Decreased laboratory testing for lecithin-to-sphingomyelin ratio and phosphatidylglycerol after fetal lung maturity assessment from lamellar body count in amniotic fluid

Abstract

The objectives of this study were to do inexpensive lamellar body count (LBC) in amniotic fluid, to do statistical analysis to evaluate cutoff values for fetal lung maturity (FLM) and fetal lung immaturity (FLI), to derive a threshold for obtaining a lecithin-to-sphingomyelin (L/S) ratio and phosphatidylglycerol percentage (%PG), and to determine the potential cost savings to the hospital if they use this new method. Testing (LBC, L/S ratio, and %PG) was done on 123 specimens of amniotic fluid. Receiver operating characteristic (ROC) curve, discriminant, linear regression, chi2, and cost analyses were used to evaluate the laboratory and financial parameters. Lamellar body counts of greater than 41,500 (Coulter MAXM: sensitivity, 90.5%; specificity, 87.7%; positive predictive value, 79.2%; negative predictive value, 94.7%) and greater than 32,000 (Coulter Gen.S: sensitivity, 90.5%; specificity, 85.2%; positive predictive value, 76.0%; negative predictive value, 94.5%) were the best threshold for biochemical FLM. Similarly, LBC of less than 24,000 (MAXM: sensitivity, 78.6%; specificity, 100%; positive predictive value, 100%; negative predictive value, 90.0%) and less than 21,000 (Gen.S: sensitivity, 71.4%; specificity, 100%; positive predictive value, 100%; negative predictive value, 87.1%) provided the best statistical cutoff for biochemical FLI from discriminant analysis. The authors concluded that FLM and FLI can be predicted with reasonable accuracy from LBC in amniotic fluid specimens. The expensive and not easily accessible L/S ratio and %PG can then be done only in cases in which LBC indicates transitional FLM. A cascade approach results in 86% savings to the hospital if the L/S ratio and %PG are not sent to a reference laboratory.