Preeclampsia Prediction Similar, Modest with Two Algorithms

This article originally appeared here.
Algorithms for Preeclampsia Prediction
Algorithms for Preeclampsia Prediction

(HealthDay News) — Two algorithms offer similar and modest performance for predicting preeclampsia in nulliparous women at 11–13 weeks of gestation, according to a study published online December 4 in BJOG: An International Journal of Obstetrics & Gynaecology.

Ragnhild B. Skråstad, from the Norwegian University of Science and Technology in Trondheim, and colleagues conducted a prospective screening study involving 541 nulliparous women at 11–13 weeks gestational age. The authors examined the First Trimester Screening Program version 2.8 by the Fetal Medicine Foundation (FMF) and the Preeclampsia Predictor TM version 1 revision 2 by Perkin Elmer (PREDICTOR) for the prediction of preeclampsia.

The researchers observed similar performance for the two algorithms, which was quite poor. At a 10% fixed false positive rate, prediction of preeclampsia requiring delivery <42 weeks had an area under the curve of 0.77 and sensitivity of 40% for the FMF algorithm, and an area under the curve of 0.74 and sensitivity of 30% for the PREDICTOR algorithm. At a 10% fixed false positive rate, the area under the curve was 0.94 and sensitivity 80% for the FMF algorithm for preeclampsia requiring delivery <37 weeks.

"Fetal Medicine Foundation and PREDICTOR algorithms had similar and only modest performance in predicting preeclampsia," the authors write.

Abstract
Full Text (subscription or payment may be required)

Loading links....