social media depend on race.

Depression has robust natural language correlates and can increasingly be measured in language using predictive models. However, despite evidence that language use varies as a function of individual demographic features (e.g., age, gender), previous work has not systematically examined whether and how depression's association with language varies by race. We examine how race moderates the relationship between language features (i.e., first-person pronouns and negative emotions) from social media posts and self-reported depression, in a matched sample of Black and White English speakers in the United States. Our findings reveal moderating effects of race: While depression severity predicts I-usage in White individuals, it does not in Black individuals. White individuals use more belongingness and self-deprecation-related negative emotions. Machine learning models trained on similar amounts of data to predict depression severity performed poorly when tested on Black individuals, even when they were trained exclusively using the language of Black individuals. In contrast, analogous models tested on White individuals performed relatively well. Our study reveals surprising race-based differences in the expression of depression in natural language and highlights the need to understand these effects better, especially before language-based models for detecting psychological phenomena are integrated into clinical practice.

A transdiagnostic, dimensional classification of anxiety shows improved parsimony and predictive noninferiority to DSM.

The current conceptualization of anxiety in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5)-which includes 11 anxiety disorders plus additional anxiety-related conditions-does not align with accumulating evidence that anxiety is transdiagnostic and dimensional in nature. Transdiagnostic dimensional anxiety models have been proposed, yet they measure anxiety at either a very broad (e.g., "anxiety") or very narrow (e.g., "performance anxiety") level, overlooking intermediate properties of anxiety that cut across DSM disorders. Using indicators from a well-validated semistructured interview of anxiety-related disorders, we constructed intermediate-level transdiagnostic dimensions representing the intensity, avoidance, pervasiveness, and onset of anxiety. We captured these content-agnostic dimensions in a sample representing varying levels and forms of anxiety (N = 268), including individuals with generalized anxiety disorder, social anxiety disorder, panic disorder, agoraphobia, specific phobia, separation anxiety disorder, posttraumatic stress disorder, and obsessive-compulsive disorder (n = 205) and individuals with no psychopathology (n = 63). In preregistered analyses, our dimensional anxiety model showed noninferiority to DSM-5 diagnoses in predicting concurrent and prospective measures of anxiety-related impairment, anxiety vulnerabilities, comorbid depression, and suicidal ideation. These results held regardless of whether the dimensions were combined into a single composite or retained as separate components. Our transdiagnostic dimensional model offers meaningful gains in parsimony over DSM, with no loss of predictive power. This project provides a methodological framework for the empirical evaluation of other transdiagnostic dimensional models of psychopathology that have been proposed as alternatives to the DSM. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Depression and anxiety have distinct and overlapping language patterns: Results from a clinical interview.

Depression has been associated with heightened first-person singular pronoun use (I-usage; e.g., "I," "my") and negative emotion words. However, past research has relied on nonclinical samples and nonspecific depression measures, raising the question of whether these features are unique to depression vis-à-vis frequently co-occurring conditions, especially anxiety. Using structured questions about recent life changes or difficulties, we interviewed a sample of individuals with varying levels of depression and anxiety (N = 486), including individuals in a major depressive episode (n = 228) and/or diagnosed with generalized anxiety disorder (n = 273). Interviews were transcribed to provide a natural language sample. Analyses isolated language features associated with gold standard, clinician-rated measures of depression and anxiety. Many language features associated with depression were in fact shared between depression and anxiety. Language markers with relative specificity to depression included I-usage, sadness, and decreased positive emotion, while negations (e.g., "not," "no"), negative emotion, and several emotional language markers (e.g., anxiety, stress, depression) were relatively specific to anxiety. Several of these results were replicated using a self-report measure designed to disentangle components of depression and anxiety. We next built machine learning models to detect severity of common and specific depression and anxiety using only interview language. Individuals' speech characteristics during this brief interview predicted their depression and anxiety severity, beyond other clinical and demographic variables. Depression and anxiety have partially distinct patterns of expression in spoken language. Monitoring of depression and anxiety severity via language can augment traditional assessment modalities and aid in early detection. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Perseverative thinking is associated with features of spoken language.

Perseverative thinking (PT), such as rumination or worry, is a transdiagnostic process implicated in the onset and maintenance of emotional disorders. Existing measures of PT are limited by demand and expectancy effects, cognitive biases, and reflexivity, leading to calls for unobtrusive, behavioral measures. In response, we developed a behavioral measure of PT based on language. A mixed sample of 188 participants with major depressive disorder, generalized anxiety disorder, or no psychopathology completed self-report PT measures. Participants were also interviewed, providing a natural language sample. We examined language features associated with PT, then built a language-based PT model and examined its predictive power. PT was associated with multiple language features, most notably I-usage (e.g., "I", "me"; ß = 0.25) and negative emotion language (e.g., "anxiety", "difficult"; ß = 0.19). In machine learning analyses, language features accounted for 14% of the variance in self-reported PT. Language-based PT predicted the presence and severity of depression and anxiety, psychiatric comorbidity, and treatment seeking, with effects in the r = 0.15-0.41 range. PT has face-valid linguistic correlates and our language-based measure holds promise for assessing PT unobtrusively. With further development, this measure could be used to passively detect PT for deployment of "just-in-time" interventions.

Lithium continuation therapy following ketamine in patients with treatment resistant unipolar depression: a randomized controlled trial.

The N-methyl-D-aspartate (NMDA) receptor antagonist ketamine is associated with rapid but transient antidepressant effects in patients with treatment resistant unipolar depression (TRD). Based on work suggesting that ketamine and lithium may share overlapping mechanisms of action, we tested lithium compared to placebo as a continuation strategy following ketamine in subjects with TRD. Participants who met all eligibility criteria and showed at least an initial partial response to a single intravenous infusion of ketamine 0.5 mg/kg were randomized under double-blind conditions to lithium or matching placebo before receiving an additional three infusions of ketamine. Subsequent to the ketamine treatments, participants remained on lithium or placebo during a double-blind continuation phase. The primary study outcome was depression severity as measured by the Montgomery-Åsberg Depression Rating Scale compared between the two groups at Study Day 28, which occurred ~2 weeks following the final ketamine of four infusions. Forty-seven participants with TRD were enrolled in the study and underwent an initial ketamine infusion, of whom 34 participants were deemed to have at least a partial antidepressant response and were eligible for randomization. Comparison between treatment with daily oral lithium (n = 18) or matching placebo (n = 16) at the primary outcome showed no difference in depression severity between groups (t32 = 0.11, p = 0.91, 95% CI [-7.87, 8.76]). There was no difference between lithium and placebo in continuing the acute antidepressant response to ketamine. The identification of a safe and effective strategy for preventing depression relapse following an acute course of ketamine treatment remains an important goal for future studies.