Multiple stakeholders drive diverse interpretability requirements for machine learning in healthcare
Multiple stakeholders drive diverse interpretability requirements for machine learning in healthcare
复制标题
多个利益相关者推动医疗保健中机器学习的各种可解释性要求
DOI：
10.1038/s42256-023-00698-2
复制
发表时间：
2023-08
影响因子：
23.8
通讯作者：
F. Imrie;Robert I. Davis;M. Van Der Schaar
中科院分区：
文献类型：
--
作者：
F. Imrie;Robert I. Davis;M. Van Der Schaar
机器学习的应用在医学和医疗保健领域越来越普遍，从而实现了更准确的预测模型。然而，这通常是以可解释性为代价的，限制了机器学习方法的临床影响。为了实现机器学习在医疗保健领域的潜力，从多个利益相关者和各种角度理解这些模型至关重要，这需要不同类型的解释。在这个视角中，我们探索了五种根本不同类型的事后机器学习可解释性。我们强调了它们提供的不同类型的信息，并描述了每种信息何时有用。我们研究了医疗保健领域的各个利益相关者，深入研究了他们的具体目标，要求和目标。我们讨论了当前的可解释性概念如何帮助满足这些要求，以及每个利益相关者需要什么来使机器学习模型具有临床影响力。最后，为了便于采用，我们发布了一个开源的可解释性库，其中包含不同类型的可解释性的实现，包括用于可视化和探索解释的工具。
Applications of machine learning are becoming increasingly common in medicine and healthcare, enabling more accurate predictive models. However, this often comes at the cost of interpretability, limiting the clinical impact of machine learning methods. To realize the potential of machine learning in healthcare, it is critical to understand such models from the perspective of multiple stakeholders and various angles, necessitating different types of explanation. In this Perspective, we explore five fundamentally different types of post-hoc machine learning interpretability. We highlight the different types of information that they provide, and describe when each can be useful. We examine the various stakeholders in healthcare, delving into their specific objectives, requirements and goals. We discuss how current notions of interpretability can help meet these and what is required for each stakeholder to make machine learning models clinically impactful. Finally, to facilitate adoption, we release an open-source interpretability library containing implementations of the different types of interpretability, including tools for visualizing and exploring the explanations.