Early-Onset Versus Late-Onset Preeclampsia in Bogotá, Colombia: Differential Risk Factor Identification and Evaluation Using Traditional Statistics and Machine Learning

Abstract

Background/Objectives: Preeclampsia (PE) is a major cause of maternal and perinatal morbidity and mortality, particularly in low- and middle-income countries. Early-onset PE (EOP) and late-onset PE (LOP) are distinct clinical entities with differing pathophysiological mechanisms and prognoses. However, few studies have explored differential risk factors for EOP and LOP in Latin American populations. This study aimed to identify and assess clinical risk factors for predicting EOP and LOP in a cohort of pregnant women from Bogotá, Colombia, using traditional statistics and machine learning (ML). Methods: A cross-sectional observational study was conducted on 190 pregnant women diagnosed with PE (EOP = 80, LOP = 110) at a tertiary hospital in Bogotá between 2017 and 2018. Risk factors and perinatal outcomes were collected via structured interviews and clinical records. Traditional statistical analyses were performed to compare the study groups and identify associations between risk factors and outcomes. Eleven ML techniques were used to train and externally validate predictive models for PE subtype and secondary outcomes, incorporating permutation-based feature importance to enhance interpretability. Results: EOP was significantly associated with higher maternal education and history of hypertension, while LOP was linked to a higher prevalence of allergic history. The best-performing ML model for predicting PE subtype was linear discriminant analysis (recall = 0.71), with top predictors including education level, family history of perinatal death, number of sexual partners, primipaternity, and family history of hypertension. Conclusions: EOP and LOP exhibit distinct clinical profiles in this cohort. The combination of traditional statistics with ML may improve early risk stratification and support context-specific prenatal care strategies in similar settings.

Keywords: Latin America; artificial intelligence; early-onset preeclampsia; hypertension in pregnancy; late-onset preeclampsia; machine learning; risk factors; traditional statistics.

Figure 1

Filtered correlation matrix between particular risk factors and outcomes considered in this study. This matrix was obtained from the full correlation matrix (Figure S1) by applying a threshold of |ρ| ≥ 0.12 for the correlation coefficient.

Figure 2

Recall of the machine learning models developed for the prediction of categorical outcomes, after variable selection. HELLP: hemolysis, elevated liver enzymes, low platelet count syndrome. IUGR: intrauterine growth restriction. LogReg: logistic regression; LDA: linear discriminant analysis. GNB: Gaussian naïve Bayes. KNN: k-nearest neighbors. DecTree: decision tree. RF: random forest. GradBoost: gradient boosting. SVM: support vector machine. MLP: simple multilayer perceptron.

Figure 3

Contribution of variables for models that best predict the analyzed categorical outcomes. (A) PE onset. (B) Delivery type. (C) Newborn vital status. (D) Newborn malformations. (E) Eclampsia or HELLP syndrome. (F) IUGR. PE: preeclampsia. HELLP: hemolysis, elevated liver enzymes, low platelet count syndrome. IUGR: intrauterine growth restriction. LDA: linear discriminant analysis. KNN: k-nearest neighbors. GNB: Gaussian naïve Bayes. LogReg: logistic regression. RF: random forest.