Sepsis remains a major cause of mortality and morbidity worldwide. What exactly is sepsis? It is a dysregulated host response to infection, and it is estimated to afflict over 48.9 million people a year worldwide, leading to death in approximately 11 million. We all know that the early detection of sepsis is critical since interventions such as fluid resuscitation, antibiotic administration, and source control all have great benefits when implemented earlier in the disease course.

Bring on AI! Researchers at University of California San Diego School of Medicine utilized an artificial intelligence (AI) model in the emergency departments at UC San Diego Health to quickly identify patients at risk for sepsis infection. The study found that the AI algorithm, “COMPOSER”, which was previously developed by the research team, resulted in a 17% reduction in mortality! The algorithm continuously monitors more than 150 different patient variables that could be linked to sepsis, such as lab results, vital signs, current medications, demographics and medical history. The algorithm notifies nursing staff via the EHR assisting the medical team in identifying the appropriate treatment plan!

This is the first study to report improvement in patient outcomes by utilizing an AI deep-learning model and is being used in many hospital in-patient units throughout the UC San Diego Health system. Imagine if you will, the possibility of eliminating human error when a resident is at risk of developing sepsis. An AI system that alerts your staff to impending danger. Wow, what a great tool! Unfortunately, it isn’t available yet but stay tuned, it should surely be something to consider when budgeting for capital expenses in the future! Stay well and stay informed!