Digital mental health (DMH) is the use of technology to improve population well-being
through rapid disease detection, outcome measurement, and care. Although several
randomized clinical trials have demonstrated that digital mental health tools are highly
effective, most consumers do not sustain their use of these tools. The field currently
lacks an understanding of DMH tool engagement, how engagement is associated with
well-being, and what practices are effective at sustaining engagement. In this
partnership between Mental Health America (MHA), Talkspace (TS), and the University of
Washington (UW), the investigators propose a naturalistic and experimental, theory-driven
program of research, with the aim of understanding 1) how consumer engagement in
self-help and clinician assisted DMH varies and what engagement patterns exist, 2) the
association between patterns of engagement and important consumer outcomes, and 3) the
effectiveness of personalized strategies for optimal engagement with DMH treatment.
This study will prospectively follow a large, naturalistic sample of MHA and TS
consumers, and will apply machine learning, user-centered design strategies, and micro
randomized and sequential multiple assignment randomized trials (SMART) to address these
aims. As is usual practice for both platforms, consumers will complete online mental
health screening and assessment, and the investigators will be able to classify
participants by disease status and symptom severity. The sample that the investigators
will be working with will not be limited by diagnosis or co-morbidities. Participants
will enter the MHA and TS platforms prospectively over 4 years. For aim 1, participant
data will be analyzed statistically to reveal differences in engagement and dropout
across groups based on demographics, symptoms and platform activity. For aim 2, the
investigators will use supervised machine learning techniques to identify subtypes based
on consumer demographics, engagement patterns with DMH, reasons for disengagement,
success of existing MHA and TS engagement strategies, and satisfaction with the DMH
tools, that are predictive of future engagement patterns. Finally, based on the outcomes
from aim 2, in aim 3a the investigators will conduct focus groups applying user centered
design strategies to identify and co-build potentially effective engagement strategies
for particular client subtypes. The investigators will then conduct a series of
micro-randomized and SMART trials to determine which theory-driven engagement strategies,
co-designed with users, have the greatest fit with subtypes developed under aim 2. The
investigators will test the effectiveness of these strategies to 1) prevent disengagement
from those who are more likely to have poor outcomes after disengagement, 2) improve
movement from motivation to volition and, 3) enhance optimal dose of DMH engagement and
consequently improve mental health outcomes. These data will be analyzed using
longitudinal mixed effects models with effect coding to estimate the effectiveness of
each strategy on client engagement behavior and mental health outcomes.
The purpose of aim 3b is to identify effective engagement strategies tailored to client
needs and demographics to increase MHA website engagement, and to better understand how
self-help mental health resources can help people overcome negative thinking and support
healthier thought processes. The investigators will compare effective engagement
strategies tailored to subtypes developed under aim 2 to study the mediated impact of
engagement strategies on consumer mental health outcomes. The study team will determine
if engagement strategies targeted to consumer engagement subtype will enhance engagement
and in turn result in improved clinical outcomes. These will be compared to generic
strategies that are not subtype targeted.
All aim 3b activities will occur with MHA, broken down into two parts: (Study 1) a
sequential multiple assignment randomized trial (SMART) and (Study 2) a Do-It-Yourself
(DIY) tool longitudinal randomized control trial (RCT). Study 1 will use a SMART to
examine methods to optimize engagement with MHA's website, and Study 2 will recruit
participants for a longitudinal month-long study where they are randomly assigned to a
control group, the use of a DIY tool without Artificial Intelligence (AI), or the use of
a DIY tool with AI to examine the efficacy of using a digital tool to improve mental
health functioning. An AI tool that uses machine learning/Natural Language Processing
(NLP)/AI methods was developed to personalize and tailor an intervention to improve
engagement and completion outcomes. The study focuses on a specific, popular DIY tool
that teaches cognitive restructuring. Pilot work showed that (1) engagement and
completion rates on DIY tools can be low, and (2) a pilot AI tool had significantly
higher engagement and completion rates. These differences may arise due to AI support,
User Interface/User Experience/design differences, other factors, or a combination
thereof. Additionally, the efficacy of the digital tool to improve mental health
functioning is unknown. Study 2 will recruit participants who will be randomly assigned
to one of three groups for a longitudinal month-long study: thrice-weekly DIY tool use
with AI, without AI, or a control group.