Read the primary source rather than the write-up and the two do not agree, so here is what is actually in it.
The apnoea data is some of the strongest non-weight evidence in the class. SURMOUNT-OSA showed large reductions in apnoea-hypopnoea index on tirzepatide, with a meaningful fraction of participants improving enough to change their treatment category. Mechanistically it is upper-airway fat and reduced abdominal load rather than anything neurological, which is why the effect tracks weight loss closely.
Where I think it is weakest: the follow-up is short relative to how long people actually take these drugs, so durability is an assumption here rather than a finding.
So the question, as narrowly as I can put it: what people did about re-titration, because feeling better is not the same as a study saying you are better. Happy to be told the question itself is wrong.
Note on sourcing:
Figures above are from the primary publication rather than the press summary. If a number here disagrees with one you have, post yours and we will work out which of us is reading a secondary source.