Dascena publishes on a computational approach to early sepsis detection
In this study Dascena evaluates a sepsis prediction algorithm. The findings are published in Computers in Biology and Medicine.
Early diagnosis and treatment of severe sepsis and septic shock, which are among the leading causes of death in the United States, have been shown to decrease the risk of adverse outcomes. InSight was developed using data from the electronic health record and novel machine learning techniques to satisfy the need for high performance sepsis screening. Using only nine commonly available vital signs, InSight was shown to accurately predict sepsis at least three hours before the onset of the first five-hour Systemic Inflammatory Response Syndrome (SIRS) event. InSight also demonstrated sensitivity and specificity that rivaled or exceeded those of current clinical detection tools. Improvements in early identification of high risk patients were made possible by key high-order correlations between the vital sign measurements.