Huo Wen-Jie, Peng Fei, Quan Song, Wang Xiao-Cong
Department of Obstetrics and Gynecology, Nanfang Hospital, Southern Medical University, Guangzhou, China.
Department of Psychology, School of Public Health, Southern Medical University, Guangzhou, China.
Sci Rep. 2025 Jul 2;15(1):22631. doi: 10.1038/s41598-025-06998-4.
Predicting blastocyst formation poses significant challenges in reproductive medicine and critically influences clinical decision-making regarding extended embryo culture. While previous research has primarily focused on determining whether an IVF cycle can produce at least one blastocyst, less attention has been given to quantifying blastocyst yields. This study aims to develop and validate such a quantitative predictive tool for IVF cycles. We employed three machine learning models-SVM, LightGBM, and XGBoost-which demonstrated comparable performance and outperformed traditional linear regression models (R: 0.673-0.676 vs. 0.587, Mean absolute error: 0.793-0.809 vs. 0.943). Ultimately, LightGBM emerged as the optimal model, due to utilizing fewer features (8 vs. 10-11 in SVM/XGBoost) and offering superior interpretability. We then stratified predictions and actual yields into three categories (0, 1-2, and ≥ 3 blastocysts) to evaluate the model's discriminative performance. In this multi-classification task, LightGBM demonstrated robust accuracy (0.675-0.71) with fair-to-moderate agreement (kappa coefficients: 0.365-0.5) across both the overall cohort and poor-prognosis subgroups. Feature importance analysis identified three critical predictors: the number of extended culture embryos, the mean cell number on Day 3, and the proportion of 8-cell embryos. By leveraging the potential of machine learning, this research provides clinicians with valuable insights for making individualized decisions regarding extended embryo culture.
预测囊胚形成在生殖医学中面临重大挑战，并且对关于延长胚胎培养的临床决策有着至关重要的影响。虽然先前的研究主要集中在确定体外受精（IVF）周期是否能产生至少一个囊胚，但对囊胚产量的量化关注较少。本研究旨在开发并验证一种用于IVF周期的定量预测工具。我们采用了三种机器学习模型——支持向量机（SVM）、轻量级梯度提升机（LightGBM）和极端梯度提升（XGBoost）——它们表现出可比的性能，并且优于传统线性回归模型（相关系数：0.673 - 0.676对比0.587，平均绝对误差：0.793 - 0.809对比0.943）。最终，LightGBM成为最优模型，因为它使用的特征较少（8个，而SVM/XGBoost为10 - 11个）且具有更好的可解释性。然后，我们将预测结果和实际产量分为三类（0个、1 - 2个和≥3个囊胚），以评估模型的判别性能。在这个多分类任务中，LightGBM在整个队列和预后不良亚组中都表现出稳健的准确性（0.675 - 0.71），一致性从中等到良好（卡帕系数：0.365 - 0.5）。特征重要性分析确定了三个关键预测因素：延长培养胚胎的数量、第3天的平均细胞数以及8细胞胚胎的比例。通过利用机器学习的潜力，本研究为临床医生在做出关于延长胚胎培养的个性化决策时提供了有价值的见解。
