JMIR Publications

ABSTRACT

Background:

The growing global burden of mental health disorders has intensified the search for scalable, accessible, and cost-effective interventions. Conversational agents in the form of digital humans have emerged as promising tools to deliver mental health support across diverse populations and settings.

Objective:

The scoping review seeks to provide a comprehensive analysis of digital humans' roles in depression management, identifying their specific applications in both diagnostic processes and therapeutic interventions. Additionally, this study aims to evaluate the design choices implemented in digital human systems, including their appearance, interaction modalities, back-end intelligence systems, and the various roles they assume.

Methods:

Following the PRISMA-ScR guidelines, we systematically searched peer-reviewed literature across major databases including ACM Digital Library, IEEE Xplore, Web of Science, and PubMed to capture both psychological and technological perspectives. The search query used was to include a wide variety of synonyms for digital humans and depression: ("avatar" OR "virtual agent" OR "embodied conversational agent" OR "relational agent" OR "digital human" OR "virtual human" OR "virtual character") AND ("Major Depressive Disorder" OR "Depression"). Studies were included if they described the development, implementation, or evaluation of digital humans designed to support mental health outcomes. Data were charted on agent design, therapeutic approach, target population, delivery context, and reported effectiveness.

Results:

Twenty studies (2010-2024) were included. Depression assessment studies comprised 35% (n=7), interventions 55% (n=11), and combined approaches 10% (n=2). Assessment protocols included questionnaires (PHQ-9, CES-D-VAS-VS), semi-structured interviews based on DSM-5 criteria, and interactive tasks designed to elicit emotional responses. Intervention approaches employed Cognitive Behavioral Therapy, psychoeducation, Compassion-Focused Therapy, and Avatar Therapy. Digital humans assumed five distinct roles: interviewer (n=6), facilitator (n=3), counselor (n=3), educator (n=3), and actor (n=5). Interviewers primarily appeared in assessment studies, presenting structured questions. Counselors engaged in therapeutic dialogues, while educators delivered psychoeducational content. Facilitators assisted participants in achieving system goals. Actors portrayed specific emotions or dysfunctional beliefs to facilitate therapeutic processes. Studies highlighted digital humans' utility in enhancing diagnostic processes and therapeutic interventions, noting potential for transformation through physiological data integration.

Conclusions:

This scoping review demonstrates that digital humans represent a transformative advancement in depression management, offering innovative applications across both assessment and intervention phases. The evidence reveals digital humans' effectiveness in replicating traditional therapeutic roles while providing unique advantages including 24/7 accessibility, reduced stigma, consistent care delivery, and personalized support. Digital humans successfully function across multiple roles with demonstrated capability to establish therapeutic alliances and elicit meaningful engagement comparable to human providers. Findings underscore the need for continued research to fully realize digital humans' potential in addressing depression-specific needs, advocating for expansion into diverse therapeutic scenarios and exploration of unexplored digital human applications.