Betsy Stade

All Publications

• Generative artificial intelligence in posttraumatic stress disorder treatment: Exploring five different use cases. Journal of traumatic stress Held, P., Stade, E. C., Dondanville, K., Wiltsey Stirman, S. 2025

  Abstract

  Posttraumatic stress disorder (PTSD) is a prevalent and debilitating condition, yet many individuals face substantial barriers to accessing evidence-based interventions. Advances in generative artificial intelligence (AI), particularly large language models (LLMs), have generated optimism about improving access and care. We present five emerging use cases for clinical AI tools in the context of PTSD treatment, some of which were presented as part of a symposium at the 40th Annual Meeting of the International Society for Traumatic Stress Studies. The first two use cases involve AI-assisted training tools. The third use case focuses on an AI-assisted automated fidelity rating system aimed at improving adherence to evidence-based PTSD protocols. The last two use cases feature AI-assisted therapy tools. Although AI-based innovations hold the promise of enhancing the reach and consistency of evidence-based PTSD interventions, they also raise important ethical and safety challenges, including risk of bias, threats to patient privacy, and the question of how to incorporate clinical oversight. Ongoing collaboration among multidisciplinary teams involving clinicians, researchers, and technology developers will be essential to ensuring that AI tools remain patient-centered, ethically sound, and effective.

  View details for DOI 10.1002/jts.23188

  View details for PubMedID 40736259

• Readiness Evaluation for AI-Mental Health Deployment and Implementation (READI): A Review and Proposed Framework. Technology, mind, and behavior Stade, E. C., Eichstaedt, J. C., Kim, J. P., Stirman, S. W. 2025; 6 (2)

  Abstract

  While generative artificial intelligence (AI) may lead to technological advances in the mental health field, it poses safety risks for mental health service consumers. Furthermore, clinicians and healthcare systems must attend to safety and ethical considerations prior to deploying these AI-mental health technologies. To ensure the responsible deployment of AI-mental health applications, a principled method for evaluating and reporting on AI-mental health applications is needed. We conducted a narrative review of existing frameworks and criteria (from the mental health, healthcare, and AI fields) relevant to the evaluation of AI-mental health applications. We provide a summary and analysis of these frameworks, with a particular emphasis on the unique needs of the AI-mental health intersection. Existing frameworks contain areas of convergence (e.g., frequent emphasis on safety, privacy/confidentiality, effectiveness, and equity) that are relevant to the evaluation of AI-mental health applications. However, current frameworks are insufficiently tailored to unique considerations for AI and mental health. To address this need, we introduce the Readiness Evaluation for AI-Mental Health Deployment and Implementation (READI) framework for mental health applications. The READI framework comprises considerations of Safety, Privacy/Confidentiality, Equity, Effectiveness, Engagement, and Implementation. The READI framework outlines key criteria for assessing the readiness of AI-mental health applications for clinical deployment, offering a structured approach for evaluating these technologies and reporting findings.

  View details for DOI 10.1037/tmb0000163

  View details for PubMedID 41048253

  View details for PubMedCentralID PMC12494062

• Reply to Wang: Clarifying model performance and language markers of depression across races. Proceedings of the National Academy of Sciences of the United States of America Rai, S., Stade, E. C., Giorgi, S., Francisco, A., Ganesan, A. V., Ungar, L. H., Curtis, B., Guntuku, S. C. 2024; 121 (31): e2410449121

  View details for DOI 10.1073/pnas.2410449121

  View details for PubMedID 39052830

• Reply to De Freitas: Social media language explains less of the variance in depression of Black individuals than of White individuals. Proceedings of the National Academy of Sciences of the United States of America Rai, S., Stade, E. C., Giorgi, S., Francisco, A., Ungar, L. H., Curtis, B., Guntuku, S. C. 2024; 121 (29): e2411458121

  View details for DOI 10.1073/pnas.2411458121

  View details for PubMedID 38976725

• Key language markers of depression on social media depend on race. Proceedings of the National Academy of Sciences of the United States of America Rai, S., Stade, E. C., Giorgi, S., Francisco, A., Ungar, L. H., Curtis, B., Guntuku, S. C. 2024; 121 (14): e2319837121

  Abstract

  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.

  View details for DOI 10.1073/pnas.2319837121

  View details for PubMedID 38530887

• Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation. Npj mental health research Stade, E. C., Stirman, S. W., Ungar, L. H., Boland, C. L., Schwartz, H. A., Yaden, D. B., Sedoc, J., DeRubeis, R. J., Willer, R., Eichstaedt, J. C. 2024; 3 (1): 12

  Abstract

  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.

  View details for DOI 10.1038/s44184-024-00056-z

  View details for PubMedID 38609507

  View details for PubMedCentralID 10227700

• A transdiagnostic, dimensional classification of anxiety shows improved parsimony and predictive noninferiority to DSM. Journal of psychopathology and clinical science Stade, E. C., DeRubeis, R. J., Ungar, L., Ruscio, A. M. 2023; 132 (8): 937-948

  Abstract

  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).

  View details for DOI 10.1037/abn0000863

  View details for PubMedID 38010770

• Depression and anxiety have distinct and overlapping language patterns: Results from a clinical interview. Journal of psychopathology and clinical science Stade, E. C., Ungar, L., Eichstaedt, J. C., Sherman, G., Ruscio, A. M. 2023

  Abstract

  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-a-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).

  View details for DOI 10.1037/abn0000850

  View details for PubMedID 37471025

• Lithium continuation therapy following ketamine in patients with treatment resistant unipolar depression: a randomized controlled trial NEUROPSYCHOPHARMACOLOGY Costi, S., Soleimani, L., Glasgow, A., Brallier, J., Spivack, J., Schwartz, J., Levitch, C. F., Richards, S., Hoch, M., Wade, E., Welch, A., Collins, K. A., Feder, A., Iosifescu, D. V., Charney, D. S., Murrough, J. W. 2019; 44 (10): 1812–19

  View details for DOI 10.1038/s41386-019-0365-0

  View details for Web of Science ID 000480643900019