1 - (SYM 84) Using a Predictive Algorithm for Triaging and Adapting Level of Psychological Care for Depression and Anxiety: Results from the STAND Program

There is a growing need to personalize mental health care to improve engagement and efficacy. Existing personalized care for disorders like depression and anxiety predominantly use symptom severity in decision-making. The Screening and Treatment for Anxiety and Depression (STAND) program provides evidence-based, stratified stepped-care. This RCT utilizes an innovative multivariate decision-making algorithm for triaging and adapting levels of mental health care. The levels of care include a self-guided online wellness program, coach-guided digital therapy, and clinician-delivered care. The novel multivariate algorithms are comprised of baseline (for triage and adaptation) and time-varying variables (for adaptation) in four areas: (1) social determinants of mental health, (2) early adversity and life stressors, (3) predisposing, enabling, and need influences on health service use, and (4) comprehensive mental health status. The RCT aims to evaluate whether the multivariate algorithm improves adherence, symptoms, and functioning above and beyond the traditional, symptom-based algorithm. Participants (N = 386) were recruited from a diverse community college sample in the greater Los Angeles area. In the symptom-severity approach, triaging and adaptation to levels of care were based on symptom severity, whereas in the multivariate approach, decisions were based on a comprehensive set of measures across the aforementioned four domains that were assessed with self-reports. Participants completed computerized adaptive tests for depressive, anxiety, and suicidality symptoms at baseline and up to forty weeks. Results from multilevel models showed significant declines over time in depressive, anxiety, and suicidality symptoms, ps < .001. Symptom decline across the three treatment levels (online wellness program, coach-guided digital therapy, clinician delivered care) did not differ. The benefits of using the novel multivariate decision-making algorithm over the traditional symptom severity decision-making approach with respect to treatment adherence, symptom improvement, and functional recovery will be discussed. The findings from the current investigation will inform the practice of triaging and adaptation for psychological treatment and the use of personalized mental health care broadly.