机器学习整合抗磷脂抗体预测复发性流产患者妊娠结局
LGBM模型预测复发性流产的AUC在妊娠者为0.875、非妊娠者为0.778,随机森林模型预测不良妊娠结局的AUC为0.885,均优于单一指标。模型校正、决策曲线和SHAP分析显示临床实用性良好。
要点
- 机器学习整合标准与非标准抗磷脂抗体可提升复发性流产和不良妊娠结局的预测准确性。
- LGBM模型预测复发性流产的AUC为0.875(妊娠者)和0.778(非妊娠者)。
- 随机森林模型预测不良妊娠结局的AUC为0.885,优于所有单一指标(AUC 0.516-0.647)。
核心结论
- 机器学习模型显著提升了复发性流产和不良妊娠结局的诊断与预测性能。
- LGBM和随机森林模型准确性最佳,可作为辅助诊断和早期预警工具。
研究设计与样本
- 多中心前瞻性研究,招募1321名参与者,最终纳入751例。
- 训练6种机器学习算法,以AUC、校准曲线、决策曲线分析和SHAP评估最优模型。
主要发现
- 以第95百分位为截断值,有复发性流产史的妊娠女性抗磷脂抗体阳性率为2.62%至12.13%。
- 有复发性流产史的非妊娠女性抗磷脂抗体阳性率为4.29%至19.74%。
- LGBM模型预测复发性流产的AUC在妊娠者为0.875、非妊娠者为0.778。
- 随机森林模型预测不良妊娠结局的AUC为0.885,超过所有单一指标(AUC 0.516-0.647)。
- 校准曲线、决策曲线分析和SHAP分析显示模型具有较强临床实用性。
关键数值与推荐
- 抗磷脂抗体阳性截断值采用第95百分位。
- LGBM模型预测复发性流产的AUC:妊娠者0.875,非妊娠者0.778。
- 随机森林模型预测不良妊娠结局的AUC为0.885。
- 单一指标预测的AUC范围为0.516至0.647。
临床怎么用
- 对于有复发性流产史的患者,可考虑使用机器学习模型整合标准与非标准抗磷脂抗体进行风险评估。
- LGBM和随机森林模型可作为辅助诊断和早期预警工具,帮助识别不良妊娠结局高风险者。
局限性
- 需要更大规模的外部队列进一步验证模型。
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
OBJECTIVES: Antiphospholipid antibodies (aPLs) are closely associated with recurrent spontaneous abortion (RSA) and adverse pregnancy outcomes (POs). Non-criteria aPLs may aid in diagnosing seronegative aPL-related RSA, but their limited performance often leads to missed or delayed diagnosis. This study aimed to improve diagnostic and predictive accuracy by integrating criteria and non-criteria aPLs with machine learning (ML) algorithm. METHODS: In this multicenter prospective study, 1,321 participants were recruited and 751 included. Fifteen aPLs were measured using chemiluminescence immunoassay. Six ML algorithms were trained, and the optimal model was evaluated using the area under the curve (AUC), calibration curves, decision curve analysis (DCA), and Shapley additive explanations (SHAP). RESULTS: Using the 95th percentile as the cut-off, aPL positivity ranged from 2.62 to 12.13 % in pregnant woman with a history of RSA and 4.29-19.74 % in non-pregnant woman with a history of RSA. The light gradient boosting machine (LGBM) model achieved AUCs of 0.875 (pregnant) and 0.778 (non-pregnant) for RSA prediction, while the random forest (RF) model achieved an AUC of 0.885 for PO prediction - surpassing all single indicators (AUC 0.516-0.647). Calibration, DCA, and SHAP analyses demonstrated strong clinical utility. CONCLUSIONS: The ML models substantially improved diagnostic and predictive performance for RSA and PO. The LGBM and RF models showed the best accuracy and may serve as auxiliary diagnostic and early warning tools. Larger external cohorts are needed for further validation.
引用
- Jiang X, Chai J, Li X, et al. Machine learning-based integration of antiphospholipid antibodies for predicting pregnancy outcomes in patients with recurrent spontaneous abortion: a multicenter prospective study. Clin Chem Lab Med. 2026. PMID: 41764780. doi:10.1515/cclm-2026-0088
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。