没有免费的午餐：医学影像机器学习中数据集偏差的因果视角
No Fair Lunch: A Causal Perspective on Dataset Bias in Machine Learning for Medical Imaging
AI总结：
本文从因果视角分析医学影像机器学习中的数据集偏差，提出三类因果偏差机制，并指出当前缓解方法的局限性，进而提供一个实用的三步框架以支持安全公平的AI预测模型开发。
摘要：
随着机器学习方法在临床决策中日益重要，解决公平性问题变得愈发紧迫。尽管已有大量工作致力于检测和改善算法偏差，但现有方法仍存在不足，可能带来有害后果。我们的因果视角为算法偏差提供了新见解，强调不同来源的数据集偏差可能看似无法区分，却需要截然不同的缓解策略。我们引入了源于患病率、表现和标注差异的三类因果偏差机制。我们的因果分析表明，当前的缓解方法仅处理了狭窄且通常不切实际的场景子集。我们提供了一个实用的三步框架，用于推理医学影像中的公平性问题，以支持安全且公平的AI预测模型的开发。
英文摘要：
As machine learning methods gain prominence within clinical decision-making, addressing fairness concerns becomes increasingly urgent. Despite considerable work dedicated to detecting and ameliorating algorithmic bias, today's methods are deficient with potentially harmful consequences. Our causal perspective sheds new light on algorithmic bias, highlighting how different sources of dataset bias may appear indistinguishable yet require substantially different mitigation strategies. We introduce three families of causal bias mechanisms stemming from disparities in prevalence, presentation, and annotation. Our causal analysis underscores how current mitigation methods tackle only a narrow and often unrealistic subset of scenarios. We provide a practical three-step framework for reasoning about fairness in medical imaging, supporting the development of safe and equitable AI prediction models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
