Skip to main content
Skip to footer

Saving Lives Through Sepsis Surveillance

Published on 3/27/2017

Pictured above: Neal L. Patterson, co-founder, chairman and CEO of Cerner, at the Cerner Health Conference.

Early recognition of sepsis is imperative to early treatment and saving lives. A sepsis clinical decision support system that offers real-time surveillance and electronic alert notification capabilities is more reliable when incorporating trusted clinical definitions of sepsis.

The St. John Sepsis Surveillance Agent, developed by Cerner Corporation in 2010, draws from the best published evidence and uses cloud computing with big data analytics to screen and activate on high-risk patients early in their infectious process, while increasing precision in estimating mortality risk to enable medical decision.

The beginning of the St. John Sepsis Surveillance Agent

The urgency of sepsis surveillance at Cerner began with the tragic death of Cerner Co-founder, Chairman and CEO Neal Patterson's sister-in-law, Linda, who died from strep pneumonia sepsis in 2006. After being ill all week, she visited her rural primary care doctor on a Friday evening because she was concerned her symptoms were getting worse. She left without active treatment, worsened over the weekend, and was taken to the local emergency room. After some tests, she was eventually transferred to a larger medical center an hour away, where she was again assessed and eventually admitted to the ICU. Antibiotic therapy began hours after her admission to the ICU and likely many hours after infection entered her blood stream. Severe sepsis is a condition that requires early recognition and timely treatment within a six-hour window. By the time antibiotics were initiated, Linda's "six golden hours" had been consumed by a fragmented care process that failed to create any intervention.

The St. John Sepsis Surveillance Agent, named after St. John's Hospital in Tulsa, Oklahoma — Cerner's first client — has now been implemented in over 550 hospitals in the United States, and the global utility of the solution is growing. Several quality improvement studies have been conducted, culminating in three peer-reviewed publications in the American Journal of Medical Quality and the Journal of the Royal Society of Medicine Open. Collectively, these studies suggest sepsis clinical decision support, which includes the St. John Sepsis Surveillance Agent and sepsis management content, is an effective approach toward early identification of high-risk patients and a reliable alarm system necessary for provider adoption, which ultimately can save lives.

Identifying sepsis risk and driving better patient outcomes

In early 2016, the updated sepsis consensus guideline (Sepsis-3) included a new indication of sepsis risk, termed the quick Sequential [Sepsis-related] Organ Failure Assessment (qSOFA). The purpose of qSOFA is to identify non-ICU patients under suspicion of infection who could be deteriorating into a sepsis complication.

As a commitment to eradicating sepsis and ensuring the best evidence available is being used for sepsis surveillance and clinical decision support, a team of Cerner researchers conducted a new study that examined the utility of qSOFA as an alternative alert mechanism to the St. John Sepsis Surveillance Agent, and whether qSOFA improves clinimetric performance. The study has been published in the American Journal of Medical Quality. You can find it here.

Figure 1 (left side). St. John Sepsis Surveillance Agent screens in more patients at-risk of sepsis and earlier in their infection process when compared to qSOFA.

Figure 2 (right side). Discrimination of mortality risk is significantly better when the predictive model includes St. John Sepsis Surveillance Agent when compared to the risk model that includes qSOFA.

Researchers found qSOFA, in contrast to the St. John Sepsis Surveillance Agent, identified substantially fewer patients at-risk of sepsis and much later in their infectious process taking them beyond the three-hour opportunity-risk window (Figure 1), and were less likely of in-hospital death (Figure 2). Finally, the time-to-event analysis showed patients with qSOFA indicated less urgency and a lower likelihood of experiencing an accelerated composite outcome of admission to ICU or death because of their lower acuity when compared to patients with a St. John Sepsis Surveillance Agent "Sepsis" alert. In sum, these findings illustrate the clinimetric performance of St. John Sepsis Surveillance Agent is superior to qSOFA.

A balance point was sought between clinical precision of detection and timing of alert activation. The St. John Sepsis Surveillance Agent is perhaps unique in this regard.

Despite the initial focus on early recognition of sepsis, from the very onset of our work, one of the most important factors has been to identify patients at-risk of death, irrespective of the final diagnosis of sepsis. We aimed to bring appropriate clinical attention onto these vulnerable patients, and believe the St. John Sepsis Surveillance Agent met these objective criteria.

The St. John Sepsis Agent helps hospitals reduce sepsis cases through early detection. To learn more about this Cerner solution, request more information here.