OHDSI Home | Forums | Wiki | Github

Creating custom covariates and table 1 specifications

(Sigfried Gold) #1

The Using Feature Extraction vignette mentions the possibility of creating custom table 1 specifications (p. 12):

The createTable1 function requires a simple specification of what variables to include in the table. The default specifications included in the package can be reviewed by calling the getDefaultTable1Specifications function. The specification reference analysis IDs and covariate IDs, and in the default specification these IDs refer to those in the default covariate settings. It is possible to create custom table 1 specifications and use those instead.

Can anyone provide any guidance on how to go about this? I’d like to make a table 1 that has custom covariates (I haven’t determined which of the two methods I’m going to use for making those yet.)

Alternatively, are there good examples of how to extract and present information from covariateData besides createTable1?

(Sigfried Gold) #2

I’ve been using the method for creating covariates from cohort attributes
described here, but then, looking for examples of how other people did this and how they used it, I found that maybe it’s never been used outside a single use in PatientLevelPrediction (see last item in
this github search).

@schuemie: It looks like you did a bunch of great work making feature extraction customizable. Are people using the other method (I haven’t checked yet), or have people been satisfied with existing covariates and table 1 output? Or am I looking in the wrong places. I guess I need to review more studies other people are doing rather than relying mostly on the feature extraction documentation, but if anyone has pointers, let me know.

(Sigfried Gold) #3

Oh, I just found this: CustomCovariateSetting from @Dongsu_Park and @SCYou. I’ll see what I can learn from browsing through the code.