THURSDAY, Sept. 16 (HealthDay News) -- Researchers have developed a noninvasive tool based on gestational age, birth weight, and real-time data routinely collected in neonatal intensive care units to predict morbidity risk in premature infants; their findings have been published in the Sept. 8 issue of Science Translational Medicine.
Suchi Saria, of Stanford University in Palo Alto, Calif., and colleagues validated a physiological assessment score they developed for preterm newborns on 138 infants to determine the effectiveness of the algorithm for prospectively identifying premature infants at risk for short- and long-term morbidity.
The researchers found that the score, called PhysiScore, outperformed the standard Apgar score and other neonatal scoring systems. It predicted overall morbidity with 86 percent sensitivity and 96 percent specificity, and specific complications at 90 to 96 percent sensitivity and 100 percent specificity.
"Our flexible methodology of individual risk prediction based on automated, rapid, noninvasive measurements can be easily applied to a range of prediction tasks to improve patient care and resource allocation," the authors write.
Abstract
Full Text (subscription or payment may be required)