Intrapartum hypertension is associated with adverse outcomes, yet tools for its prediction are limited. This study aimed to develop a predictive model using routine clinical data. This retrospective case-control study included 200 women, comprising 100 with intrapartum hypertension and 100 matched controls. We developed a predictive model by first screening candidate variables through univariate analysis. Variables that showed significant differences were then entered into a multivariate logistic regression model to identify independent predictors. The model’s performance was evaluated using the area under the receiver operating characteristic curve (AUC). Internal validation was conducted via the bootstrap method with 500 resamples to correct for optimism and to estimate a more generalizable AUC. Intrapartum hypertension was defined as a systolic blood pressure ≥ 140 mmHg or a diastolic blood pressure ≥ 90 mmHg during labor, confirmed on two separate occasions. Risk factors were identified using univariate and multivariate logistic regression, and predictive performance was assessed by ROC analysis. The case group exhibited higher rates of cesarean delivery (14% vs. 4%), higher peak blood pressure, and greater neonatal birth weight (all P < 0.05). Independent risk factors identified were elevated lactate dehydrogenase (LDH), higher admission weight, gestational diabetes mellitus, proteinuria in the second trimester or antenatal period (all P < 0.05). The final multivariate model achieved an AUC of 0.832. After bootstrap internal validation, the optimism-corrected AUC was 0.815. A model incorporating five routinely available clinical parameters (including lactate dehydrogenase level, admission weight, gestational diabetes mellitus, and second-trimester or antenatal proteinuria) effectively identifies parturients at high risk for developing intrapartum hypertension. This tool can facilitate early, targeted monitoring in clinical practice.
Lu et al. (2026) studied this question.