Cowan Lorna M, Adamestam Imad, Masterson John A, Beatty Monika, Boardman James P, Chislett Louis, Johnston Pamela, Joss Judith, Lawrence Heather, Litchfield Kerry, Plummer Nicholas, Rhode Stella, Walsh Timothy S, Wise Arlene, Wood Rachael, Weir Christopher J, Lone Nazir I
Department of Anaesthesia, Critical Care, and Pain Medicine, Royal Infirmary of Edinburgh, University of Edinburgh, Edinburgh, UK.
Edinburgh Clinical Trials Unit, Usher Institute, The University of Edinburgh, Edinburgh, UK.
J Intensive Care Soc. 2025 Jan 23;26(2):164-171. doi: 10.1177/17511437251313700. eCollection 2025 May.
Identifying women at highest or lowest risk of perinatal intensive care unit (ICU) admission may enable clinicians to risk stratify women antenatally so that enhanced care or elective admission to ICU may be considered or excluded in birthing plans. We aimed to develop a statistical model to predict the risk of maternal ICU admission.
We studied 762,918 pregnancies between 2005 and 2018. Predictive models were constructed using multivariable logistic regression. The primary outcome was ICU admission. Additional analyses were performed to allow inclusion of delivery-related factors. Predictors were selected following expert consultation and reviewing literature, resulting in 13 variables being included in the primary analysis: demographics, prior health status, obstetric history and pregnancy-related factors. A complete case analysis was performed. -fold cross validation was used to mitigate against overfitting.
Complete data were available for 578,310 pregnancies, of whom 1087 were admitted to ICU (0.19%). Model performance was fair (area under the ROC curve = 0.66). A comparatively high cut-point of ⩾0.6% for ICU admission risk resulted in a negative predictive value (NPV) of 99.8% (specificity 97.8%) but positive predictive value (PPV) of 0.8% (sensitivity 9.1%). Models including delivery-related factors demonstrated superior discriminative performance.
Our model for maternal ICU admission has an acceptable discriminative performance. The low frequency of ICU admission and resulting low PPV indicates that the model would be unlikely to be useful as a 'rule-in' test for pre-emptive consideration of ICU admission. Its potential for improving efficiency in screening as a 'rule-out' test remains uncertain.
识别围产期重症监护病房（ICU）收治风险最高或最低的女性，可能使临床医生能够在产前对女性进行风险分层，以便在分娩计划中考虑或排除加强护理或择期入住ICU的情况。我们旨在开发一种统计模型来预测产妇入住ICU的风险。
我们研究了2005年至2018年间的762,918例妊娠。使用多变量逻辑回归构建预测模型。主要结局是入住ICU。进行了额外的分析以纳入与分娩相关的因素。在专家咨询和文献回顾后选择预测因素，最终在主要分析中纳入了13个变量：人口统计学、既往健康状况、产科病史和与妊娠相关的因素。进行了完整病例分析。采用k折交叉验证来减轻过度拟合。
578,310例妊娠有完整数据，其中1087例入住ICU（0.19%）。模型性能一般（ROC曲线下面积=0.66）。ICU入院风险的相对较高切点⩾0.6%导致阴性预测值（NPV）为99.8%（特异性97.8%），但阳性预测值（PPV）为0.8%（敏感性9.1%）。纳入与分娩相关因素的模型表现出更好的判别性能。
我们的产妇入住ICU模型具有可接受的判别性能。ICU入院频率低以及由此导致的低PPV表明，该模型作为预发性考虑ICU入院的“纳入”测试不太可能有用。其作为“排除”测试提高筛查效率的潜力仍不确定。
