机器学习和深度学习用于子宫内膜异位症诊断：系统综述与荟萃分析。
完整摘要 · 中文译文
目的：评估机器学习（ML）和深度学习（DL）模型对子宫内膜异位症的诊断准确性。 方法：按照PRISMA指南（PROSPERO：CRD420251231469）进行系统综述和荟萃分析。数据库检索截至2025年11月24日。共纳入22项符合条件的研究。采用QUADAS-2评估偏倚风险。在Stata 18.0中进行合并分析。 结果：合并敏感度为0.90（95% CI 0.86-0.93），特异度为0.75（95% CI 0.64-0.84），SROC-AUC为0.92（95% CI 0.89-0.94）。阳性预测将疾病概率从10%提高至29%，而阴性预测将其降低至1%。多中心设计和DL与较低的敏感度相关。结果稳健。 结论：ML/DL模型表现出较高的诊断性能，有望用于无创辅助诊断。需要大型多中心前瞻性研究和多模态模型以实现临床转化。系统综述注册：https://www.crd.york.ac.uk/PROSPERO/view/CRD420251231469，标识符CRD420251231469。
完整摘要 · 英文原文
OBJECTIVE: To assess the diagnostic accuracy of machine learning (ML) and deep learning (DL) models for endometriosis. METHODS: A systematic review and meta-analysis were conducted in accordance with PRISMA guidelines (PROSPERO: CRD420251231469). Databases were searched through November 24, 2025. Twenty-two eligible studies were included. Risk of bias was assessed using QUADAS-2. Pooled analysis was conducted in Stata 18.0. RESULTS: Pooled sensitivity was 0.90 (95% CI 0.86-0.93), specificity 0.75 (95% CI 0.64-0.84), and SROC-AUC 0.92 (95% CI 0.89-0.94). A positive prediction increased disease probability from 10% to 29%, whereas a negative prediction reduced it to 1%. Multicenter design and DL were associated with lower sensitivity. Results were robust. CONCLUSIONS: ML/DL models demonstrate high diagnostic performance and are promising for non-invasive auxiliary diagnosis. Large multicenter prospective studies and multimodal models are needed to enable clinical translation.Systematic Review Registration: https://www.crd.york.ac.uk/PROSPERO/view/CRD420251231469, identifier CRD420251231469.