人工智能胚胎选择简史:从黑箱到玻璃箱
本文综述了人工智能在体外受精胚胎选择中的应用发展。文章指出机器学习可减少操作者主观性并节省时间,但深度学习黑箱模型缺乏可解释性且缺乏随机对照试验验证,近期证据显示黑箱模型表现不如可解释的传统机器学习模型。作者从胚胎学角度提出传统与人工智能驱动系统的新分类体系。
要点
- 机器学习可减少胚胎选择中操作者相关主观性并节省劳动时间。
- 深度学习黑箱模型缺乏可解释性,目前缺乏随机对照试验确认其有效性。
- 近期证据显示黑箱模型在胚胎选择中表现不如可解释的传统机器学习模型。
核心结论
- 玻璃箱人工智能如可解释机器学习因其伦理优势和技术可行性正被广泛推广。
- 作者从胚胎学角度提出传统与人工智能驱动系统的新分类体系。
研究设计与样本
- 本文为综述,检索范围涉及体外受精中人工智能胚胎选择的相关文献。
主要发现
- 机器学习有潜力减少胚胎选择中操作者相关主观性并节省劳动时间。
- 深度学习黑箱模型缺乏可解释性引发日益增长的担忧。
- 目前缺乏随机对照试验确认黑箱模型的有效性。
- 近期证据显示黑箱模型在胚胎选择中表现不如更可解释的传统机器学习模型。
关键数值与推荐
- 作者提出新的分类体系,从胚胎学角度定义不同基于形态学的选择方法,强调主观性、可解释性和解释性。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文指出目前缺乏随机对照试验确认黑箱模型的有效性。
- 原文指出黑箱模型缺乏可解释性。
- 原文指出近期证据显示黑箱模型表现不如传统机器学习模型。
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
With the exponential growth of computing power and accumulation of embryo image data in recent years, artificial intelligence (AI) is starting to be utilized in embryo selection in IVF. Amongst different AI technologies, machine learning (ML) has the potential to reduce operator-related subjectivity in embryo selection while saving labor time on this task. However, as modern deep learning (DL) techniques, a subcategory of ML, are increasingly used, its integrated black-box attracts growing concern owing to the well-recognized issues regarding lack of interpretability. Currently, there is a lack of randomized controlled trials to confirm the effectiveness of such black-box models. Recently, emerging evidence has shown underperformance of black-box models compared to the more interpretable traditional ML models in embryo selection. Meanwhile, glass-box AI, such as interpretable ML, is being increasingly promoted across a wide range of fields and is supported by its ethical advantages and technical feasibility. In this review, we propose a novel classification system for traditional and AI-driven systems from an embryology standpoint, defining different morphology-based selection approaches with an emphasis on subjectivity, explainability, and interpretability.
引用
- Lee T, Natalwala J, Chapple V, et al. A brief history of artificial intelligence embryo selection: from black-box to glass-box. Hum Reprod. 2024. PMID: 38061074. doi:10.1093/humrep/dead254
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。