Operationalizing Sepsis Alert Design and Clinical Decision Support: Developing Enhanced Visual Display Models

Abstract

It is vital that health care providers have the tools needed for early diagnosis and treatment of sepsis to achieve improved survival outcomes. Despite advances in early warning system technology, providers still lack responsiveness in recognizing and treating septic patients. The recently introduced Centers for Medicare and Medicaid Services early management bundle for severe/septic shock highlights the need to promote bundles of care to improve guideline compliance and lower hospital mortality. Our objective is to determine the best way to provide a sepsis alert to drive compliance in the complex cognitive system that underlies the decision-making process in the dynamic and distributed health care work environment. Alert and warning complexity is especially prevalent in health care information technology. Despite this issue, there is little consensus on how alerts and warnings should be generated and displayed to the user. Effective presentation of an alert, including how and what is displayed, may offer better cognitive support during busy patient encounters and may help providers extract information quickly. We are creating a framework to evaluate sepsis alert presentation models with enhanced visual elements integrating a textual, graphical, and figure display of the PIRO (predisposition, infection, response, organ dysfunction) classification. Our alert presentation framework is tailored to clinicians with the goal to better equip clinicians to understand their patients' data through feature extraction and visualization embedded with different asynchronous alerts.