Lasarev MR, Bialk ER, Allen DB, et al. - In view of the frequent encounter to false-positive and false-negative results in detection of babies at raised risk for congenital adrenal hyperplasia due to 21-hydroxylase deficiency (21OHD), with screening algorithms typically use cutoff values for a key steroid(s) and include considerations for covariates, such as gestational age or birth weight, researchers here evaluated principal component analysis (PCA) in the newborn screening setting to ascertain if it can enhance the positive predictive value of 21OHD screening. They applied PCA to a data set of 920 newborns with measured concentrations of 5 key steroids that are identified to be impaired in patients with 21OHD. This study is identified to be the first report of PCA applied to newborn screening for 21OHD. Findings from a retrospective study comparing the current algorithm to a tree-based algorithm using PCA-derived variables, revealed improvement in positive predictive value of 21OHD screening from 20.0% to 66.7% in correlation with application of PCA. The 21OHD reporting algorithm greatly simplified with the streamlined PCA-derived decision tree, comprising only 3 assessment points.