基于8147枚胚胎的形态动力学元数据集比较12种机器学习模型预测倍性的研究
该多中心队列研究纳入英国9家IVF诊所2012至2020年1725例患者的8147枚活检囊胚,比较混合效应逻辑回归与随机森林、极端梯度提升、深度学习等12种模型预测倍性的表现。结果显示混合效应逻辑回归预测效果优于所有机器学习方法,最佳模型基于22个预测变量(AUC 0.71,95%CI 0.67-0.73)。
要点
- 混合效应逻辑回归预测倍性优于随机森林、极端梯度提升和深度学习模型。
- 最佳模型AUC 0.71(95%CI 0.67-0.73),随机森林、极端梯度提升、深度学习AUC分别为0.68、0.63、0.63。
- 仅用形态动力学变量预测倍性AUC为0.61,仅用胚胎评级无法区分非整倍体胚胎(AUC=0.52)。
核心结论
- 在8147枚胚胎数据集上,混合效应逻辑回归预测倍性的表现优于所有机器学习方法。
研究设计与样本
- 多中心队列研究,数据来自英国9家IVF诊所2012至2020年治疗的1725例患者的8147枚活检囊胚。
- 最终验证数据集包含3004枚整倍体胚胎和5023枚非整倍体胚胎。
- 使用混合效应多变量逻辑回归、随机森林分类器、极端梯度提升和深度学习共构建12种模型。
- 每种算法构建两个模型:第一个模型使用8027枚胚胎(数据集1)和22个协变量,第二个模型使用2373枚胚胎(数据集2)和26个协变量。
- 通过将目标结局从整倍体切换为非整倍体,为每种算法创建四个最终模型(数据集1),采用内部-外部交叉验证和外部验证。
主要发现
- 所有形态动力学变量在非整倍体胚胎中均显著延迟。
- 囊胚扩张程度越高(P < 0.001)和滋养外胚层评级越好(P < 0.01),整倍体可能性显著增加。
- 单变量分析显示,桑葚胚或卵裂期碎片、桑葚胚评级、受精方法、精子浓度或前向运动与倍性状态无关联。
- 按女性年龄分层后,男性年龄与整倍体胚胎百分比不相关;两细胞或四细胞期多核化与倍性状态无关联。
- 表现最佳的模型是基于较大数据集和22个预测变量的逻辑回归(预测整倍体F1分数0.59;预测非整倍体F1分数0.77;AUC 0.71,95%CI 0.67-0.73)。
临床怎么用
- 该模型可能有助于决策,特别是在不允许进行胚胎植入前非整倍体遗传学检测或需要优先安排胚胎活检时。
局限性
- 模型尚未在前瞻性研究设计中进行验证,也尚未用于确定其是否改善临床结局。
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
STUDY QUESTION: Are machine learning methods superior to traditional statistics in predicting blastocyst ploidy status using morphokinetic and clinical biodata? SUMMARY ANSWER: Mixed effects logistic regression performed better than all machine learning methods for ploidy prediction using our dataset of 8147 embryos. WHAT IS KNOWN ALREADY: Morphokinetic timings have been demonstrated to be delayed in aneuploid embryos. Machine learning and statistical models are increasingly being built, however, until now they have been limited by data insufficiency. STUDY DESIGN, SIZE, DURATION: This is a multicentre cohort study. Data were obtained from 8147 biopsied blastocysts from 1725 patients, treated from 2012 to 2020. PARTICIPANTS/MATERIALS, SETTING, METHODS: All embryos were cultured in a time-lapse system at nine IVF clinics in the UK. A total of 3004 euploid embryos and 5023 aneuploid embryos were included in the final verified dataset. We developed a total of 12 models using four different approaches: mixed effects multivariable logistic regression, random forest classifiers, extreme gradient boosting, and deep learning. For each of the four algorithms, two models were created, the first consisting of 22 covariates using 8027 embryos (Dataset 1) and the second, a dataset of 2373 embryos and 26 covariates (Dataset 2). Four final models were created by switching the target outcome from euploid to aneuploid for each algorithm (Dataset 1). Models were validated using internal-external cross-validation and external validation. MAIN RESULTS AND THE ROLE OF CHANCE: All morphokinetic variables were significantly delayed in aneuploid embryos. The likelihood of euploidy was significantly increased the more expanded the blastocyst (P < 0.001) and the better the trophectoderm grade (P < 0.01). Univariable analysis showed no association with ploidy status for morula or cleavage stage fragmentation, morula grade, fertilization method, sperm concentration, or progressive motility. Male age did not correlate with the percentage of euploid embryos when stratified for female age. Multinucleation at the two-cell or four-cell stage was not associated with ploidy status. The best-performing model was logistic regression built using the larger dataset with 22 predictors (F1 score 0.59 for predicting euploidy; F1 score 0.77 for predicting aneuploidy; AUC 0.71; 95% CI 0.67-0.73). The best-performing models using the algorithms from random forest, extreme gradient boosting, and deep learning achieved an AUC of 0.68, 0.63, and 0.63, respectively. When using only morphokinetic predictors the AUC was 0.61 for predicting ploidy status, whereas a model incorporating only embryo grading was unable to discriminate aneuploid embryos (AUC = 0.52). The ploidy prediction model's performance improved with increasing age of the egg provider. LIMITATIONS, REASONS FOR CAUTION: The models have not been validated in a prospective study design or yet been used to determine whether they improve clinical outcomes. WIDER IMPLICATIONS OF THE FINDINGS: This model may aid decision-making, particularly where pre-implantation genetic testing for aneuploidy is not permitted or for prioritizing embryos for biopsy. STUDY FUNDING/COMPETING INTEREST(S): No specific funding was sought for this study; university funds supported the first author. A.Ca. is a minor shareholder of participating centres. TRIAL REGISTRATION NUMBER: N/A.
引用
- Bamford T, Easter C, Montgomery S, et al. A comparison of 12 machine learning models developed to predict ploidy, using a morphokinetic meta-dataset of 8147 embryos. Hum Reprod. 2023. PMID: 36825452. doi:10.1093/humrep/dead034
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。