Would You Eat A Centipede to Prevent a Heart Attack?

As some of you may know, I do a fair amount of clinical research developing and evaluating artificial intelligence models — particularly machine learning algorithms that predict certain outcomes. And there’s this thorny issue that comes up as algorithms have gotten more complicated — it’s called “explainability”. The problem is that AI can be a black box. Even if you have a model that is very accurate at predicting death, clinicians don’t trust it unless you can explain how it makes its predictions — how it works. “It just works” is not good enough to build trust. <a href="https://fperrywilson.medium.com/would-you-eat-a-centipede-to-prevent-a-heart-attack-38746e3a2d89">Read More</a>