A randomized clinical trial for sepsis using InSight was conducted at two mixed medical-surgical intensive care units at UCSF from December 2016 to February 2017. Using only the most commonly recorded measurements in the electronic health record, InSight predicted sepsis onset and alerted the appropriate care team. There was a significant (P = .04) decrease in hospital LOS (13 d vs. 10.3 d) and a 58.0% reduction in in-hospital mortality rate when using InSight (21.3% vs 8.96%) (P = .02). No adverse events were reported during this trial. These results were presented at the 47th Critical Care Congress, organized by the Society for Critical Care Medicine (SCCM).