A Smartphone-Based Self-Management Intervention for Individuals with Bipolar Disorder (LiveWell): Development of an Expert System to Provide Adaptive User Feedback (Preprint)

BACKGROUND Bipolar disorder is a severe mental illness that results in significant morbidity and mortality. While pharmacotherapy is the primary treatment, adjunctive psychotherapy can assist individuals with using self-management strategies to improve outcomes. However, access to therapy is limited. Smartphones and other technologies have the potential to increase access to therapeutic strategies that enhance self-management while simultaneously augmenting care by providing adaptive delivery of content to users as well as provider alerts to facilitate clinical care communication. Unfortunately, while adaptive interventions are being developed and tested to improve care, information describing the components of adaptive interventions is often not published in sufficient detail to facilitate replication and improvement of these interventions. OBJECTIVE To contribute to and support improvement and dissemination of technology-based mental health interventions, this paper provides a detailed description of the expert system for adaptively delivering content and facilitating clinical care communication for LiveWell, a smartphone based self-management intervention for individuals with bipolar disorder. METHODS Information from empirically supported psychotherapies for bipolar disorder, health psychology behavior change theories, and chronic disease self-management models was combined with user-centered design data and psychiatrist feedback to guide the development of the expert system. RESULTS Decision points determining the times at which intervention options are adapted were selected to occur daily and weekly based on daily and weekly self-report check-in data on medication adherence, sleep duration, routine, and wellness levels. This data was selected for use as the tailoring variables determining which intervention options to deliver when and to whom. Decision rules linking delivery of options and tailoring variable values were developed based on existing literature regarding bipolar disorder clinical status states and psychiatrist feedback. To address the need for adaptation of treatment with varying clinical states, decision rules for a clinical status state machine were developed for use with self-reported wellness rating data. Clinical status from this state machine is incorporated into hierarchal decision tables (if-then/elseif-then) that select content for delivery to users and alerts to providers. The majority of the adaptive content addresses sleep duration, medication adherence, managing signs and symptoms, building support, and keeping a regular routine as well as determinants underlying engagement in these target behaviors: attitudes and perceptions, knowledge, support, evaluation, planning. However, when problems with early warning signs, symptoms, and transitions to more acute clinical states are detected, the decision rules shift the adaptive content to focus on managing signs and symptoms and engaging with psychiatric providers. CONCLUSIONS Adaptive mental health technologies have the potential to enhance self-management of mental health disorders. However, the need for individuals with bipolar disorder to engage in the management of multiple target behaviors and to address changes in clinical status highlights the importance of detailed reporting of adaptive intervention components to allow replication and improvement of adaptive mental health technologies for complex mental health problems. CLINICALTRIAL NCT02405117, NCT03088462