Re:Too Many Medicines Simply Don’t Work
by LorenPechtel on Friday May 31, 2019 @03:40PM
(#20064240)
Yeah. When evaluating a drug we should not only be looking overall, but if there is a subset of the test population for which it behaves differently. This is especially true for any diagnosis of exclusion.
Such a drug should be approved but with a big warning that it only works in some cases.
You have to fix the hypotheses to test before you begin the experiment, as otherwise you will stumble upon a lot of spurious correlations. That your birthday is the same day than someone's in your class/work group is a rare event, that two people have the same birthday in your class/work group, not at all uncommon. This is the birthday paradox. In the same spirit, with a drug you'll always find groups where it works because of spurious correlations, specially if you don't fix beforehand the group where you want to test it.
Run one trial to find correlations with specific groups, then run another trial under the hypothesis that it works for that group.
Well sure but that costs a fortune. Drug development is already extremely expensive.
That is a good idea, but it generates accusations of special pleading. Medical science is plagued with many kinds of fetish, and medical doctors are not generally obliged to actually understand science.
But the DSM is full of illnesses that are really a half dozen completely different conditions with the same (or just similar) apparent symptoms, each with its own cause, and no reliable way to distinguish it from the others except that maybe drug X helps one, and drugs Y, Z, W, and V are useless for it. Likewise, the one that Y helps, and the one that responds to Z, and the rest where nothing seems to work. In double-blind trials, V, W, X, Y, and Z are all "shown" to be equally useless.
That does NOT mean V, W, X, Y, and Z don't work. The "gold standard" is as subject to GIGO as everything else. You simply cannot tell anything about what it means without looking at underlying facts.