Predicting hyperlactatemia in the ICU

Abstract

Sepsis, which occurs when an infection leads to a systemic inflammatory response, is believed to contribute to one in two to three hospital deaths in the United States. Using the Multiparameter Intelligent Monitoring in Intensive Care (MIMIC II) database of electronic medical records from Boston's Beth Israel Deaconess Medical Center (BIDMC), we worked to characterize sepsis at BIDMC's intensive care units (ICUs). Additionally, we developed a real-time algorithm to stratify patients with infectious complaints into different risk categories for progressing to septic shock. From arterial blood pressure waveform trends collected from bedside monitors and readily available among patients with an arterial catheter, high-resolution time signals of heart rate and arterial blood pressure measurements, as well as estimates of cardiac output and total peripheral resistance, we developed a variety of classifiers to place patients in risk categories based on serum lactate levels, a proxy for hypoperfusion and imminent circulatory shock.