hdPS and its machine learning extensions in residual confounding control

6.1 Genrate recurrence covariates

(Schneeweiss et al. 2009)

In this step, we generate 3 binary recurrence covariates for each of the candidate empirical covariates identified in the previous step:

occurred at least once
occurred sporadically (at least more than the median)
occurred frequently (at least more than the 75th percentile)

step2 <- get_recurrence_covariates(df = out1, 
                                   patientIdVarname = "idx",
                                   eventCodeVarname = "icd10", 
                                   patientIdVector = patientIds)

6.2 Example of recurrence covariates

ICD-10-CM code (dimension 1)	code appeared at least once	code appeared at least more than the median	code appeared at least more than the 75th percentile
D64.9 Anemia	rec_dx_D64_once	rec_dx_D64_sporadic	rec_dx_D64_frequent
D75.9P Blood clots	rec_dx_D75_once	rec_dx_D75_sporadic	rec_dx_D75_frequent
D89.9 Immune disorder	rec_dx_D89_once	rec_dx_D89_sporadic	rec_dx_D89_frequent
\(\ldots\)	\(\ldots\)	\(\ldots\)	\(\ldots\)
E07.9 Disorder of thyroid	rec_dx_E07_once	rec_dx_E07_sporadic	rec_dx_E07_frequent

Example of 3 binary covariates (hypothetical) created based on the candidate empirical covariates.

6.3 Recurrence covariates in the data

out2 <- step2$recurrence_data
ncol(out2)
#> [1] 143

Here we show binary recurrence covariates for only 2 columns

6.4 Refined recurrence covariates

Below you can click to see a list of all recurrence covariates obtained in our data.

ICD-10 Recurrence Data
1	rec_dx_A49_once	rec_dx_B00_once	rec_dx_B20_once
2	rec_dx_B20_frequent	rec_dx_B35_once	rec_dx_B37_once
3	rec_dx_B96_once	rec_dx_C50_once	rec_dx_D75_once
4	rec_dx_E03_once	rec_dx_E04_once	rec_dx_E05_once
5	rec_dx_E07_once	rec_dx_E28_once	rec_dx_E28_frequent
6	rec_dx_E29_once	rec_dx_E78_once	rec_dx_E79_once
7	rec_dx_E87_once	rec_dx_F17_once	rec_dx_F20_once
8	rec_dx_F20_frequent	rec_dx_F29_once	rec_dx_F31_once
9	rec_dx_F31_frequent	rec_dx_F32_once	rec_dx_F39_once
10	rec_dx_F41_once	rec_dx_F43_once	rec_dx_F90_once
11	rec_dx_G20_once	rec_dx_G20_frequent	rec_dx_G25_once
12	rec_dx_G30_once	rec_dx_G30_frequent	rec_dx_G31_once
13	rec_dx_G40_once	rec_dx_G43_once	rec_dx_G47_once
14	rec_dx_G89_once	rec_dx_H04_once	rec_dx_H10_once
15	rec_dx_H40_once	rec_dx_H40_frequent	rec_dx_H57_once
16	rec_dx_H57_frequent	rec_dx_H66_once	rec_dx_I10_once
17	rec_dx_I10_frequent	rec_dx_I20_once	rec_dx_I21_once
18	rec_dx_I48_once	rec_dx_I48_frequent	rec_dx_I49_once
19	rec_dx_I50_once	rec_dx_I50_frequent	rec_dx_I51_once
20	rec_dx_I63_once	rec_dx_I70_once	rec_dx_I80_once
21	rec_dx_I99_once	rec_dx_J01_once	rec_dx_J02_once
22	rec_dx_J20_once	rec_dx_J30_once	rec_dx_J40_once
23	rec_dx_J42_once	rec_dx_J43_once	rec_dx_J43_frequent
24	rec_dx_J44_once	rec_dx_J44_frequent	rec_dx_J45_once
25	rec_dx_J45_frequent	rec_dx_J98_once	rec_dx_K04_once
26	rec_dx_K08_once	rec_dx_K21_once	rec_dx_K25_once
27	rec_dx_K27_once	rec_dx_K30_once	rec_dx_K31_once
28	rec_dx_K58_once	rec_dx_K59_once	rec_dx_K76_once
29	rec_dx_K92_once	rec_dx_L08_once	rec_dx_L20_once
30	rec_dx_L23_once	rec_dx_L29_once	rec_dx_L40_once
31	rec_dx_L70_once	rec_dx_L93_once	rec_dx_L93_frequent
32	rec_dx_M06_once	rec_dx_M06_frequent	rec_dx_M10_once
33	rec_dx_M13_once	rec_dx_M19_once	rec_dx_M1A_once
34	rec_dx_M25_once	rec_dx_M54_once	rec_dx_M62_once
35	rec_dx_M79_once	rec_dx_M81_once	rec_dx_N19_once
36	rec_dx_N20_once	rec_dx_N28_once	rec_dx_N30_once
37	rec_dx_N32_once	rec_dx_N39_once	rec_dx_N40_once
38	rec_dx_N42_once	rec_dx_N52_once	rec_dx_N92_once
39	rec_dx_N94_once	rec_dx_N95_once	rec_dx_R00_once
40	rec_dx_R05_once	rec_dx_R06_once	rec_dx_R07_once
41	rec_dx_R09_once	rec_dx_R10_once	rec_dx_R11_once
42	rec_dx_R12_once	rec_dx_R19_once	rec_dx_R21_once
43	rec_dx_R25_once	rec_dx_R32_once	rec_dx_R35_once
44	rec_dx_R39_once	rec_dx_R41_once	rec_dx_R42_once
45	rec_dx_R45_once	rec_dx_R51_once	rec_dx_R52_once
46	rec_dx_R60_once	rec_dx_R73_once	rec_dx_T14_once
47	rec_dx_T78_once	rec_dx_T88_once	rec_dx_Z79_once
48	rec_dx_Z95_once

Tip

Given that we had one dimension of proxy data, \(p=1\), at most \(n=200\) most prevalent codes (with the restriction that minimum number of patients in each code = 20), and \(3\) intensity, we could theoretically have at most \(p \times n \times 3 = 1 \times 200 \times \ 3 = 600\) recurrence covariates.

Based on all of the restrictions, we created 143 distinct recurrence covariates.
The merged data (analytic and proxies) size is now 7,585.

If 2 or all 3 recurrence covariates are identical, only one distinct recurrence covariate is returned. This is why you do not see any sporadic recurrence covariate here.
Recurrence covariate creation is for each patient, and it is possible to have same code occur multiple time because we are working with a 3 digit granularity (possible to have medications from other codes within same ICD-10 3 digit granularity).