Stepwise covariate modeling

Hi! I am performing stepwise covariate modeling using PsN feature in Pirana. I am getting some covariates which are statistically reducing OFV significantly, however, when I include those covariates in the PK model, the results I am getting are exactly similar to what I am getting in my base model, i.e. there is no difference in individual predictions or pop predictions or any other diagnostic plots. So, does that mean I should move forward WITHOUT including those covariates as they don't seem to be explaining inter-individual variability despite scm telling me that they are statistically significant? Regards, Sumeet K. Singla Ph.D. Candidate Division of Pharmaceutics and Translational Therapeutics College of Pharmacy | University of Iowa Iowa City, Iowa [email protected]<mailto:[email protected]> 518.577.5881

Hi, I am not 100% certain that a decrease in the IIV terms associated with the covariate-parameter relationships is a criteria used in the automated selection process implemented by the PsN scm command (at least I could not find any reference in the documentation). You may want to implement a more manual approach to the problem where you define your own set of criteria for covariate selection that you would apply at each step. PS: our KIWI platform can help you with the automated creation of univariate runs at each step and summarization of results while keeping you in control of the covariate selection criteria... --- Sébastien Bihorel Director, Pharmacometrics and KIWI™ applications Cognigen Corporation, a SimulationsPlus company Buffalo Office: +1 716 633 3463 ext. 323 | https://www.simulations-plus.com/cognigen/

Hi Sumeet, If you have rich sampling (and rich information on all parameters of interest) then one would not expect much difference between the individual parameter estimates with/without covariates in the model. This does not make the covariate model meaningless, since future patients may be sparsely sampled, or the model may be used to identify subpopulations, or for predictions of future patients, etc. When you say that pop predictions do not change, exactly what do you mean by that? The population typical value is not expected to change much (it may for categorical covariates with high impact) - the interpretation of the population parameter value has shifted from e.g. "median parameter value in population" (base model) to "median parameter value for a subject with typical covariate values". This is because the covariate equations are generally centered around typical covariate values: We do not want the population parameter to represent CL for a subject with zero kilo body weight - had it been coded that way the population parameters would have changed dramatically. So the question is rather if the typical parameter values for two subjects with different covariate values are different to a degree that it is important to account for (i.e. clinically relevant). If we assume that you have body weight on CL, you can calculate e.g. the 2.5th and 97.5th percentiles of body weight in your population (or in another population or relevance). And then you can calculate TVCL for these two different weights and compare to the typical body weight (e.g. 70 kg). You may have for example this equation*: TVCL=THETA(1)*(WT/70)**THETA(2) Based on the point estimate and SE of THETA 2, you can then calculate percent change (from the typical 70 kg body weight) with point estimate and 95% CI, for each of the two extreme body weights. And you can illustrate this in a so-called Forest plot (or tornado plot), for all covariate coefficients. If the CI is wide, the data does not contain enough information to rule out clinical relevance (if you think the parameter in question is important - maybe abs rate is in some cases not, for examples). But given that it has been selected by SCM, if the SE agrees (with LRT) CIs should not overlap with zero percent change. If the CI is tight and with small change in the parameter, then that covariate relation can be concluded to be clinically irrelevant, despite being statistically significant. This may happen if you have many subjects in your data. (Or if your limit for what is a relevant change is very wide) In this case it may be justified leaving that covariate relation out of the final model. Then of course, the fact that something was not statistically significant does not mean that the covariate effect is clinically irrelevant - it may just be that you do not have enough information. To assess that you would need to use FREM or FFEM (instead of SCM) - but this is out of scope for your original question. Best wishes Jakob *actually, for this example, THETA 2 may be fixed according to allometric principles, but let’s assume this is a large molecule and that allometry was not deemed suitable in this case, and therefore the covariate was tested in SCM, or otherwise estimated.

Hi, If all of the individual predictions are the same for the model with the covariate and without the covariate, then it sounds like the original model is at a local minimum instead of a global minimum. Best regards, Luann

I think we are making it more difficult than needed, especially for the people who just started using the NLME. It does not hurt to include statistically significant covariate in the model even if the actual effect is small and does no manifest itself on the standard diagnostic plots. It make sense to check whether there is an error in the model code. Plots of random effects versus covariates of interest should help to see whether covariate model changed the individual random effects. If not (that is, random effects of the model with and without covariate effect are numerically identical) then the coding is wrong and should be checked. Thanks Leonid

Thank you everyone for taking time out of your busy schedule to reply to my question. I think all points were excellent. Gives me more to think about how to proceed from here and make more informed decision about my model. Regards, Sumeet

I suspect you are using same file name at the bottom of model for base model as well as final model after inclusion of covariates. Please check, if so then use different file name for final model. I hope this can work. Regards Usman