Development, validation, and clinical utility of a risk prediction model for recurrent preeclampsia

Abstract

Objectives: We aim to establish a predictive model for recurrent preeclampsia. Methods: A retrospective review of medical records from three hospitals between 2010 and 2021 was conducted. The study included women who had two consecutive singleton deliveries at the same hospital, with the first delivery complicated by preeclampsia. A multivariable logistic regression model was constructed using a training cohort, and subsequently cross-validated and tested using an independent cohort. The model's performance was assessed in terms of discrimination and calibration, and its clinical utility was evaluated using decision curve analysis (DCA). Results: Among 296 405 deliveries, 694 women met the inclusion criteria, with 151 (21.8%) experiencing recurrent preeclampsia. The predictive model incorporated 10 risk factors from previous preeclampsia, including gestational weeks with elevated blood pressure, gestational diabetes mellitus (GDM), pericardial effusion, heart failure, limb edema, serum creatinine, white blood cell count, low platelet counts within one week before delivery, SBP on the first postpartum day, and postpartum antihypertensive use. Additionally, one risk factor from the index pregnancy was included, which was antihypertensive use before 20 weeks. The model demonstrated better discrimination, calibration, and a net benefit across a wide range of recurrent preeclampsia risk thresholds. Furthermore, the model has been translated into a clinical risk calculator, enabling clinicians to calculate individualized risks of recurrent preeclampsia. Conclusion: Our study demonstrates that a predictive tool utilizing routine clinical and laboratory factors can accurately estimate the risk of recurrent preeclampsia. This predictive model has the potential to facilitate shared decision-making by providing personalized and risk-stratified care.