Researchers at the University of Pittsburgh School of Medicine has created an algorithm, after studied electronic health records (HER) data, which recognizes and assigns patients into four separate types of sepsis. Sepsis, according to the lead study author and member of University of Pittsburgh’s Clinical Research, Investigation, and Systems Modeling of Acute Illness Center, is a life-threatening condition that occurs when a patient’s bodily response to an infection harms its own tissues and organs, has traditionally been treated with a “one size fits all,” approach.
Backed by the National Institutes of Health, Dr. Seymour and his research team utilized computer algorithms for the study to evaluate 29 clinical variables reported in the EHRs of more than 20,000 UPMC patients, where they were diagnosed with sepsis within six hours of arriving at the hospital from 2010 to 2012. Where the algorithm organized patients into four distinct types of sepsis are include Alpha – 33 percent of patients; individuals had the fewest abnormal lab results, least organ dysfunction, and lowest in-hospital death rate. Beta – 27 percent of patients; older individuals with most chronic illnesses and kidney dysfunction. Gamma – patients with similar frequency as Beta individuals, but with increased inflammation and primarily pulmonary dysfunction. Delta – 13 percent of patients; most deadly type, often with liver dysfunction and shock and the highest in-hospital death rate.
For the study, researchers found that the algorithm to be successful on further tests of EHRs from 43,000 UPMC sepsis patients in addition to clinical data from around 500 pneumonia patients at 28 U.S. hospitals. Afterward, the research team tested their findings on a number of recently completed international clinical trials that examined various therapies for sepsis. However, the team also found that when participants in these trials were separated by the four sepsis types, some trials that previously failed ended up succeeding. The researchers’ next steps in sepsis therapy are to target treatments which deploy to the specific kinds of sepsis and design new clinical trials to analyze their effectiveness.