Discussion: View Thread

Hello all,
I am working with a collaborator, trying to design a clinical trial for an intervention that is provided monthly. The primary outcome is whether the patient has any recurrence during the trial using an intent-to-treat analysis. We are trying to determine how to handle a secondary analysis of treatment "intensity", the number of monthly interventions a patient actually receives. We decided on this sort of analysis since it would be difficult to define a per-protocol analysis. The challenge I see is that once a subject has a recurrence, then the total number of monthly interventions they actually received is irrelevant since the monthly interventions beyond the recurrence clearly had no impact on that recurrence. The only thing that would be of importance is the number of interventions before a recurrence. However, patients that have a recurrence are automatically more likely to have fewer number of interventions. This issue seems similar to a drug trial where the patient would have to take the drug for several weeks before they achieve therapeutic levels of the drug, and they could have a recurrence before achieving therapeutic levels. I would welcome any advice!
Cheers,

------------------------------
Robert Podolsky
Biostatistician
------------------------------

Robert, I don't know if anyone replied privately. 
this may be a question best asked in the Biopharmaceutical section.  In advance of that, analyses of recurrence are well studied , for example using cox recurrent event analysis or some repeated measures mixed models. Possibly you could consider the recurrence as a time varying covariate. Perhaps the analyses of bladder tumor example often used in cox recurrent events would be helpful to look at , and if so, I think Therneau (and several others ) used that example. Some cox model formulations for bladder cancer  https://pubmed.ncbi.nlm.nih.gov/28525539/  The documentations for the survival module in R (authored by Therneau) has the bladder cancer recurrence data set https://cran.r-project.org/package=survival/survival.pdf

------------------------------
Chris Barker, Ph.D.
2022 Statistical Consulting Section
Chair-elect
Consultant and
Adjunct Associate Professor of Biostatistics
www.barkerstats.com


---
"In composition you have all the time you want to decide what to say in 15 seconds, in improvisation you have 15 seconds."
-Steve Lacy
------------------------------