Paydar Khadijeh, Sheikhtaheri Abbas
Independent Researcher, Tabriz, Iran.
Health Management and Economics Research Center, Health Management Research Institute, Iran University of Medical Sciences, Tehran, Iran.
Heliyon. 2025 Feb 14;11(4):e42679. doi: 10.1016/j.heliyon.2025.e42679. eCollection 2025 Feb 28.
Fetal loss is possible during pregnancy in women with systemic lupus erythematosus (SLE). Predicting pregnancy outcomes for women with SLE can be an effective aid in providing consultation and treatment services. Therefore, this study aimed to develop a machine-learning model that could predict pregnancy outcomes before pregnancy in women with SLE.
The data of all pregnant women referred to the rheumatology center of Shariati Hospital and a specialized rheumatology clinic since 1980 were retrospectively collected from their medical records. Data collection was done by gathering 26 variables that affect pregnancy outcomes. Then, we used standard algorithms to select important features that affect pregnancy outcomes before pregnancy (11 different feature sets). A variety of machine learning algorithms were trained using both imbalanced and balanced datasets in Clementine and Weka software. Finally, the model with a higher area under the receiver operating characteristic curve (AUC) and F-score was selected to predict pregnancy outcomes.
Out of 149 pregnancies, 46 pregnancies resulted in spontaneous abortion, while 103 pregnancies resulted in live birth. Compared with other models, the Chi-square automatic interaction detection (CHAID) decision tree was selected as the best-performing model with higher accuracy (93.5 %), specificity (92.9 %), sensitivity (93.8 %), precision (97 %), F-score (0.95), and AUC (0.96).
By using the CHAID decision tree to predict the outcome of pregnancy in women with SLE and extracted rules, it is possible to use appropriate methods that prevent spontaneous abortion and also provide timely consultation to women with SLE for making decisions to become pregnant.
系统性红斑狼疮（SLE）女性在孕期可能发生胎儿丢失。预测SLE女性的妊娠结局有助于提供有效的咨询和治疗服务。因此，本研究旨在开发一种机器学习模型，用于预测SLE女性妊娠前的妊娠结局。
回顾性收集自1980年以来转诊至沙里亚蒂医院风湿病中心和一家专门的风湿病诊所的所有孕妇的病历数据。通过收集26个影响妊娠结局的变量来完成数据收集。然后，我们使用标准算法选择妊娠前影响妊娠结局的重要特征（11种不同的特征集）。在Clementine和Weka软件中，使用不平衡和平衡数据集对多种机器学习算法进行训练。最后，选择具有较高受试者工作特征曲线下面积（AUC）和F分数的模型来预测妊娠结局。
在149次妊娠中，46次妊娠导致自然流产，103次妊娠导致活产。与其他模型相比，卡方自动交互检测（CHAID）决策树被选为性能最佳的模型，其准确率更高（93.5%）、特异性（92.9%）、敏感性（93.8%）、精确率（97%）、F分数（0.95）和AUC（0.96）。
通过使用CHAID决策树预测SLE女性的妊娠结局并提取规则，可以采用适当的方法预防自然流产，并及时为SLE女性提供咨询，以便她们做出妊娠决策。
