文献速递妇科

利用人工智能:机器学习算法构建术前子宫内膜异位症预测模型

Utilizing Artificial Intelligence: Machine Learning Algorithms to Develop a Preoperative Endometriosis Prediction Model.
PubMed 文献 · J Minim Invasive Gynecol · 2025-05-19

回顾性病例对照研究纳入2011至2022年788例因卵巢、盆腔脏器或腹膜表面病变行腹腔镜或机器人辅助切除术的女性,分析209项临床特征预测子宫内膜异位症,极端梯度提升模型准确率83%、敏感度96%、AUC 0.81,关键预测因子包括呕吐、绞痛、规律月经、痛经严重度和直肠阴道检查后穹窿触痛,结论认为机器学习有术前预测潜力,但需在多样化人群中进一步验证。

要点

  • 极端梯度提升模型预测子宫内膜异位症准确率83%、敏感度96%、AUC 0.81。
  • 关键预测因子包括呕吐、绞痛、规律月经、痛经严重度及直肠阴道检查后穹窿触痛。
  • 作者认为机器学习有术前预测潜力,但需在多样化人群中进一步验证以开发广泛适用的工具。

核心结论

  • 机器学习算法有潜力利用临床特征在术前预测子宫内膜异位症。
  • 识别的预测因子如后穹窿触痛、绞痛和规律月经可帮助初级保健提供者早期识别和转诊。
  • 需在多样化人群中进一步验证以开发广泛适用的临床预测工具。

研究设计与样本

  • 回顾性病例对照研究,2011年至2022年。
  • 地点为专注于盆腔疼痛和微创妇科手术的三级转诊中心。
  • 参与者为2011年至2022年由单一外科医生行腹腔镜或机器人辅助卵巢、盆腔脏器或腹膜表面病变切除术的18至55岁女性。
  • 排除需急诊手术、缺乏送病理分析的手术标本或缺乏记录的术前盆腔检查的女性。
  • 分析209项临床特征作为子宫内膜异位症的预测因子,主要结局为模型预测性能。

主要发现

  • 788名参与者中,654名(83%)有病理证实的子宫内膜异位症。
  • 极端梯度提升模型准确率83%、敏感度96%、受试者工作特征曲线下面积0.81。
  • Shapley加性解释分析识别的关键预测因子包括呕吐(141例[21.56%] vs 10例[7.46%],p < .001)、绞痛(325例[49.69%] vs 38例[28.36%],p < .001)、规律月经(429例[65.60%] vs 60例[44.78%],p < .001)、痛经严重度(0-3 Likert量表)(3 [1, 2] vs 3 [1, 2],p = .02)和直肠阴道检查后穹窿触痛(126例[19.27%] vs 7例[5.22%],p < .001)。

关键数值与推荐

  • 模型性能评估指标包括准确率、敏感度、特异度和受试者工作特征曲线下面积。
  • 特征重要性使用Shapley加性解释值评估。

临床怎么用

  • 作者认为识别的预测因子如后穹窿触痛、绞痛和规律月经可帮助初级保健提供者早期识别和转诊。
  • 作者结论指出机器学习有术前预测潜力,但需在多样化人群中进一步验证以开发广泛适用的临床预测工具。

局限性

  • 需在多样化人群中进一步验证以开发广泛适用的临床预测工具。

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 evaluate the predictive value of clinical features in the diagnosis of endometriosis by utilizing machine learning algorithms (MLAs), aiming to develop an accurate, explainable prediction model. DESIGN: Retrospective case-control study from 2011 to 2022. SETTING: Tertiary referral center specializing in pelvic pain and minimally invasive gynecologic surgery. PARTICIPANTS: All women aged 18 to 55 undergoing laparoscopic or robot-assisted excision of lesions of the ovary, pelvic viscera, or peritoneal surface by a single surgeon from 2011 to 2022. Exclusion criteria included women who required emergent surgery, as well as those lacking surgical specimens submitted for pathological analysis or a documented preoperative pelvic examination. INTERVENTIONS: A total of 209 clinical features, including demographics, presenting symptoms, gynecologic/obstetric history, and physical exam findings, were analyzed as predictors of endometriosis. The primary outcome was model performance in predicting endometriosis, evaluated using accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve. Feature importance was assessed using Shapley Additive Explanation values. RESULTS: Among 788 participants, 654 (83%) had pathology-confirmed endometriosis. The MLA, extreme gradient boosting, achieved an accuracy of 83%, sensitivity of 96%, and area under the receiver operating characteristic curve of 0.81. Shapley Additive Explanation analysis identified key predictors, including emesis (141 [21.56%] vs 10 [7.46%], p < .001), crampy pain (325 [49.69%] vs 38 [28.36%], p < .001), regular periods (429 [65.60%] vs 60 [44.78%], p < .001), severity of dysmenorrhea (0-3 Likert scale) (3 [1, 2] vs 3 [1, 2] p = .02), and retrocervical tenderness on rectovaginal exam (126 [19.27%] vs 7 [5.22%], p < .001). CONCLUSION: This study demonstrates that MLAs have potential to predict endometriosis preoperatively utilizing clinical features. Identified predictors, such as retrocervical tenderness, crampy pain, and regular periods, can aid primary care providers in early recognition and referral. Further validation in diverse populations is necessary to develop a widely applicable clinical prediction tool.

来源:J Minim Invasive Gynecol,查看原文。版权归原作者所有。

引用

  1. Snyder DL, Sidhom S, Chatham CE, et al. Utilizing Artificial Intelligence: Machine Learning Algorithms to Develop a Preoperative Endometriosis Prediction Model. J Minim Invasive Gynecol. 2025. PMID: 40398559. doi:10.1016/j.jmig.2025.05.003

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。