Jean-Louis Abitbol
2006-Oct-04 12:50 UTC
[R] [OT] Survival and Function as co-primary endpoints in clinical trials. How to simulate in R ?
Dear R-Helpers, Apologies in advance as this is partly (widely ?) OT. Not sure where to ask, R is my favorite computer tool (no kidding) and there are plenty of knowledgable and helpful people on the list. Background: There are discussions among experts and regulatory authorities (cf guideline http://www.emea.europa.eu/pdfs/human/ewp/056598en.pdf) that, in for example Amyotrophic Lateral Sclerosis, a functional endpoint (respiratory function, muscular testing, rating scale) should be associated (co-primary, 2 primaries etc..) to survival in drug trials. My problem: I wish to illustrate that from my point of view and when you have a drug that improves survival this is not what you should do for the following reasons: - Death leads to missing data on function (sic) - This does not occur at random if the drug impacts survival - The assessment of function is biased in defavor of the drug improving survival (keeping alive patients with poor function) and in favor of the placebo group (those who survive have better function) The questions: 1-Would some one please suggest litterature where this is discussed or examples of similar situations 2- I would like to simulate the process in R ie generate survival (exponential for a start although Weibull may be be more appropriate) data with several drug effects on survival (I can do this), and also simulate various effects on function (for example vital capacity) which would be correlated to the effect on survival (not sure I know what Ineed to do and how to do it...). I realize this is not clear language and a clear question but to help formulate the question better I would appreciate pointers to relevant litterature/scripts on simulation of clinical trials in general or more specific to my problem in R. Please answer to me directly to avoid OT inconvenience to the list and so that I am not black listed...I'll be happy to summarize if relevant to the list. Best regards, Jean-Louis Jean-Louis Abitbol, MD Chief Medical Officer Trophos SA, Parc scientifique de Luminy, Case 931 Luminy Biotech Entreprises 13288 Marseille Cedex 9 France Email: jlabitbol at trophos.com ---- Backup Email: abitbol at sent.com Cellular: (33) (0)6 24 47 59 34 Direct Line: (33) (0)4 91 82 82 73-Switchboard: (33) (0)4 91 82 82 82 Fax: (33) (0)4 91 82 82 89
Seemingly Similar Threads
- Error when reading a SAS transport file
- Script for dose proportionality assessment using power model and confidence interval criteria
- assigning differences in a loop
- Sample size for factorial clinical trials with survival endpoints
- BMDP and SAS (was R in clinical trials)