文献速递生殖医学

展望未来:基于机器学习的卵母细胞冷冻保存后返还率预测模型

Looking into the future: a machine learning powered prediction model for oocyte return rates after cryopreservation.
PubMed 文献 · Reprod Biomed Online · 2024-08-29

研究利用美国辅助生殖技术学会报告的所有美国生育诊所数据,采用多种机器学习算法构建预测模型,分析2014—2020年77,631个卵母细胞冷冻周期,评估患者使用冻存卵母细胞的可能性。集成模型在测试集上平衡准确度0.83、敏感度0.76、特异度0.91,受试者工作特征曲线下面积0.90。

要点

  • 集成模型预测卵母细胞返还的平衡准确度0.83,敏感度0.76,特异度0.91。
  • 影响返还可能性的关键因素包括患者年龄、有无伴侣、种族或民族、诊所地理区域和冷冻指征。
  • 模型可用于患者咨询,帮助识别更可能使用冻存卵母细胞的患者。

核心结论

  • 该模型表现出显著的预测准确性,是卵母细胞冷冻保存患者咨询的有价值工具。
  • 模型有助于识别更可能使用冻存卵母细胞的患者,增强医疗决策和配子储存项目的效率。
  • 模型可应用于自费和保险资助的周期。

研究设计与样本

  • 研究使用惩罚回归、随机森林、梯度提升机、线性判别分析和自助聚合决策树等多种学习算法,数据分为训练集和测试集。
  • 分析数据来自向美国辅助生殖技术学会报告的所有美国生育诊所,共纳入2014—2020年77,631个卵母细胞冷冻周期。
  • 分析变量包括患者人口学特征、医学和生育诊断、伴侣信息及地理位置。

主要发现

  • 患者平均年龄34.5岁。
  • 治疗指征分布为:计划性35.6%、性别相关0.1%、医学指征15.5%、肿瘤相关5.7%、未知42.3%。
  • 不孕诊断较少见:不明原因不孕1.8%、年龄相关不孕3.2%、卵巢储备减退9.9%、子宫内膜异位症1.6%。
  • 结合自助聚合分类与回归树、随机梯度提升和线性判别分析的集成模型在测试集上预测准确性最高,平衡准确度0.83、敏感度0.76、特异度0.91,受试者工作特征曲线下面积0.90,精确率—召回曲线下面积0.57。
  • 影响返还可能性的关键因素包括患者年龄、有无伴侣、种族或民族、诊所地理区域和卵母细胞冷冻指征。

临床怎么用

  • 作者认为该模型是卵母细胞冷冻保存患者咨询的有价值工具,可帮助识别更可能使用冻存卵母细胞的患者。

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

RESEARCH QUESTION: Could a predictive model, using data from all US fertility clinics reporting to the Society for Assisted Reproductive Technology, estimate the likelihood of patients using their stored oocytes? DESIGN: Multiple learner algorithms, including penalized regressions, random forests, gradient boosting machine, linear discriminant analysis and bootstrap aggregating decision trees were used. Data were split into training and test datasets. Patient demographics, medical and fertility diagnoses, partner information and geographic locations were analysed. RESULTS: A total of 77,631 oocyte-cryopreservation cycles (2014-2020) were analysed. Patient age averaged 34.5 years. Treatment indications varied: planned (35.6%), gender-related (0.1%), medically indicated (15.5%), oncologic (5.7%) and unknown (42.3%). Infertility diagnoses were less common: unexplained infertility (1.8%), age-related infertility (3.2%), diminished ovarian reserve (9.9%) and endometriosis (1.6%). An ensemble model combining bootstrap aggregation classification and regression trees, stochastic gradient boosting and linear discriminant analysis yielded the highest predictive accuracy on test set (balanced accuracy: 0.83, sensitivity: 0.76, specificity: 0.91), with a receiver operating characteristic curve of 0.90 and precision-recall curve and area under the curve of 0.57. Key factors influencing the likelihood of returning for oocyte use included patient age, presence of a partner, race or ethnicity, the clinic's geographic region and oocyte cryopreservation indication. CONCLUSIONS: This model demonstrated significant predictive accuracy, and is a valuable tool for patient counselling on oocyte cryopreservation. It helps to identify patients more likely to use stored oocytes, enhancing healthcare decision-making and the efficiency of gamete storage programmes. The model can be applied to self-financed and insurance-funded cycles.

来源:Reprod Biomed Online,查看原文。版权归原作者所有。

引用

  1. Fouks Y, Bortoletto P, Chang J, et al. Looking into the future: a machine learning powered prediction model for oocyte return rates after cryopreservation. Reprod Biomed Online. 2024. PMID: 39642702. doi:10.1016/j.rbmo.2024.104432

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。