Validation of a Predictive Model of Pre-eclampsia from a Cohort Study in Pregnant Women

Background & Aims: To validate a predictive model of pre-eclampsia for classifying pregnant women into pre-eclamptic and healthy groups. Materials Methods: A cohort study was carried out in total 132 women, including biochemical clinical parameters assessing the classification performed by from 10-fold cross-validation method experts’ criteria. Results: highly value obtained set included proposed model. Wilks’ Lambda, eigenvalues, canonical correlation, distances between centroids groups point to high classificatory power discriminant function. Risk indexes, computed centroids, provided measure different risk levels this condition. The analysis these indexes prospective allowed effect parameters. new ten models achieved 100% correct (AUC:1.00; CI:0.00-1.00; p=0.00). sensitivity specificity model, ROC curves, showed consistency even though there were only four manifestations entity. Moreover, assessed criteria study, showing an AUC 3 rd trimester pregnancy. Conclusions: could constitute accurate diagnostic tool, employing markers oxidative stress as significant element prediction