Complex machine learning systems are increasingly used in critical domains such as medicine, where their decisions may have a substantial impact on human lives. Therefore, it is considered to be of utmost importance that these decisions can be made understandable to humans. In recent years, the community of 'explainable artificial intelligence' (XAI) has created a vast body of methods to bridge a perceived gap between 'complexity' and 'interpretability'.However, a concrete problem to be solved b…