PROJECT SUMMARY/ABSTRACT Septic shock has a mortality rate above 40%, and is treated with supportive care including vasopressors. Yet, evidence shows vasopressor treatment response and clinician practices are heterogeneous. The key factors mediating this heterogeneity are unknown. This research project investigates the role of patient-specific factors in treatment response to initial and adjunctive vasopressor therapy in patients with septic shock. We seek to develop accurate, individualized tools to predict the heterogeneity of response to a variety of vasopressors in individual septic shock patients and implement these tools into bedside practice. Our preliminary data show early initiation of adjunctive vasopressin is associated with lower mortality, and individual patient and treatment characteristics are associated with vasopressin responsiveness. Therefore, we propose the novel hypothesis that clinically translatable models are capable of predicting early vasopressor treatment response and will optimize initial and adjunctive vasopressor therapy to improve clinical outcomes. This hypothesis will be tested through three interrelated, but independent specific aims: (1) to apply machine learning techniques to predict initial vasopressor therapy response; (2) to develop a decision model for optimizing adjunctive vasopressor therapy outcomes; and (3) to identify determinants of successful vasopressor prediction model clinical translation. Our proposal is innovative in concept because it is the first to use cutting-edge data science methods to develop prediction models for initial and adjunctive vasopressor treatment effects. The proposed research is significant because it has the potential to decrease mortality in septic shock patients by developing and implementing personalized vasopressor treatment approaches. Cleveland Clinic is the ideal environment to complete the proposed research due to the high volume (>6,000 yearly) of clinically and socio- demographically diverse sepsis patients, integrated multi-professional treatment and research teams, extensive informatics infrastructure, large cohesive health-system with a shared electronic health record, and history of successful evidence translation into improved care delivery. As a critical care clinical pharmacist, Dr. Bauer is uniquely positioned to develop and implement innovative vasopressor treatment strategies through knowledge of the combined influences of medication pharmacology and pharmacodynamics, patient comorbidities, and disease pathophysiology on treatment effects. With the mentorship of Dr. Vidula Vachharajani and other internationally-recognized experts, Dr. Bauer will pursue training goals to enhance his understanding of applied clinical translational science, clinical prediction modeling, implementation science, and research leadership. Pursuit of these aims and training goals through the K08 Career Development Award mechanism will facilitate achievement of Dr. Bauer’s long-te...