Bloch-Elkouby Lab for Suicide Prevention and Psychotherapy Research

Kate's Poster

Protocol for a Randomized Controlled Trial Evaluating the Effectiveness of an AI-Enhanced Virtual Human Training for Therapy with High-Risk Patients

Kate Van Houten¹˒²˒³, You-Syuan Lin¹˒², Samuel Welsh¹˒², Jimmy Pengyu Chen¹˒², Igor Galynker¹, & Sarah Bloch-Elkouby¹˒²

¹ Icahn School of Medicine at Mount Sinai
² Ferkauf Graduate School of Psychology, Yeshiva University
³ Teachers College, Columbia University

Introduction

Clinicians commonly experience intense emotional responses, such as distress, helplessness, frustration, and avoidance, when assessing suicide risk and treating high-risk patients (Barzilay et al., 2019; Huggett et al., 2021). These emotional reactions can undermine empathic communication (EC) and damage the therapeutic alliance, in turn exacerbating suicidal outcomes. Although EC and therapeutic alliance are important to supporting high-risk patients, few training programs address clinicians’ Emotional Self-Awareness and Management (ESA-M) to improve EC and the alliance (McCabe et al., 2017; Barzilay et al., 2019).

Virtual Human Interactions (VHIs) involve conversations with standardized virtual patients, derived from rich, real-world patient data, and can simulate encounters with patients at high risk for suicidal behaviors who present with Suicide Crisis Syndrome (SCS) (Bloch-Elkouby et al., 2025). VHIs assist clinicians in managing their ESA-M, such as regulating negative facial expressions and verbal empathic communications. VHIs provide an opportunity for clinicians to practice and develop these challenging skills in an environment that is lower risk than working with live patients.

Gaps in Literature

This study presents an innovative opportunity to learn about suicide prevention from a novel focus point. Suicide prevention has historically focused on what interventions clinicians are delivering rather than what is occurring interpersonally (Zalsman et al., 2016). The emotional processes in a therapeutic dyad critically affect the therapeutic alliance (Barzilay et al., 2020).

Although the therapeutic alliance is an established predictor of treatment engagement and clinical outcomes (Li et al., 2024), little is known about the emotional processes that establish the alliance. Suicide prevention literature can expand upon the exploration of emotional processes that improve the alliance.

Innovations

Proposed Methods

Significance of the Proposed Study

This study can advance knowledge of the underlying mechanisms responsible for improving clinician care and patient outcomes. Understanding the active ingredients in treatment, such as ESA-M or EC, is essential because it allows for further lines of research that are more focused on process. This transdiagnostic process research is foundational for understanding which populations benefit most from particular mechanisms and what factors impair essential active ingredients.

Prior literature has established that therapeutic alliance outcomes differ cross-culturally (Li et al., 2024). Results from this study can provide transdiagnostic insights that contribute to understanding disparities, including cross-cultural processes.

Breaking down suicide prevention efforts into their component ingredients is an essential step toward improving and expanding care. Active ingredients in psychotherapy can act as facilitators or barriers depending on the setting in which they are utilized. A better understanding of the building blocks of suicide prevention can improve the field as a whole.

References

Barzilay, S., Schuck, A., Bloch-Elkouby, S., Yaseen, Z. S., Hawes, M., Rosenfield, P., Foster, A., & Galynker, I. (2019). Associations between clinicians’ emotional responses, therapeutic alliance, and patient suicidal ideation. Depression and Anxiety, 37(3), 214–223. https://doi.org/10.1002/da.22973

Bloch-Elkouby, S., Johnson, B., Chen, J. P., Hayek, R. E., Jones, A., Eid, T., De Siqueira, A. G., Apter, Y., Yao, H., Lok, B., Foster, A., & Galynker, I. (2025). Can training clinicians in emotional awareness using virtual patient interactions improve the therapeutic alliance with psychiatric outpatients and reduce suicidal outcomes? Psychiatry Research, 356, 116846. https://doi.org/10.1016/j.psychres.2025.116846

Huggett, C., Gooding, P., Haddock, G., & Pratt, D. (2021). The relationship between the therapeutic alliance and suicidal experiences in people with psychosis receiving therapy. International Journal of Environmental Research and Public Health, 18(20), 10706. https://doi.org/10.3390/ijerph182010706

Li, Y., Whiston, S., Wong, Y. J., & Gilman, L. (2024). Clients’ race/ethnicity as a moderator of the relationship between the therapeutic alliance and treatment outcome. International Journal for the Advancement of Counselling, 46(2), 219–241. https://doi.org/10.1007/s10447-024-09546-3

McCabe, R., Sterno, I., Priebe, S., Barnes, R., & Byng, R. (2017). How do healthcare professionals interview patients to assess suicide risk? BMC Psychiatry, 17(1), 122. https://doi.org/10.1186/s12888-017-1212-7

Zalsman, G., Hawton, K., Wasserman, D., Van Heeringen, K., Arensman, E., Sarchiapone, M., Carli, V., Höschl, C., Barzilay, R., Balazs, J., Purebl, G., Kahn, J. P., Sáiz, P. A., Lipsicas, C. B., Bobes, J., Cozman, D., Hegerl, U., & Zohar, J. (2016). Suicide prevention strategies revisited: 10-year systematic review. The Lancet Psychiatry, 3(7), 646–659. https://doi.org/10.1016/S2215-0366(16)30030-X