How exactly are eras generated? (e.g., Rx vs. Dx)

Gents:

Why couldn’t the data tell that? We could for each product generate the distribution of distance between individual admistrations (in case of drug) or diagnoses (in case of condition) and try to infer what a good persistence window would be. This could be improved by finding out (e.g. from the label) whether e.g. a “chronic” drug a drug is interventional (like pain meds, taken when it aches) or to control a certain condition (anitdiabetics, coagulants, immune suppressants). Likewise, for conditions, you could use the hierarchy to improve by comparing closely linked conditions to each other, who are likely on teh same scale of acuteness.

What did you have in mind?

1 Like