generated from opensafely/research-template
-
Notifications
You must be signed in to change notification settings - Fork 0
/
cr_analysis_dataset.do
1127 lines (854 loc) · 31.5 KB
/
cr_analysis_dataset.do
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
********************************************************************************
*
* Do-file: cr_analysis_dataset.do
*
* Project: SGTF 617 CFR
*
* Programmed by: Daniel Grint
*
* Data used: output/input.csv
* lookups/MSOA_lookup.dta
*
* Data created: output/cr_analysis_dataset.dta (main analysis dataset)
*
* Other output: None
*
********************************************************************************
*
* Purpose: This do-file creates the variables required for the
* main analysis and saves into Stata datasets.
*
********************************************************************************
* Open a log file
cap log close
log using ./logs/cr_analysis_dataset, replace t
clear
import delimited ./output/input.csv
merge m:1 msoa using ./lookups/MSOA_lookup
drop if _merge==2
drop _merge
rename hiv hiv_code
****************************
* Create required cohort *
****************************
gen study_start = date(sgss_pos_inrange, "YMD")
summ study_start
noi disp "MINIMUM START DATE: " %td r(min)
gen study_end = date("02july2021", "DMY")
format %td study_start study_end
* DROP IF NO POSITIVE PCR TEST IN SGSS DURING STUDY PERIOD
noi di "NO POSITIVE TEST IN STUDY PERIOD"
drop if sgss_pos_inrange == ""
* DROP IF DIED ON/BEFORE STUDY START DATE
noi di "DIED ON/BEFORE STUDY START DATE:"
drop if date(died_date_ons, "YMD") <= study_start
/* DROP IF COVID POSITIVE ON/BEFORE STUDY START DATE
noi di "COVID POSITIVE BEFORE STUDY START DATE:"
drop if date(covid_tpp_probable, "YMD") < study_start
drop if date(first_pos_test_sgss, "YMD") < study_start
*/
/* DROP IF VACCINATED ON/BEFORE STUDY START DATE
noi di "VACCINATED ON/BEFORE STUDY START DATE:"
drop if date(covid_vacc_date, "YMD") <= study_start
*/
* Age: Exclude those with implausible ages
assert age<.
noi di "DROPPING AGE>105:"
drop if age>105
* Sex: Exclude categories other than M and F
assert inlist(sex, "M", "F", "I", "U")
noi di "DROPPING GENDER NOT M/F:"
drop if inlist(sex, "I", "U")
**************************
* CREATE SGTF VARIABLE *
**************************
desc sgtf
replace sgtf=99 if sgtf==.
gen has_sgtf=0
replace has_sgtf=1 if inrange(sgtf,0,1)
label define sgtfLab 0 "non-VOC" 1 "VOC" 9 "Unclassified" 99 "Blank"
label values sgtf sgtfLab
******************************
* Convert strings to dates *
******************************
* Covariates
foreach var of varlist bp_sys_date ///
bp_dias_date ///
hba1c_percentage_date ///
hba1c_mmol_per_mol_date ///
hypertension ///
bmi_date_measured ///
chronic_respiratory_disease ///
chronic_cardiac_disease ///
diabetes ///
lung_cancer ///
haem_cancer ///
other_cancer ///
chronic_liver_disease ///
stroke ///
dementia ///
other_neuro ///
organ_transplant ///
dysplenia ///
sickle_cell ///
aplastic_anaemia ///
hiv_date ///
permanent_immunodeficiency ///
temporary_immunodeficiency ///
ra_sle_psoriasis dialysis {
confirm string variable `var'
replace `var' = `var' + "-15"
rename `var' `var'_dstr
replace `var'_dstr = " " if `var'_dstr == "-15"
gen `var'_date = date(`var'_dstr, "YMD")
order `var'_date, after(`var'_dstr)
drop `var'_dstr
format `var'_date %td
}
rename bmi_date_measured_date bmi_date_measured
rename bp_dias_date_measured_date bp_dias_date
rename bp_sys_date_measured_date bp_sys_date
rename hba1c_percentage_date_date hba1c_percentage_date
rename hba1c_mmol_per_mol_date_date hba1c_mmol_per_mol_date
rename hiv_date_date hiv_date
* Dates of: covid tests, ONS death
foreach var of varlist dereg_date died_date_ons covid_tpp_probable covid_vacc_date ///
first_pos_test_sgss sgss_pos_inrange ae_admission_date {
confirm string variable `var'
rename `var' _tmp
gen `var' = date(_tmp, "YMD")
drop _tmp
format %d `var'
}
gen ae_dest = string(ae_destination,"%17.0g")
*******************************
* Recode implausible values *
*******************************
* BMI
* Only keep if within certain time period? using bmi_date_measured ?
