An artificial intelligence (AI) algorithm for detecting sepsis warning signs has been proven to increase survival rates and reduce hospital stays.
In a study by researchers at Case Western Reserve University and MetroHealth, emergency room patients flagged by an AI algorithm as potentially having sepsis received antibiotics sooner and had better outcomes than those receiving standard care for sepsis.
The findings from the study have been published in the journal, Critical Care Medicine.
Identifying sepsis as early as possible
Sepsis is a life-threatening reaction to an infection that occurs when the body’s immune system overreacts to an infection and starts to damage the body’s own tissues and organs. The prognosis of patients with sepsis is related to the severity or stage of sepsis, as well as to the underlying health status of the patient. It is estimated that patients with severe sepsis or septic shock have a mortality rate of about 40% to 60%, so it is very important that sepsis is detected as early as possible.
The research investigation was carried out over a period of five months in 2019, tracking around 600 patients who came through the emergency department. MetroHealth implemented an electronic health record-embedded early warning system for sepsis. Patients aged 18 and over who presented to the emergency department were randomised into a group receiving standard care for sepsis and a separate pathway augmented by the early warning system.
The early warning system alerted both the physicians and pharmacists, meaning patients who were flagged by the system received antibiotics significantly faster than those patients whose alert was hidden. The researchers found that, collectively, people who received early antibiotics lived longer and had more days out of hospital than those in the standard care group.
Yasir Tarabichi, Assistant Professor of Medicine at the Case Western Reserve School of Medicine and the study’s principal investigator, said: “We showed that, when providers had access to the early warning system, patients had better sepsis-related outcomes.
“These patients got their antibiotics faster and had, on average, more days ‘alive and out of hospital’ than the group that had usual care. Taken together, the increase in survival rates and reduction in hospital stay improved with the implementation of the early warning system.
“This study adds to the recent national discourse about sepsis early warning systems.
“Recent studies assessed how that score worked in isolation, which is not reflective of how it would actually be used in the real world. We envisioned the early warning system’s role as supportive to our healthcare team’s response to sepsis. Most importantly, we assessed the utility of the tool with the highest quality approach—a randomised controlled study. In fact, our work stands out as the first published randomised controlled evaluation of a model-based early warning system in the emergency room setting,” Tarabichi said.
MetroHealth Senior Vice President Brook Watts, Professor of Medicine at the Case Western Reserve School of Medicine, said the study demonstrates that, from an institutional level, MetroHealth is committed to working collaboratively to try new approaches to improve outcomes from patients.
Professor Watts said: “We rigorously validate and implement new tools that can help our patients.
“This was an integrated team-based response to sepsis, with augmentation by artificial intelligence. It demonstrates our focus on quality improvement. We have great providers and information service experts willing and interested in leveraging new technology to improve patient care.”