S.T.A.N.D. Alacrity Center Signature Project

The purpose of this study is to evaluate clinical decision-making algorithms for (a) triaging to level of care and (b) adapting level of care in a low income, highly diverse sample of community college students at East Los Angeles College (ELAC).

The target enrollment is 200 participants per year, for five years (N=1000). Participants are between the ages of 18 and 40 years and will be randomized into either symptom severity decision-making (SSD) or data-driven decision-making (DDD). Participants in each condition will be triaged to one of three levels of care, including self-guided online prevention, coach-guided online cognitive behavioral therapy, and clinician-delivered care. After initial triaging, level of care will be adapted throughout the entire time of the study enrollment. Participants will complete computerized assessments and self-report questionnaires as part of the study.

Recruitment will take place in the first two to four months of each academic year. The total length of participation is 40 weeks.

Community colleges provide a critical pathway for workforce development and socio-economic gain, but this opportunity is mitigated by unmet need for mental health services, particularly for depression and anxiety, and particularly for racial/ethnic minority students. A scalable and effective system of care that manages mental health needs in concert with social mental health determinants is sorely needed. The Alacrity Center aims to implement the STAND system of care, which screens and treats anxiety and depression, for a highly diverse community college population. STAND triages to various level of care, ranging from self-guided online prevention, to coach-guided online cognitive behavioral therapy (CBT), to clinician-delivered care. After initial triaging, STAND makes adaptations to level of care throughout the entire time of study enrollment (e.g., moved up to a higher level of care during acute treatment). These triaging and adaptation decisions currently are based on current symptom severity. Such decisions can be optimized by comprehensive data-driven algorithms that predict the need for a particular level of care and for adaptation to level of care throughout treatment, and especially algorithms that are suited to the needs of underserved community college students who face substantial life stressors.

The overarching aim of the Signature Project is to evaluate clinical decision-making algorithms for (a) triaging to level of care and (b) adapting level of care in a low income, highly diverse sample of community college students at East Los Angeles College (ELAC). The end goal is to improve the effectiveness of STAND and to advance the science of personalized mental health. To do this, we will compare the standard approach that relies solely upon symptom severity to a data-driven approach to decision making that uses multivariate predictive algorithms comprised of baseline static and time-varying features from four overlapping and mutually reinforcing theoretical constructs: (1) social determinants of mental health (employment, income, housing & food security, discrimination, social support, race/ethnicity, acculturation, immigration status, gender, sexual orientation); (2) early adversity and life stressors; (3) predisposing, enabling and need influences upon health services use; and (4) comprehensive mental health status (depression, anxiety and suicide severity, comorbidities, neurocognitive functioning, emotion dysregulation, regulatory strategy use, treatment history and preferences, social, occupational, home and academic functioning). The overarching design is to randomize ELAC students to either symptom severity decision-making (SSD) or data-driven decision-making (DDD), and evaluate whether DDD improves adherence to treatment, symptoms, and functioning. Other aims of this project are to (a) identify distal and proximal risk factors for suicide and self-harm and (b) examine effects of the decision-making condition (SSD, DDD) on suicidality and self-harm outcomes.

Participants will be enrolled in the first two to four months of the academic year at ELAC. The target enrollment is 200 participants per year over five years (n = 1000 total). Participants are current ELAC student between the ages of 18-40. Predictors and outcomes will be assessed at baseline and either weekly or every 8 weeks until week 40. Multivariate prediction models will be used for initial level of care triaging and later adaptations of level of care based on a comprehensive set of variables that have been shown to drive current mental health needs. Participants will complete computerized assessments and self-report questionnaires. The total length of participation is 40 weeks.