文献速递生殖医学

机器学习预测人类胚胎整倍体性:寻找最佳模型与预测特征

Machine learning for prediction of euploidy in human embryos: in search of the best-performing model and predictive features.
PubMed 文献 · Fertil Steril · 2022-01-19

本研究为回顾性队列分析,纳入2016年1月至2019年12月治疗的128对不孕夫妇的539枚胚胎(45%整倍体,55%非整倍体),比较5种机器学习模型在9个数据集上的预测性能。随机森林分类器在包含胚胎形态动力学、标准发育及人口学临床特征的数据集C1上准确率最高(71%),AUC为0.75;特征选择并重新训练后准确率提升至72%。

要点

  • 随机森林分类器在数据集C1上准确率71%、AUC 0.75,为所有模型中最高。
  • 特征选择并重新训练后,准确率、召回率和F1分数分别提升至72%、88%和76%。
  • 形态动力学特征的相对预测权重最高。

核心结论

  • 随机森林分类器使用包含胚胎形态动力学、标准胚胎发育及受试者人口学与临床特征的数据集,可以可接受的准确率(>70%)预测整倍体性。

研究设计与样本

  • 回顾性队列分析,在一所大学医院的生殖医学科进行。
  • 纳入2016年1月至2019年12月治疗的128对不孕夫妇,分析539枚胚胎(45%整倍体,55%非整倍体)的人口学与临床数据及胚胎发育和形态动力学数据。
  • 训练并使用了随机森林分类器、scikit-learn梯度提升分类器、支持向量机、多变量逻辑回归和朴素贝叶斯机器学习模型,在9个数据库中进行评估,这些数据库包含26个形态动力学特征(作为绝对时间[A1]、中间时间[A2]或组合时间[A3])单独或加上19个标准发育特征[B1、B2和B3],并加或不加40个人口学与临床特征[C1、C2和C3]。
  • 对表现最佳的模型与数据集组合执行了特征选择和模型重新训练。

主要发现

  • 随机森林分类器模型在数据集C1上训练和使用时准确率最高(71%),AUC最高(0.75)。
  • 在数据集C1上,随机森林分类器模型的精确率、召回率或敏感度、F1分数和AUC分别为66%、86%、75%和0.75。
  • 特征选择和重新训练后,准确率、召回率或敏感度和F1分数分别提升至72%、88%和76%。
  • 形态动力学特征具有最高的相对预测权重。

关键数值与推荐

  • 主要结局指标为每个数据集上机器学习模型的总体准确率、精确率、召回率或敏感度、F1分数(精确率和召回率的加权平均值)以及受试者工作特征曲线下面积(AUC)。
  • 次要结局指标为表现最佳的模型与数据集组合的特征重要性排名。

临床怎么用

  • 原文未据此给出推荐。

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

OBJECTIVE: To assess the best-performing machine learning (ML) model and features to predict euploidy in human embryos. DESIGN: Retrospective cohort analysis. SETTING: Department for reproductive medicine in a university hospital. PATIENT(S): One hundred twenty-eight infertile couples treated between January 2016 and December 2019. Demographic and clinical data and embryonic developmental and morphokinetic data from 539 embryos (45% euploid, 55% aneuploid) were analyzed. INTERVENTION(S): Random forest classifier (RFC), scikit-learn gradient boosting classifier, support vector machine, multivariate logistic regression, and naïve Bayes ML models were trained and used in 9 databases containing either 26 morphokinetic features (as absolute [A1] or interim [A2] times or combined [A3]) alone or plus 19 standard development features [B1, B2, and B3] with and without 40 demographic and clinical characteristics [C1, C2, and C3]. Feature selection and model retraining were executed for the best-performing combination of model and dataset. MAIN OUTCOME MEASURE(S): The main outcome measures were overall accuracy, precision, recall or sensitivity, F1 score (the weighted average of precision and recall), and area under the receiver operating characteristic curve (AUC) of ML models for each dataset. The secondary outcome measure was ranking of feature importance for the best-performing combination of model and dataset. RESULT(S): The RFC model had the highest accuracy (71%) and AUC (0.75) when trained and used on dataset C1. The precision, recall or sensitivity, F1 score, and AUC were 66%, 86%, 75%, and 0.75, respectively. The accuracy, recall or sensitivity, and F1 score increased to 72%, 88%, and 76%, respectively, after feature selection and retraining. Morphokinetic features had the highest relative predictive weight. CONCLUSION(S): The RFC model can predict euploidy with an acceptable accuracy (>70%) using a dataset including embryos' morphokinetics and standard embryonic development and subjects' demographic and clinical features.

来源:Fertil Steril,查看原文。版权归原作者所有。

引用

  1. De Gheselle S, Jacques C, Chambost J, et al. Machine learning for prediction of euploidy in human embryos: in search of the best-performing model and predictive features. Fertil Steril. 2022. PMID: 35058042. doi:10.1016/j.fertnstert.2021.11.029

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。