Background: Depression is the most prevalent mental health disorder in VHA and is strongly associated with disability and suicide mortality, especially when untreated. Understanding the profiles of patients that disengage from care will help develop support systems to improve care utilization and outcomes. According to Levesque’s framework, relevant patient characteristics that lead to care access map onto a process that incorporates identifying health care needs and desire for care, healthcare seeking, reaching, and utilization, all leading to health care outcomes. Using this framework, the proposed CDA takes a two-prong approach in response to underutilization of care among those with depression by: developing risk predictive models through analytics methodology and leveraging the role of mood and symptom self-monitoring as key components in depression management. Significance/Impact: The knowledge developed through this CDA has long term implications for OEF/OIF Veterans who are at highest risk for depression and suicide. Depression has a significant impact on Veterans, providers, and the VA. It is a disorder that is linked to substantial medical and economic burden in the VA. Depression is a risk factor for the development and maintenance of medical and psychiatric conditions (i.e., PTSD, TBI). Despite persistent efforts to increase care for depression, treatment guidelines are exclusively focused on those engaging in care. Pre-treatment interventions have the potential to increase mental health care utilization and reduce depression related burden on patients and the VA. Such interventions can minimize provider burden by reducing no shows and by increasing adherence. Innovation: Research shows that the VA has the potential to foster the development of tools to enhance mental health care for Veterans. To fill gaps in the use of analytics and technology in enhancing care for mental health concerns, the proposed work is innovative in two ways: 1) we propose the use of big data and analytics tools to identify patient profiles associated with mental health treatment engagement and increased risk for drop out of care; 2) develop a technology driven intervention to increase self-efficacy and active engagement in mental health care. Specific Aims: RA1: Identify risk profiles (scores) associated with depression treatment use. Test prediction models using VHA electronic health records (EHR). Risk scores computed in Aim 1 will be used in selection of patients at risk and eligible for the proposed intervention.TA1: Gain proficiency in methods and analysis of EHR/big data. RA2: Design an eHealth intervention using technology driven self-monitoring. TA2: Develop skills and knowledge about intervention development. RA3: Formatively evaluate and pilot the eHealth intervention. TA3: Gain proficiency in formative evaluation. Methodology: RA1 will use a retrospective cohort design. Leveraging the strengths of EHR data and analytics tools, we will investigate r...