JMIR Publications

ABSTRACT

Background:

There is a pioneer algorithm developed by Fetal Medicine Foundation (FMF) to predict preeclampsia based on maternal characteristics combined with biophysical and/or biochemical markers. The Afro-Caribbean ethnicity is the second risk factor, in magnitude, found in populations tested by FMF, which was not confirmed in a Brazilian scenario.

Objective:

This study aimed to analyze the performance of preeclampsia (PE) prediction software by customization of maternal ethnicity.

Methods:

It was an observational, cross-sectional study, with secondary evaluation of data from FMF first trimester screening tests of singleton pregnancies. Risk scores were calculated from maternal characteristics and biophysical markers and were presented as the risk for early PE (PE34) and preterm PE (PE37). The following steps were followed: (1)identification of women characterized as black ethnicity; (2)calculation of early and preterm PE risk, reclassifying them as white, which generated a new score; (3)comparison of the proportions of women categorized as high risk between the original and new scores; (4)construction of the receiver operator characteristic(ROC)curve; (5)calculation of the area under the curve(AUC), sensitivity and false positive rate(FPR); (6)comparison of the AUC, sensitivity and FPR of the original with the new risk by chi-square test.

Results:

A total of 1531 cases composed the final sample, with 219 out of 1531 cases (14.3% - 95% CI: 12.5 - 16.0) and 182 out of 1531 cases (11.9% (95%- CI: 10.3 - 13.5) were respectively classified as high risk for PE development, originally and after recalculating the new risk. The comparison of FMF2012 predictive model performance between the originally estimated risks and the estimated “new risks”, showed that the difference was not significant for sensitivity and AUC, but it was significant for FPR.

Conclusions:

We concluded that black ethnicity classification of Brazilian pregnant women by FMF2012 algorithm increases the false positive rate. Suppressing ethnicity effect didn’t improve the test sensitivity. By modifying demographic characteristics it is possible to improve some performance aspects of clinical prediction tests. Clinical Trial: No trial registration