Hastings Center Report
In Defense of Post Hoc Explanations of Medical AI
Recently, critics have argued that the benefits of post hoc explanations for medical AI’s outputs and operations have been greatly exaggerated. These explanations have been faulted for merely approximating, rather than replicating, the reasoning processes of black box systems. Yet even approximations can improve users’ functional understanding of black box systems, increase the accuracy of clinician-AI teams, and assist clinicians in justifying their AI-informed decisions.
