Edward Antwi E, Amoakoh-Coleman M, Vieira DL, et al. - Given that development of prediction models for gestational hypertension and preeclampsia involved data and assumptions from developed countries, researchers sought to investigate their suitability and application for low resource settings. Searching seven databases, they retrieved 8,309 articles; of these, 40 were eligible for review. In 77% of all the prediction models, biomarkers were combined with maternal clinical characteristics. In most models, the following were used as predictive biomarkers: pregnancy associated plasma protein-A and placental growth factor. In most of the evaluated studies, the CHARMS, TRIPOD and STROBE guidelines were not completely followed in prediction model development and reporting. Prediction modelling studies and subsequent application of prediction models in clinical practice may improve with adherence to these guidelines. They recommend performing external validation of prediction models using maternal characteristics, with good discrimination and calibration, for use in low and middle income countries where biomarker assays are not routinely available.