The emergency departments of Emory University Hospital face significant challenges in the timely identification and treatment of sepsis. Inconsistent reassessment in the waiting room causes developing sepsis symptoms to go undetected until deterioration is obvious. Once sepsis is recognized, treatment delays continue because blood culture collection, a key step in the sepsis treatment bundle, often depends on locating ultrasound machines that are stored unpredictably across the ED. These delays put patients at risk and threaten Emory’s ability to meet the SEP-1 compliance threshold mandated by the Centers for Medicare and Medicaid, which affects the hospitals' reimbursements.

This project introduces two solutions to address the difficulties Emory faces in achieving timely sepsis detection and treatment, respectively. The first solution is a patient-priority dashboard that uses survival analysis to estimate patients' risk of developing sepsis. Instead of relying on intuition or random checks, nurses can consult the continuously updated ranking to determine who needs reassessment and catch deterioration earlier.

The second solution focuses on treatment delay during blood culture collection. When patients are hard sticks and require ultrasound machine-guided blood draws, nurses often have trouble finding the machines. To fix this, we developed an optimization model that identifies machine placements that minimize retrieval time, cutting unnecessary walking and speeding up treatment.

Together, these tools give nurses a clearer sense of who needs attention and remove avoidable delays when treatment begins. Implementation of our improvements would yield a 36.6-minute reduction in sepsis diagnosis time and prevent an estimated 166 cases of progression to severe sepsis annually. The impact includes $3.86 million in annual savings through improved SEP-1 compliance and reduced length of stay, demonstrating how addressing fundamental workflow inefficiencies can simultaneously improve patient outcomes and financial performance.