Development and validation of a risk prediction model for preeclampsia at Debre Tabor Comprehensive Specialized Hospital, Northwest Ethiopia

Preeclampsia is one of the leading causes of maternal and perinatal morbidity and mortality in low-resource settings, including Ethiopia. Systematic screening of preeclampsia is currently the focus of clinical attention. Therefore, a risk prediction model for preeclampsia can be developed based on easily available predictors. A retrospective cohort study was conducted at Debretabor Comprehensive Specialized Hospital among a total of 1100 pregnant women. A simplified risk prediction model was developed based on maternal characteristics using a binary logistic regression model and the model's performance was assessed by discrimination power and calibration. The internal validity of the model was evaluated by the bootstrapping technique. Decision curve analysis was used to determine the clinical impact of the model. Age>35 years, primigravida, chronic hypertension, diabetes mellitus, multiple gestations, family history of preeclampsia and mean arterial pressure >90 mmHg remained in the final multivariable prediction model. The discriminatory power of the model was 85.9% (95% CI=0.823, 0.895). This study explored the possibility of predicting preeclampsia using easily available maternal characteristics. Therefore, using this model could help identify preeclampsia, so it can be applied in clinical practice. We recommend that researchers externally validate the model and that clinicians use a risk prediction model.