toad007

> [...] would you hesitate to prescribe it because nobody understood how it worked? I have yet to hear "yes, I would hesitate", most people say "it would be cruel to deny a person a treatment that worked".

I feel like the way you frame the question makes answering it very easy but oversimplifies the reality.

In a situation where an AI suggests a treatment to you without explanation and it appears to work, probably you can't even determine that the improved outcome is due to the drug or due to randomness (yes there are really rare cases where people recovered from stage 4 cancer). Especially if it's a personalized drug.

If in this hypothetical world "it works on the patients I've tried it on" is good enough to try the drug, and you're willing to potentially cause harm if it doesn't work, then what's the line between science and pseudoscience/quack medicine? Every treatment surely "appears to work" in at least some cases. So wouldn't it be cruel to deny the patient a try at every last treatment that has ever worked for someone in the past, including practices like bloodletting, acupuncture, etc? Would you give all of your patients this?

I really would be curious why you would say no to some treatments and not others. Would it be because a study on the treatment shows it improves patient outcomes in some statistically significant way? But statistical significance isn't a guarantee that the effect is real. Not to mention there can't be a study like that if this is some personalized medicine that was just generated by the AI.

Everyone wants the patient to survive but making correct decisions under uncertainty is not easy, I'm sure you know this. It gets harder when you can't even point to a mechanism for why a drug works.