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.

Monitoring mood symptoms in young adults at-risk for bipolar disorder

The ages of 18-25 years are ‘peak onset’ times of major depression and bipolar disorder. These disorders have different courses and treatments, but diagnosing bipolar disorder is difficult because manic symptoms occur less often than depressive symptoms and many individuals do not recall manic symptoms. A ‘misdiagnosis lag’ of 8-10 years can contribute to prolonged periods of potentially ineffective treatments and suboptimal outcomes such as high symptom burden, relationship problems, educational attainment and occupational functioning.

This project will use remote prospective assessment and monitoring of depressive and manic symptoms in at-risk patients in-between patient visits to increase the ‘data points’ clinicians have when assessing a bipolar disorder diagnosis. This is especially important for people at risk for bipolar disorder (for example those with a family history of bipolar disorder) because manic symptoms can be provoked by first-line medication treatments for major depression. The project will use a new manic symptom measure (the Patient Mania Questionnaire-9) and a commonly used depressive symptom measure (the Patient Health Questionnaire-9) to monitor symptoms, and learn how clinicians and patients use this information clinically.

Bipolar disorder measures in clinical care

The goals of this project are to 1) determine which validated bipolar disorder patient-reported symptom measure is most acceptable and helpful to patients and clinicians in clinical care, 2) demonstrate that the preferred measure can be used to monitor outcomes with high fidelity in routine care, and 3) assess the feasibility of comparing effectiveness of measurement-based care (MBC) to usual care in a randomized trial.

Disseminating a user-friendly guide: Advancing the science of intervention adaptation and improving access to evidence-based psychological treatment

Adaptation of evidence-based practices and programs (EBPs) is a necessary component of the implementation process. EBPs must be adapted to function with the constraints of real-world practice settings, providers’ expertise, and patients’ needs. The science of intervention adaptation is hungry for well-defined methods of EBP adaptation to guide decision making. A how-to guide for EBP adaptation titled MODIFI: Making Optimal Decisions for Intervention Flexibility during Implementation, is under development with NIMH funding (F32 MH116623). MODIFI will be disseminated via multiple strategies locally, nationally, and internationally. Dissemination of MODIFI will improve the practice of intervention adaptation by providing practitioners with a how-to guide that is (a) evidence-based, (b) usable, and (c) supported by the expert consensus of implementation practitioners and researchers.

Study to Promote Innovation in Rural Integrated Telepsychiatry (SPIRIT)

The primary goal of this project is to quantitatively compare the treatment experience, engagement, self-reported clinical outcomes, and recovery-oriented outcomes of patients initially randomized to telepsychiatry collaborative care and telepsychiatry enhanced referral. In addition, for the subset of patients randomized to telepsychiatry enhanced referral who do not engage in treatment and are still symptomatic at 6 months, an additional goal is to quantitatively compare the treatment experience, treatment engagement, self-reported clinical outcomes and recovery-oriented outcomes of patients randomized to continued- telepsychiatry enhanced referral or phone enhanced referral. Additional goals are to gain an in-depth understanding of patients’ and providers’ treatment experiences and to examine treatment heterogeneity among subgroups of patients based on race/ethnicity, age and clinical severity.