Psychotherapy delivery relies on a negotiation between patient self-reports and clinical intuition. Growing evidence for technological support of psychotherapy suggests opportunities to aid the mediation of this tension. To explore this prospect, we designed a prototype of a clinical decision support system (CDSS) for treating veterans with post-traumatic stress disorder in a Prolonged Exposure (PE) therapy intensive outpatient program. We conducted a two-phase interview study to collect perspectives from practicing PE clinicians and former PE patients who are United States veterans. Our analysis distills opportunities for a CDSS (e.g., offering homework review at a glance, aiding patient conceptualization) and larger challenges related to context and deployment (e.g., navigating Veterans Affairs). By reframing our findings through three human-centered perspectives (distributed cognition, situated learning, infrastructural inversion), we highlight the complexities of designing a CDSS for psychotherapists in this context and offer theory-aligned design considerations.

Suhas Bn, Yash Mahajan, Dominik O. Mattioli, Andrew M. Sherrill, Rosa I. Arriaga, Christopher Wiese, Saeed Abdullah. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

The advancement of AI systems for mental health support is hindered by limited access to therapeutic conversation data, particularly for trauma treatment. We present Thousand Voices of Trauma, a synthetic benchmark dataset of 3,000 therapy conversations based on Prolonged Exposure therapy protocols for Post-traumatic Stress Disorder (PTSD). The dataset comprises 500 unique cases, each explored through six conversational perspectives that mirror the progression of therapy from initial anxiety to peak distress to emotional processing. We incorporated diverse demographic profiles (ages 18-80, M=49.3, 49.4\% male, 44.4\% female, 6.2\% non-binary), 20 trauma types, and 10 trauma-related behaviors using deterministic and probabilistic generation methods. Analysis reveals realistic distributions of trauma types (witnessing violence 10.6\%, bullying 10.2\%) and symptoms (nightmares 23.4\%, substance abuse 20.8\%). Clinical experts validated the dataset's therapeutic fidelity, highlighting its emotional depth while suggesting refinements for greater authenticity. We also developed an emotional trajectory benchmark with standardized metrics for evaluating model responses. This privacy-preserving dataset addresses critical gaps in trauma-focused mental health data, offering a valuable resource for advancing both patient-facing applications and clinician training tools.

The mental health crisis in the United States spotlights the need for more scalable training for mental health workers. While present-day AI systems have sparked hope for addressing this problem, we must not be too quick to incorporate or solely focus on technological advancements. We must ask empirical questions about how to ethically collaborate with and integrate autonomous AI into the clinical workplace. For these Human-Autonomy Teams (HATs), poised to make the leap into the mental health domain, special consideration around the construct of trust is in order. A reflexive look toward the multidisciplinary nature of such HAT projects illuminates the need for a deeper dive into varied stakeholder considerations of ethics and trust. In this paper, we investigate the impact of domain---and the ranges of expertise within domains---on ethics- and trust-related considerations for HATs in mental health. We outline our engagement of 23 participants in two speculative activities: design fiction and factorial survey vignettes. Grounded by a video storyboard prototype, AI- and Psychotherapy-domain experts and novices alike imagined TEAMMAIT, a prospective AI system for psychotherapy training. From our inductive analysis emerged 10 themes surrounding ethics, trust, and collaboration. Three can be seen as substantial barriers to trust and collaboration, where participants imagined they would not work with an AI teammate that didn't meet these ethical standards. Another five of the themes can be seen as interrelated, context-dependent, and variable factors of trust that impact collaboration with an AI teammate. The final two themes represent more explicit engagement with the prospective role of an AI teammate in psychotherapy training practices. We conclude by evaluating our findings through the lens of Mayer et al.'s Integrative Model of Organizational Trust to discuss the risks of HATs and adapt models of ability-, benevolence-, and integrity-based trust. These updates motivate implications for the design and integration of HATs in mental health work.

Today, clinicians have limited visibility into the quality of homework exercises that occur outside of the clinical context; however, understanding patient performance in these exercises is essential for guiding patient-centered care. To address this, we present the Clinician Homework Review (CHR), a unique measure and interface that displays similarity ratings calculated using sensor-captured patient-generated data (sPGD; i.e. heart rate, phone usage, ambient noise, and physical activity) for therapeutic exercises outside of the clinical setting within the post-traumatic stress disorder (PTSD) treatment context. Through concept testing sessions with 10 clinicians, we examine how sPGD can be leveraged to measure and investigate what contributes to patient performance in a therapeutic exercise. We also share in-depth information regarding clinician interpretation and planned use of data displayed by CHR in clinical sessions with patients. We frame our results in the context of situated objectivity and propose the notion of "perceived reference weight," which describes the significance attributed to contextualized data. In doing so, we support clinical decision-making in PTSD therapy.

Past research has demonstrated that accounts of trusted others can provide additional context into real world behavior relevant to clinical decision-making and patient engagement. Our research investigates the Social Sensing System, a concept which leverages trusted other feedback for veterans in therapy for PTSD. In our two phase study, we work with 10 clinicians to develop text-message queries and realistic scenarios to present to patients and trusted others. We then present the results in the form of a storyboard to 10 veterans with PTSD and 10 trusted others and gather feedback via semi-structured interview and survey. We find that while trusted other feedback may provide a unique and useful perspective, key design features and considerations of underlying relationships must be considered. We present our findings and utilize the mechanisms and conditions framework to assess the power dynamics of systems such as social sensing in the mental health realm.

Post-traumatic stress disorder (PTSD) disproportionately affects United States veterans, yet they may be reluctant to seek or engage in care. We interview 21 participants, including veterans with PTSD, clinicians who treat veterans and friends and family that support veterans through mental health ordeals. We investigate the military identity these veterans share. We explore how this may add to their reluctance in care-seeking behaviors. We also explore the roles of human and non-human intermediaries in ecologies of care and the potential for enhancing patient empowerment in current clinical treatment contexts. We discuss how military culture can be utilized in clinical care, how multiple perspectives can be leveraged to create a more holistic view of the patient, and finally, how veterans can be empowered during treatment. We conclude with recommendations for the design of sociotechnical systems that prioritize the above in support of the mental well-being of veterans with PTSD.