文献速递生殖医学

胚胎学「金羊毛」再次遥不可及:近期一项使用人工智能的随机对照试验再次表明囊胚形态学仍是难以超越的标准

The 'golden fleece of embryology' eludes us once again: a recent RCT using artificial intelligence reveals again that blastocyst morphology remains the standard to beat.
PubMed 文献 · Hum Reprod · 2025-01-01

囊胚形态学评分常规用于胚胎选择且结局良好。人工智能(AI)的回顾性研究曾显示惊人预测能力,但近期一项随机对照试验(RCT)显示,深度学习算法「iDAScore version 1」在临床妊娠率上未能证明非劣效于标准形态学。良好囊胚形态学再次被证明是预测活产的高标准。

要点

  • 囊胚形态学评分常规用于胚胎选择且结局良好。
  • 近期RCT中,深度学习算法「iDAScore version 1」在临床妊娠率上未能证明非劣效于标准形态学。
  • 良好囊胚形态学再次被证明是预测活产的高标准,不应放弃开发可识别形态学未捕捉的存活胚胎额外特征的方法。

核心结论

  • 近期一项RCT未能证明深度学习算法「iDAScore version 1」在临床妊娠率上非劣效于标准形态学,良好囊胚形态学再次被证明是预测活产的高标准。

研究设计与样本

  • 原文为针对近期一项随机对照试验(RCT)的评论,该RCT使用深度学习算法「iDAScore version 1」与标准形态学比较临床妊娠率。

主要发现

  • 近期RCT未能证明「iDAScore version 1」在临床妊娠率上非劣效于标准形态学。
  • 许多回顾性研究显示AI具有惊人的预测能力。
  • 良好囊胚形态学再次被证明是预测活产的高标准。

临床怎么用

  • 囊胚形态学评分常规用于胚胎选择且结局良好。
  • 作者认为不应放弃开发进一步方法,以识别形态学未捕捉的存活胚胎额外特征。

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

Grading of blastocyst morphology is used routinely for embryo selection with good outcomes. A lot of effort has been placed in IVF to search for the prize of selecting the most viable embryo to transfer ('the golden fleece of embryology'). To improve on morphology alone, artificial intelligence (AI) has also become a tool of interest, with many retrospective studies being published with impressive prediction capabilities. Subsequently, AI has again raised expectations that this 'golden fleece of embryology' was once again within reach. A recent RCT however was not able to demonstrate non-inferiority using a deep learning algorithm 'iDAScore version 1' for clinical pregnancy rate when compared to standard morphology. Good blastocyst morphology has again proven itself as a high bar in predicting live birth. We should however not give up on the development of further approaches which may allow us to identify extra features of viable embryos that are not captured by morphology.

来源:Hum Reprod,查看原文。版权归原作者所有。

引用

  1. Sakkas D. The 'golden fleece of embryology' eludes us once again: a recent RCT using artificial intelligence reveals again that blastocyst morphology remains the standard to beat. Hum Reprod. 2025. PMID: 39602554. doi:10.1093/humrep/deae263

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。