Anders Alexandersson
Anders Alexandersson
Both your packages are great. But it would be very helpful if you can better describe or explain the differences. My question is: **Why does the regular sum score differ...
@jackwasey @ellessenne The user-written Stata command `elixhauser` (SSC) agrees with `comorbidity`. Here I show the Stata output for the simulated data. ``` # Stata code: elixhauser code, idvar(id) index(e) tabm...
**Which mismatched codes does `icd9_comorbid_quan_elix(x, hierarchy = FALSE)` count and why?** Using the Stata command `cf` for comparing two datasets, I notice that here are 727 mismatches of 1,000 possible:...
How do I sort the `icd` data so that the two sets of data have the same sort order? I wrongly assumed `icd` would not change the sort order. I...
Thank you, Jack. The R code snippet sorts the input data with N=15,000. But it seems to me that it is the output data with N=1,000 that needs to be...
Thanks! So, there are 35 mismatched ids? That's worse than 3 but much better than 727 :-) ``` > table(singledf$same) 0 1 35 965 ```
My experience is the same. However, applied researchers differ widely in skills and needs. I work for the Florida cancer data registry. Before discussing scoring other than sum scores, it...
I had up-to-date `icd` stable version 3.1.2. I have now updated to development version 3.2.0 (fixed typo!). > packageVersion("icd") [1] ‘3.2.0’ > packageVersion("comorbidity") [1] ‘0.1.1’ As a result, when I...
I agree with Jack that it is now time to focus on the scoring: **In Alessandro's code, I do not understand the `score.comorbidity` for the remaining 9 problematic ids.** For...
Here is a list of all 9 observations for `comorbidity` that have problematic scoring to me: ``` > filter(comorbidity9, id %in% c(90,116,287,589,604,659,752,762,996)) %>% + select(id, hypc,ond,diabunc,diabc,rf,ld,pud,lymph,metacanc,solidtum, + coag,psycho,depre, score.comorbidity) id...