The figures, for anyone assembling their own picture. Relative versus absolute is the distinction that gets lost: a 20% relative reduction on a high baseline risk is a large absolute benefit, and the same relative figure on a low baseline risk is a small one.

Ask again with the specifics and you will get a better answer than this one.

Following on from Dr.EndoEP — and this may be the naive question:

How much of the SELECT benefit is plausibly independent of the weight loss, and whether that distinction changes anything practical?

DanielChem_CHI said:

Relative versus absolute is the distinction that gets lost: a 20% relative reduction on a high baseline risk is a large absolute benefit, and the same…

Adding the part of the answer the thread has not reached. SELECT is the trial that changed the framing of this class, because it was an outcome trial rather than a weight trial: about a 20% relative reduction in major adverse cardiovascular events in people with established cardiovascular disease and overweight or obesity, without diabetes. The effect appeared earlier than the weight-loss curve can comfortably explain, which is the basis for arguing that some of the benefit is direct — anti-inflammatory and vascular — rather than purely a consequence of weight.

Closing the loop on my own question.

Update: the thing I was blaming turned out not to be the cause. Leaving the original post as written rather than editing it, so the mistake stays visible for whoever searches this next.

LindaRN_retired said:

SELECT is the trial that changed the framing of this class, because it was an outcome trial rather than a weight trial: about a 20% relative reduction…

LindaRN_retired has the substance of this right. The condition it depends on is worth stating. Yes, and the corollary is less popular: if the reasoning holds, it also holds where it produces an answer we do not like.