A computer algorithm developed by researchers from Johns Hopkins in Baltimore could correctly predict septic shock in 85 percent of cases without increasing the number of false positives, according to a study published in Science Translational Medicine.
"The critical advance our study makes is to detect these patients early enough that clinicians have time to intervene," Suchi Saria, a Johns Hopkins assistant professor of computer science and health policy and the study's leader, told Hub.
Researchers created an algorithm that determines a Targeted Real-time Early Warning Score based on 27 factors which measure a patient's risk of septic shock. To do so, researchers used electronic health records of 16,234 patients admitted to intensive care units at Boston-based Beth Israel Deaconess Medical Center from 2001 to 2007.
"With a median lead time of over 24 hours, this scoring algorithm may allow clinicians enough time to intervene before the patients suffer the most damaging effects of sepsis," the study reads.
Now the researchers are looking into how the algorithm and TREWScore can be used in a hospital or nursing home, according to the Hub report.