A Prediction Model of Preeclampsia in Hyperglycemia Pregnancy.

PURPOSE: To investigate the risk factors associated with preeclampsia in hyperglycemic pregnancies and develop a predictive model based on routine pregnancy care.

PATIENTS AND

METHODS

The retrospective collection of clinical data was performed on 951 pregnant women with hyperglycemia, including those diagnosed with diabetes in pregnancy (DIP) and gestational diabetes mellitus (GDM), who delivered after 34 weeks of gestation at the Maternal and Child Health Hospital Affiliated to Anhui Medical University between January 2017 and December 2019. Observation indicators included liver and kidney function factors testing at 24-29+6 weeks gestation, maternal age, and basal blood pressure. The indicators were screened univariately, and the "rms" package in R language was applied to explore the factors associated with PE in HIP pregnancy by stepwise regression. Multivariable logistic regression analysis was used to develop the prediction model. Based on the above results, a nomogram was constructed to predict the risk of PE occurrence in pregnant women with HIP. Then, the model was evaluated from three aspects: discrimination, calibration, and clinical utility. The internal validation was performed using the bootstrap procedure.

RESULTS

Multivariate logistic regression analysis showed that cystatin C, uric acid, glutamyl aminotransferase, blood urea nitrogen, and basal systolic blood pressure as predictors of PE in pregnancy with HIP. The predictive model yielded an area under curve (AUC) value of 0.8031 (95% CI: 0.7383-0.8679), with an optimal threshold of 0.0805, at which point the sensitivity was 0.8307 and specificity of 0.6604. Hosmer-Lemeshow test values were P = 0.3736, Brier score value was 0.0461. After 1000 Bootstrap re-samplings for internal validation, the AUC was 0.7886, the Brier score was 0.0478 and the predicted probability of the calibration curve was similar to the actual probability. A nomogram was constructed based on the above to visualize the model.

CONCLUSION

This study developed a model for predicting PE in pregnant women with HIP, achieving high predictive performance of PE risk through the information of routine pregnancy care.