| HIMSS

Many in healthcare remain wary of AI because of longstanding concerns about “black box” models. “Black box” is shorthand for models that are sufficiently complex that they are not straightforwardly interpretable to humans. Lack of interpretability in AI can undermine trust, especially in healthcare, in which so many decisions are— literally—life and death. There has been a recent explosion of research in the field of explainable AI aimed at addressing these concerns. The promise of explainable machine learning is considerable, but it is important for practitioners who may encounter these techniques in clinical decision-support tools or novel research papers to have critical understanding of both their strengths and their limitations. This session reviews key concepts and techniques in the field of explainable machine learning as they apply to healthcare. Key concepts reviewed include interpretability vs explainability and global vs local explanations. Techniques demonstrated include permutation importance, surrogate decision trees, local interpretable model-agnostic explanations, and partial dependence plots. We will discuss several limitations with explainability techniques, focusing on they can omit important information about how black-box models work. We conclude with guidelines about when it is appropriate to use black- box models with explanations rather than interpretable techniques.

Opening the Black Box: Promise and Limitations of Explainable AI

Speakers:

Jeremy Petch, PhD