Saving Lives With Algorithm-Enabled Process Innovation for Sepsis Care

Abstract

Predictive algorithms have an increasingly important role in supporting the day-to-day operations of healthcare organizations. Yet, fully realizing the value of algorithms lies critically in the opportunity to re-engineer the related processes and redefine roles in ways that make organizations more effective. We study whether and how algorithm-enabled process innovation (AEPI) creates value in the context of early diagnosis of sepsis|a costly condition that is the leading cause of death for hospitalized patients. Specifically, we collaborated with a large U.S. based hospital system and examined how AEPI developed for sepsis care impact patient mortality and related process outcomes (e.g., timely diagnosis and treatment). Our empirical analysis shows that sepsis AEPI reduces the likelihood of death from sepsis (42% relative reduction in mortality risk due to sepsis). This reduction occurs in parallel with improvements in timeliness of diagnostic (53% relative increase in the likelihood of timely lactate measurement) and clinical interventions (28% relative increase in the likelihood of timely antibiotics administration) for sepsis patients. We identify partial lapses in process outcomes in parallel to a partial lapse in AEPI's propensity to reduce sepsis-related mortality in the early phase of implementation. This lapse mostly recovers when the entire hospital implements sepsis AEPI. Our findings suggest that streamlining sepsis care processes through a predictive algorithm holds significant promise in reducing the loss of life from sepsis. We show that such value, however, requires adherence to process changes even after the algorithm becomes a routine part of the day-to-day operations of the hospital.