The recent spike in certified Artificial Intelligence (AI) tools for healthcare has renewed the debate around adoption of this technology. One thread of such debate concerns Explainable AI (XAI) and its promise to render AI devices more transparent and trustworthy. A few voices active in the medical AI space have expressed concerns on the reliability of Explainable AI techniques and especially feature attribution methods, questioning their use and inclusion in guidelines and standards. Despite valid concerns, we argue that existing criticism on the viability of post-hoc local explainability methods throws away the baby with the bathwater by generalizing a problem that is specific to image data. We begin by characterizing the problem as a lack of semantic match between explanations and human understanding. To understand when feature importance can be used reliably, we introduce a distinction between feature importance of low- and high-level features. We argue that for data types where low-level features come endowed with a clear semantics, such as tabular data like Electronic Health Records (EHRs), semantic match can be obtained, and thus feature attribution methods can still be employed in a meaningful and useful way. Finally, we sketch a procedure to test whether semantic match has been achieved.

翻译：近期，经认证的医疗人工智能（AI）工具激增，重新引发了围绕该技术采用的争论。这场争论的一个焦点涉及可解释人工智能（XAI）及其使AI设备更透明、更可信的前景。一些活跃在医疗AI领域的专家对可解释AI技术，特别是特征归因方法的可靠性表示担忧，质疑其在指南和标准中的使用及纳入。尽管这些担忧合理，但我们认为，当前对事后局部可解释性方法的可行性的批评，通过将问题泛化至图像数据专属情境，未免有“因噎废食”之嫌。我们首先将问题定性为解释与人类理解之间缺乏语义匹配。为了厘清何时能可靠使用特征重要性，我们引入了低层次特征与高层次特征的特征重要性区分。我们认为，对于低层次特征具备明确语义的数据类型（如电子健康记录（EHR）等表格数据），语义匹配是可以实现的，因此特征归因方法仍能以有意义且实用的方式加以运用。最后，我们勾勒出一套检验语义匹配是否实现的流程。