Algorithm Could Predict Sepsis In At-Risk Patients

By Christine Kern, contributing writer

Johns Hopkins researchers have developed an algorithm combining 27 factors to assess patient risk.

Sepsis kills more Americans annually than AIDs, breast cancer, and prostate cancer combined, and for patients who contract it, hours can mean the difference between life and death.

Now, researchers at Johns Hopkins have developed an algorithm combining 27 factors to assess patient risk and predict which patients face the highest likelihood of developing sepsis. The new tool correctly predicted septic shock in 85 percent of cases, and also avoided increasing false positive rates like current screening methods tend to do.

“The critical advance our study makes is to detect these patients early enough that clinicians have time to intervene,” says study lead Suchi Saria, an assistant professor of computer science in Johns Hopkins’ Whiting School of Engineering and of health policy in the Bloomberg School of Public Health. The study was published by the journal Science Translational Medicine.

Called “A Targeted Real-Time Early Warning Score (TREWScore) for septic shock,” the algorithm predicts in advance which patients are at highest risk for septic shock providing clinicians enough lead time to intervene before patients succumb to the most damaging effects of sepsis. The study drew on electronic health records of 16,234 patients admitted to intensive care units – including medical, surgical, and cardiac units – at Boston’s Beth Israel Deaconess Medical Center from 2001 to 2007.

Co-author Peter J. Pronovost, senior vice president for patient safety and quality at Johns Hopkins Medicine, explained the research is a significant step towards treating a condition that affects an estimated one million Americans – killing approximately 200,000 – every year, many of them in hospitals and nursing homes.

“We know a lot of those deaths would likely be preventable” if sepsis were diagnosed well before it develops into septic shock and organ failure, said Pronovost, who directs the Armstrong Institute for Patient Safety and Quality at Johns Hopkins Medicine. “Right now, much of sepsis is invisible until someone is on death’s door.” Every passing hour before sepsis patients receive antibiotics, he said, “correlates strongly with risk of death.”

The algorithm could be a game-changer in the fight against sepsis, and could prove to be a valuable tool for healthcare providers in improving patient outcomes.