Statins and Statistics
Guidelines for doctors recommend prescribing cholesterol medication for patients who show a ten percent (or even lower) chance of developing heart disease over the next ten years by the most recent approved measure. When I first heard about this it struck me as odd, even absurd: another case of a hammer seeing everything as a nail. For doctors, all of us are only varying degrees of sick, and hence in need of treatment, since we are never perfectly healthy, right? But how could 10 percent be something to worry about? Isn’t it intuitive that something is probable only if it's >50 percent? And 10 percent is so far below that that it seems downright im probable. But then I thought about it in a different way: Suppose someone handed you a revolver with ten chambers in the cylinder and a bullet in one of them. Would you be willing to play Russian roulette? Or suppose you were one of ten people in a room, one of whom was to be chosen at random to be killed...