Hacker News new | ask | show | jobs
by Supermancho 1345 days ago
> The gold standard is the invitation.

I'm not sure what gold standard you are referring to (or the article or the paper - https://www.nejm.org/doi/full/10.1056/NEJMoa2208375).

Double blind studies require there to be data. An invitation doesn't speak to the effects of Colonoscopy screening at all, while simultaneously adding a confounding variable about participation. The data is about the effects of offering screenings, not the effect of those screenings, per se.

Lifelong data is the gold standard for questions about mortality and most Colonoscopy randomized trials started around 2010 (hence this very early 10-year study, which I would say is premature).
2 comments
uslic001 1344 days ago
They used intention to treat in the analysis so it included everyone invited to get a colonoscopy but only 42% got the exam. So 58% did not even get the colonoscopy. It is impossible to say what colonoscopy does or does not prevent when the majority of people in the intervention arm of the study did not get the intervention.
link
JamesBarney 1345 days ago
Participation is a confounding variable if you compare the subset of invitation group that participated with the control group instead of the invitation to the control group. That's the whole reason they use intent to treat.

Lifelong correlational data is not the gold standard for questions about mortality. It's intent to treat RCTs.

link
Supermancho 1345 days ago
> Participation is a confounding variable if you compare the subset of invitation group that participated with the control group instead of the invitation to the control group.

I believe that's what I said. That's certainly what was used. You can't compare the group subset that didn't participate, so it's a confounding variable.

> Lifelong correlational data is not the gold standard for questions about mortality.

AFAIK it is and has been over the last century. If you aren't tracking lifelong data, your mortality data is always skewed against hidden results because you didn't want to wait. When making a paper that isn't qualified (decade long effects vs effects), it's not expected to have short time-boxed data.

link