The objective of this project is to leverage Artificial Intelligence (AI) to create COACH: an on-device AI-driven digital navigator system that will support patients’ effective use of Digital Mental Health Technologies. We aim to: 1. Develop a prototype chatbot-based digital navigator; 2. Conduct preliminary evaluation of the system including lab-based usability testing with healthy participants and “red-team” stress testing with project confederates.
Practice Type: Online/remote/apps/social media
Making generative AI safe for people with mental health conditions
Hundreds of millions of people are already using Large Language Models (LLMs), including for mental health purposes, which has led to inadvertent harms. Critically, people with mental health conditions may be especially vulnerable to such harms.
In this project, we will develop the first computational framework to systematically quantify and benchmark the risks that LLMs present to people with mental health conditions. Our approach will simulate interactions of hundreds of users and LLMs to evaluate safety across a variety of mental health conditions, demographics, and AI failure modes.
Optimizing telemental health with live artificial intelligence clinical scaffolding and feedback
This project aims to develop a clinical scaffolding system to enhance telemental health care by providing real-time coaching and actionable suggestions during video-based sessions. Modeled after live supervision methodologies, it supports clinicians by identifying intervention targets and offering text-based coaching prompts to guide care. Unlike automated chatbots, this approach enables clinicians to adapt suggestions to patient needs, balancing automation with oversight for safer AI-supported mental healthcare. The proposed in-session support will facilitate efficient implementation of strategies and clinician skill development. This project seeks to enhance data privacy by processing all data on-device and avoiding external data transfers.
Project RELATE
The present study seeks to significantly expand our understanding of alcohol and cannabis co-use behaviors in the context of young adult romantic relationships through collecting daily dyadic quantitative data and qualitative interviews, and using this information to develop and pilot an integrated brief intervention to decrease alcohol and cannabis misuse and increase healthy relationships skills among this understudied, high-risk group.
Development of an mHealth support specialist for early psychosis caregivers in Washington State
Early intervention can significantly improve the trajectory of a young adult at risk for psychosis. Specialized treatment programs for youth at risk are associated with reduced symptoms and relapse risk and increased functioning. Family caregivers play a critical role in facilitating treatment engagement and recovery, but too often they lack the support they need. Specialty psychosis services providing psychoeducation for family members are expanding but still difficult to access. Caregivers face many barriers to care: limited providers and session time availability, long travel times, or patient ambivalence about treatment. As a result, a minority of youth with early psychosis have caregivers that have accessed standard-of-care family interventions.
To address these gaps, our team developed Bolster, a mobile health (mHealth) app designed to provide psychoeducation, communication coaching, and self-care support to caregivers to youth at risk for psychosis. In preliminary work, Bolster was feasible to deliver, acceptable to caregivers, and showed promising efficacy. However, mHealth interventions that are supplemented by a human clinical support have higher engagement and effectiveness than those that are purely self-guided. To optimally implement mHealth for early psychosis caregivers, there is a need for development of this clinical workforce.
We propose to develop and pilot an emerging clinical role – the mHealth support specialist (mHSS) – equipped specifically to support caregivers to youth with early psychosis. Specifically, we will (1) develop a training and supervision framework supporting the mHSS for caregivers, (2) test this framework through training and supervising one mHSS, and (3) evaluate this approach as the mHSS provides support to caregivers to young adults with early psychosis throughout Washington State. Delivering this intervention has the potential to greatly expand population access to evidence-based strategies for psychosis. Developing the mHealth support specialist model would make Washington a national leader in scalable digital interventions for caregivers. This study takes a critical step toward realizing that vision.
A pilot trial on EMA habit formation behavioral strategies for improving engagement of digital mindfulness interventions among non-suicidal self-injury engagers
Non-suicidal self-injury (NSSI), the purposeful, direct damage of one’s body without the intent to die, is a pervasive public health concern with clinically significant long-term consequences. Mindfulness – a core skill in DBT, an evidence-based treatment for NSSI, is designed to target emotion dysregulation and rumination and may be particularly relevant due to the proliferation of digital mindfulness interventions in recent years. To this end, the goal of this study is to expand the use of ecological momentary assessment (EMA) and to develop and evaluate a program of habit-formation strategies (e.g., SMART-goal setting, reinforcement scheduling) to boost user engagement and treatment effects of DMI. Following a 1-week EMA baseline period, participants (N=40) will be randomized to either TAU (Mindfulness only) or Experimental (Mindfulness + Behavioral Prompts) conditions for a 4-week intervention EMA period.
THRIVE Study
This is a study of an app intended to support recent sexual assault survivors, called THRIVE. In a prior grant, we pilot tested THRIVE and found that it reduced risk for alcohol misuse and posttraumatic stress. In the first year of this grant, we aim to revise the app to increase usability and inclusivity. In the second through fifth years of the grant, we will conduct a larger randomized controlled trial of multiple versions of the app among college students who have experienced sexual assault in the past 12 weeks. This will allow us to identify the most effective and low-burden version of THRIVE. If we are successful in identifying a highly effective and efficient version of THRIVE, this intervention would represent a highly-scalable strategy to reduce the substantial burden of posttraumatic stress and alcohol misuse on student survivors and campus service systems.
Needs Assessment for Supporting Technology use and Harm Reduction (STaHR Study)
The proposed study entails a needs assessment to develop a program for Supporting Technology use and Harm Reduction (STaHR) among HF residents with lived experience of homelessness and substance use. This study will qualitatively explore HF residents’ technology literacy as well as their perspectives on barriers and facilitators to the use of technology, broadly, and for harm-reduction service provision. Then, with a community advisory board (CAB) made up of HF residents, staff, and management, we will inform and provide recommendations to HF management and leadership ways to improve HF resident technology use and engagement with online harm-reduction services.
Developing a digital training resource for clinicians learning CBT for psychosis (CBTpro)
The Cognitive Behavioral Therapy Training Study will rigorously test CBTpro — a novel tool that uses spoken language technologies and conversational Artificial Intelligence to train behavioral health practitioners in Cognitive Behavioral Therapy. We conducted a 2-week field trial, followed by a Randomized Clinical Trail in community mental health agencies to evaluate both learner and client outcomes. The study aims to expand global access to CBT training to students and practitioners, support quality psychological treatments for clients with a range of behavioral health disorders (including Serious Mental Illness), and support ongoing clinical quality assurance in routine care settings.
Evaluation of an asynchronous remote communities approach to behavioral activation for depressed adolescents
In an effort to address the significant challenges in access to and engagement with evidence-based psychosocial interventions for adolescent depression, the proposed research is piloting the use of Asynchronous Remote Communities (ARC) supported behavioral activation (BA) to treat adolescent depression. We aim to 1) build and conduct usability testing on a functional and robust ActivaTeen platform that will satisfy the needs of mental health clinicians and adolescent patients and 2) test the feasibility, usability, and change in proposed target mechanisms (therapist alliance, timeliness of intervention, social belongingness, and engagement) and outcomes of BA+ActivaTeen compared to BA treatment only within a moderately-sized randomized control trial conducted within Seattle Children’s Hospital outpatient psychiatry clinic.
