基于机器学习算法构建胎儿生长受限不良围产结局预测模型:一项回顾性研究
在中国多中心回顾性研究中,纳入361例胎儿生长受限(FGR)孕妇作为训练集与内部测试集、50例作为外部测试集,采用随机森林、LASSO和逻辑回归筛选特征后以Stacking等六种机器学习方法建模预测不良围产结局(APO)。Stacking模型在内部测试集AUROC为0.861(95%CI 0.838-0.896),外部测试集AUROC为0.906(95%CI 0.875-0.947),校准曲线显示预测风险与观察风险高度一致。
要点
- Stacking模型预测FGR不良围产结局的内部测试集AUROC为0.861(95%CI 0.838-0.896),外部测试集AUROC为0.906(95%CI 0.875-0.947)。
- 筛选出的显著预测因素包括孕妇体重指数、高血压、FGR诊断时孕周、估计胎儿体重z评分、估计胎儿体重增长速度及异常脐动脉多普勒。
- 出现APO组妊娠期高血压疾病发生率74.8%,无APO组为18.8%(p<0.001)。
核心结论
- 整合母亲临床因素与超声参数的机器学习算法对诊断时FGR的APO具有良好预测价值,提示机器学习技术可能是早期识别FGR妊娠中高危APO的有效方法。
研究设计与样本
- 回顾性研究,在中国多中心开展,纳入2021年1月至2023年11月期间围产期诊断为FGR的单胎胎儿。
- 北京妇产医院361例妊娠作为训练集和内部测试集,海淀区妇幼保健院50例妊娠作为外部测试集。
- 采用随机森林、LASSO和逻辑回归进行特征筛选,随后使用包括Stacking在内的六种机器学习方法构建预测FGR的APO模型。
主要发现
- 诊断时孕周均值±标准差在无APO组为32.3±4.8周,在出现APO组为27.3±3.7周。
- 出现APO组妊娠期高血压疾病发生率74.8%,无APO组为18.8%(p<0.001)。
- 在17个候选预测因素中,整合随机森林、LASSO和逻辑回归方法识别出孕妇体重指数、高血压、FGR诊断时孕周、估计胎儿体重z评分、估计胎儿体重增长速度和异常脐动脉多普勒(定义为搏动指数高于第95百分位或出现舒张期血流缺失/反向)为显著预测因素。
- Stacking模型在内部测试集AUROC为0.861(95%CI 0.838-0.896),在外部测试集AUROC为0.906(95%CI 0.875-0.947)。
- 校准曲线显示预测风险与观察风险高度一致,内部和外部测试集的Hosmer-Lemeshow检验分别为p=0.387和p=0.825。
临床怎么用
- 原文结论指出机器学习技术可能是早期识别FGR妊娠中高危APO的有效方法。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVE: To create and validate a machine learning (ML)-based model for predicting the adverse perinatal outcome (APO) in foetal growth restriction (FGR) at diagnosis. DESIGN: A retrospective study. SETTING: Multi-centre in China. POPULATION: Pregnancies affected by FGR. METHODS: We enrolled singleton foetuses with a perinatal diagnosis of FGR who were admitted between January 2021 and November 2023. A total of 361 pregnancies from Beijing Obstetrics and Gynecology Hospital were used as the training set and the internal test set. In comparison, data from 50 pregnancies from Haidian Maternal and Child Health Hospital were used as the external test set. Feature screening was performed using the random forest (RF), the Least Absolute Shrinkage and Selection Operator (LASSO) and logistic regression (LR). Subsequently, six ML methods, including Stacking, were used to construct models to predict the APO of FGR. MAIN OUTCOME MEASURES: Model's performance was evaluated through indicators such as the area under the receiver operating characteristic curve (AUROC). The Shapley Additive Explanation analysis was used to rank each model feature and explain the final model. RESULTS: Mean ± SD gestational age at diagnosis was 32.3 ± 4.8 weeks in the absent APO group and 27.3 ± 3.7 in the present APO group. Women enrolled in the present APO group had a higher rate of hypertension related to pregnancy (74.8% vs. 18.8%, p < 0.001). Among 17 candidate predictors (including maternal characteristics, maternal comorbidities, obstetric characteristics and ultrasound parameters), the integration of RF, LASSO and LR methodologies identified maternal body mass index, hypertension, gestational age at diagnosis of FGR, estimated foetal weight (EFW) z score, EFW growth velocity and abnormal umbilical artery Doppler (defined as a pulsatility index above the 95th percentile or instances of absent/reversed diastolic flow) as significant predictors. The Stacking model demonstrated a good performance in both the internal test set [AUROC: 0.861, 95% confidence interval (CI), 0.838-0.896] and the external test set [AUROC: 0.906, 95% CI, 0.875-0.947]. The calibration curve showed high agreement between the predicted and observed risks. The Hosmer-Lemeshow test for the internal and external test sets was p = 0.387 and p = 0.825, respectively. CONCLUSIONS: The ML algorithm for APO, which integrates maternal clinical factors and ultrasound parameters, demonstrates good predictive value for APO in FGR at diagnosis. This suggested that ML techniques may be a valid approach for the early detection of high-risk APO in FGR pregnancies.
引用
- Meng X, Wang L, Wu M, et al. Construction of a Prediction Model for Adverse Perinatal Outcomes in Foetal Growth Restriction Based on a Machine Learning Algorithm: A Retrospective Study. BJOG. 2025. PMID: 40406888. doi:10.1111/1471-0528.18226
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。