Sepsis, a life-threatening complication of an infection, is a global health problem affecting millions of people every year. As prompt treatment is crucial to avoid death due to sepsis, studies have focused on accelerating the detection process. Now, researchers have developed a unique artificial intelligence (AI) algorithm that can detect sepsis before symptom onset and potentially save lives.
Researchers from the University of California - San Diego, found that their AI algorithm, COMPOSER, which uses real-time data to predict sepsis before obvious clinical manifestations, leads to a 17% reduction in mortality. According to the researchers, it works silently behind the scenes, continuously surveilling every patient for signs of possible sepsis.
After a patient checks in at the emergency department, the algorithm starts to continuously monitor 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 university’s press statement explained.
If a patient shows multiple variables, which is recorded as high risk for sepsis infection, the AI algorithm will notify nursing staff through the hospital's electronic health record. The staff will then check with the physician and determine the treatment plan. The study was published in the online edition of npj Digital Medicine.
These advanced AI algorithms can detect patterns that are not initially obvious to the human eye, study co-author Shamim Nemati said in the statement. "The system can look at these risk factors and come up with a highly accurate prediction of sepsis. Conversely, if the risk patterns can be explained by other conditions with higher confidence, then no alerts will be sent,” Nemati added.
COMPOSER was activated in December 2022 and is being utilized in many hospital in-patient units throughout UC San Diego Health in the United States. “It is because of this AI model that our teams can provide life-saving therapy for patients quicker," co-author Gabriel Wardi, who is also a physical at UC San Diego Health said in the statement.
This AI algorithm could potentially save lives if implemented appropriately. A 2022 study, published in the journal Chest, revealed that more than half of the patients in intensive care units in India suffer from sepsis. Developments such as the new AI algorithms could help reduce India’s high burden of sepsis.