Preeclampsia is one of the leading causes of maternal and fetal morbidity and mortality. Due to the lack of effective preventive measures, its prediction is essential to its prompt management. This study aimed to develop models using machine learning to predict late-onset preeclampsia using hospital electronic medical record data. The performance of the machine learning based models and models using conventional statistical methods were also compared. A total of 11,006 pregnant women who received antenatal care at Yonsei University Hospital were included. Maternal data were retrieved from electronic medical records during the early second trimester to 34 weeks. The prediction outcome was late-onset preeclampsia occurrence after 34 weeks’ gestation. Pattern recognition and cluster analysis were used to select the parameters included in the prediction models. Logistic regression, decision tree model, naïve Bayes classification, support vector machine, random forest algorithm, and stochastic gradient boosting method were used to construct the prediction models. C-statistics was used to assess the performance of each model. The overall preeclampsia development rate was 4.7% (474 patients). Systolic blood pressure, serum blood urea nitrogen and creatinine levels, platelet counts, serum potassium level, white blood cell count, serum calcium level, and urinary protein were the most influential variables included in the prediction models. C-statistics for the decision tree model, naïve Bayes classification, support vector machine, random forest algorithm, stochastic gradient boosting method, and logistic regression models were 0.857, 0.776, 0.573, 0.894, 0.924, and 0.806, respectively. The stochastic gradient boosting model had the best prediction performance with an accuracy and false positive rate of 0.973 and 0.009, respectively. The combined use of maternal factors and common antenatal laboratory data of the early second trimester through early third trimester could effectively predict late-onset preeclampsia using machine learning algorithms. Future prospective studies are needed to verify the clinical applicability algorithms.

Homing of endothelial progenitor cells (EPCs) to the neovascular zone is now considered to be an essential step in the formation of vascular networks during embryonic development and also for neovascularization in postnatal life. We report here the prominent role of the insulin-like growth factor 2 (IGF2)/IGF2 receptor (IGF2R) system in promoting EPC homing. With high-level expression of IGF2R in EPCs, IGF2-induced hypoxic conditions stimulated multiple steps of EPC homing in vitro and promoted both EPC recruitment and incorporation into the neovascular area, resulting in enhanced angiogenesis in vivo. Remarkably, all IGF2 actions were exerted predominantly through IGF2R-linked G(i) protein signaling and required intracellular Ca²⁺ mobilization induced by the β2 isoform of phospholipase C. Together, these findings indicate that locally generated IGF2 at either ischemic or tumor sites may contribute to postnatal vasculogenesis by augmenting the recruitment of EPCs. The utilization of the IGF2/IGF2R system may therefore be useful for the development of novel means to treat angiogenesis-dependent diseases.

Park EY, et al. Yonsei Med J. 2012 May;53(3):459-466. http://dx.doi.org/10.3349/ymj.2012.53.3.459