2
$\begingroup$

I am finishing up the data collection for my retrospective cohort study, which I have designed with the intention of conducting survival analysis. Our outcomes of interest are recurrence, metastasis, and death following various surgical treatments for a type of cancer. A few dozen cases had only 1-2 weeks of follow-up post-treatment. I am wondering whether I need to include these cases considering the fact that 1-2 weeks is really not long enough for the outcomes of interest to occur. At the same time, I wouldn't want to harm the study's internal validity by excluding them. Indeed, it would be simple enough to include the cases and censor them on the last day of follow-up, even if it is a trivial length of time.

Thoughts?

$\endgroup$
5
$\begingroup$

If people are at risk, then you probably want to count them. If they get censored early, it will not affect things much, but if someone died after 1 week you would surely want to count that (doing anything else could induce survivorship bias). One question could be whether such patients were at risk for some of the outcomes (e.g. if an outcome can only be diagnosed at a visit to the clini , but the follow-up before the first visit).

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.