Abstract Statement Atrial fibrillation (AF) is the most common arrhythmia in the world, with significant morbidity and mortality. With appropriate oral anticoagulation, the risk of stroke due to atrial fibrillation decreases by 64%. Although atrial fibrillation is commonly diagnosed and treated in the Emergency Department (ED), oral anticoagulation is significantly underprescribed. Underprescribing has been attributed to a lack of empowerment and deferral of prescribing to longitudinal care clinicians. However, patients often do not follow-up with longitudinal care clinicians, resulting in missed opportunities to provide guideline-recommended care. Our proposal focuses on this missed opportunity to change the trajectory of care in the ED for patients with atrial fibrillation with appropriate early prescribing of oral anticoagulants, and thereby, improve clinical outcomes. This R01 Physician-Scientist Early Investigator proposal is in keeping with the mission of NHLBI "to promote the prevention and treatment of heart disease … and enhance the health of all individuals so that they can live longer and more fulfilling lives." We leverage an existing outpatient shared-decision making clinical decision support tool to improve stroke prevention for patients with atrial fibrillation and test its ability to improve guideline-recommended care in the acute care setting of the Emergency Department—a fast-paced, episodic, high-intensity environment. Electronic health record clinical decision support (CDS) tools have emerged as a means to guide clinicians on best practices and can make a significant impact on clinical outcomes. By increasing guideline adherence and improving the transition of care from the ED to the outpatient setting, this proposal could significantly reduce the risk of stroke for patients with atrial fibrillation with an intervention that could be rapidly and effectively disseminated across other settings. The project is a convergent parallel quantitative-qualitative study (mixed-methods) consisting of three components: (1) Implement a clinical decision support tool in a multi-centered stepped-wedge cluster randomized trial, (2) Identify clinician facilitators and barriers to ideal AF care and refine CDS tools for different settings using qualitative approaches, and (3) Explore patient satisfaction with the tool for future scalability and generalizability. This research will allow Dr. Kea to gain knowledge on how the unique environments of each hospital setting interacts with the CDS tool and how to refine the tool for large-scale dissemination, including rural and resource-poor environments, on a national scale.