Would You Eat A Centipede to Prevent a Heart Attack?

A randomized trial shows the efficacy of Tongxinluo, a traditional Chinese medicine. But you may not want to know what is in it.

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.

It’s easier to build trust when you’re talking about a medication instead of a computer program. A new blood pressure drug comes out, it lowers blood pressure, and, importantly, we know why it lowers blood pressure — every drug has a mechanism of action and — for most of the drugs in our arsenal — we know what that mechanism is.