BACKGROUND Hypertensive disorders of pregnancy (HDP) are a major contributor to maternal morbidity, mortality, and accelerated cardiovascular (CV) disease. Comorbid conditions are likely important predictors of CV risk in pregnant people. Currently, there is no way to predict which people with HDP are at risk of acute CV complications. We developed and validated a predictive model for all CV events and for heart failure, renal failure, and cerebrovascular events specifically after HDP. METHODS Models were created using the Premier Healthcare Database. The inclusion criteria for the model dataset were delivery with an HDP with discharge from October 1, 2015 to December 31, 2020. Machine learning methods were used to derive predictive models of CV events occurring during delivery hospitalization (Index Model) or during readmission (Readmission Model) using a training set (60%) to estimate model parameters, a validation set (20%) to tune model hyperparameters and select a final model, and a test set (20%) to evaluate final model performance. RESULTS The total model cohort consisted of 553,658 deliveries with an HDP. A CV event occurred in 6501 (1.2%) of the delivery hospitalizations. Multilabel neural networks were selected for the Index Model and Readmission Model due to favorable performance compared to alternatives. This approach is designed for prediction of multiple events that share risk factors and may cooccur. The Index Model predicted all CV events with area under the receiver operating curve (AUROC) 0.878 and average precision (AP) 0.239 (cerebrovascular events: AUROC 0.941, heart failure: AUROC 0.898, and renal failure: AUROC 0.885). With a positivity threshold set to achieve ≥90% sensitivity, model specificity was 65.0%, 83.5%, 68.6%, and 65.6% for predicting all CV events, cerebrovascular events, heart failure, and renal failure, respectively. CV events within 1 year of delivery occurred in 3018 (0.6%) individuals. The Readmission Model predicted all CV events with AUROC 0.717 and AP 0.022 (renal failure: AUROC 0.748, heart failure: AUROC 0.734, and cerebrovascular events AUROC 0.698). Feature importance analysis indicated that the presence of chronic renal disease, cardiac disease, pulmonary hypertension, and preeclampsia with severe features had the greatest effect on the prediction of CV events. CONCLUSIONS Among individuals with HDP, our multilabel neural network model predicted CV events at delivery admission with good classification and events within 1 year of delivery with fair classification.

中文翻译：

---

开发和验证妊娠期高血压疾病患者孕产妇心血管发病率事件的预测模型。


背景 妊娠期高血压疾病 （HDP） 是孕产妇发病率、死亡率和加速心血管 （CV） 疾病的主要因素。合并症可能是孕妇 CV 风险的重要预测指标。目前，无法预测哪些 HDP 患者有急性 CV 并发症的风险。我们开发并验证了所有 CV 事件以及心力衰竭、肾衰竭和脑血管事件的预测模型，特别是在 HDP 之后。方法 使用 Premier Healthcare Database 创建模型。模型数据集的纳入标准是在 2015 年 10 月 1 日至 2020 年 12 月 31 日期间使用 HDP 交付。使用机器学习方法得出分娩住院期间（索引模型）或再入院期间（再入院模型）期间发生的 CV 事件的预测模型，使用训练集 （60%） 来估计模型参数，使用验证集 （20%） 来调整模型超参数并选择最终模型，以及测试集 （20%） 来评估最终模型性能。结果 整个模型队列包括 553,658 次 HDP 交付。6501 例 （1.2%） 的分娩住院病例中发生了 CV 事件。由于与其他方法相比，多标签神经网络的性能优于 Index Model 和 Readmission Model。此方法旨在预测共享风险因素并可能同时发生的多个事件。指数模型预测所有 CV 事件，受试者工作曲线下面积 （AUROC） 为 0.878，平均精度 （AP） 为 0.239 （脑血管事件：AUROC 0.941，心力衰竭：AUROC 0.898，肾功能衰竭：AUROC 0.885）。将阳性阈值设置为达到 ≥90% 的灵敏度后，模型特异性为 65.0% 、 83.5% 、 68.6% 和 65。预测所有 CV 事件、脑血管事件、心力衰竭和肾功能衰竭分别为 6%。分娩后 1 年内的 CV 事件发生在 3018 例 （0.6%） 个体中。再入院模型预测所有 CV 事件，AUROC 为 0.717 和 AP 为 0.022 （肾功能衰竭：AUROC 0.748，心力衰竭：AUROC 0.734，脑血管事件 AUROC 0.698）。特征重要性分析表明，慢性肾病、心脏病、肺动脉高压和子痫前期伴严重特征的存在对 CV 事件的预测影响最大。结论 在 HDP 个体中，我们的多标签神经网络模型预测了分娩入院时的 CV 事件，分类良好，分娩后 1 年内的事件分类公平。