* NB: Some BMI dates in future or after cohort entry
* Set implausible BMIs to missing:
replace bmi = . if !inrange(bmi, 15, 50)
* Sex
assert inlist(sex, "M", "F")
gen male = (sex=="M")
drop sex
label define maleLab 0 "F" 1 "M"
label values male maleLab
* Smoking
label define smoke_nomissLab 1 "Never" 2 "Former" 3 "Current"
gen smoke = 1 if smoking_status=="N"
replace smoke = 2 if smoking_status=="E"
replace smoke = 3 if smoking_status=="S"
replace smoke = . if smoking_status=="M"
label values smoke smoke_nomissLab
drop smoking_status
* Ethnicity (5 category)
tab ethnicity, m
replace ethnicity = . if ethnicity==.
label define ethnicityLab 1 "White" ///
2 "Mixed" ///
3 "Asian or Asian British" ///
4 "Black" ///
5 "Other"
label values ethnicity ethnicityLab
* Re-order ethnicity
gen eth5=1 if ethnicity==1
replace eth5=2 if ethnicity==3
replace eth5=3 if ethnicity==4
replace eth5=4 if ethnicity==2
replace eth5=5 if ethnicity==5
replace eth5=6 if ethnicity==.
label define eth5Lab 1 "White" ///
2 "South Asian" ///
3 "Black" ///
4 "Mixed" ///
5 "Other" ///
6 "Missing"
label values eth5 eth5Lab
recode eth5 2/4=5, gen(eth2)
order eth2, after(eth5)
label values eth2 eth5Lab
tab eth2, m
* Ethnicity (16 category)
replace ethnicity_16 = . if ethnicity==.
label define ethnicity_16 ///
1 "British or Mixed British" ///
2 "Irish" ///
3 "Other White" ///
4 "White + Black Caribbean" ///
5 "White + Black African" ///
6 "White + Asian" ///
7 "Other mixed" ///
8 "Indian or British Indian" ///
9 "Pakistani or British Pakistani" ///
10 "Bangladeshi or British Bangladeshi" ///
11 "Other Asian" ///
12 "Caribbean" ///
13 "African" ///
14 "Other Black" ///
15 "Chinese" ///
16 "Other"
label values ethnicity_16 ethnicity_16
* Ethnicity (16 category grouped further)
* Generate a version of the full breakdown with mixed in one group
gen ethnicity_16_combinemixed = ethnicity_16
recode ethnicity_16_combinemixed 4/7 = 4
label define ethnicity_16_combinemixed ///
1 "British or Mixed British" ///
2 "Irish" ///
3 "Other White" ///
4 "All mixed" ///
8 "Indian or British Indian" ///
9 "Pakistani or British Pakistani" ///
10 "Bangladeshi or British Bangladeshi" ///
11 "Other Asian" ///
12 "Caribbean" ///
13 "African" ///
14 "Other Black" ///
15 "Chinese" ///
16 "Other"
label values ethnicity_16_combinemixed ethnicity_16_combinemixed
* STP
tab stp
rename stp stp_old
bysort stp_old: gen stp = 1 if _n==1
replace stp = sum(stp)
drop stp_old
* MSOA/UTLA
egen n_msoa = tag(msoa)
count if n_msoa
bysort msoa: gen count1 = _N
summ count1, d
egen n_utla = tag(utla)
count if n_utla
bysort utla: gen count2 = _N
summ count2, d
* Regroup UTLAs with small case numbers
gen utla_group = utla_name
tab utla_group
replace utla_group = "Redbridge, Barking and Dagenham" if utla_name == "Barking and Dagenham"
replace utla_group = "Redbridge, Barking and Dagenham" if utla_name == "Redbridge"
replace utla_group = "Bucks/Ox/West. Berks/Swindon" if utla_name == "Buckinghamshire"
replace utla_group = "Bucks/Ox/West. Berks/Swindon" if utla_name == "Oxfordshire"
replace utla_group = "Bucks/Ox/West. Berks/Swindon" if utla_name == "Swindon"
replace utla_group = "Bucks/Ox/West. Berks/Swindon" if utla_name == "West Berkshire"
replace utla_group = "Camden and Westminster" if utla_name == "Camden"
replace utla_group = "Camden and Westminster" if utla_name == "Westminster"
replace utla_group = "" if utla_name == "Isles of Scilly"
replace utla_group = "Richmond and Hounslow" if utla_name == "Richmond upon Thames"
replace utla_group = "Richmond and Hounslow" if utla_name == "Hounslow"
replace utla_group = "Rutland and Lincoln" if utla_name == "Rutland"
replace utla_group = "Rutland and Lincoln" if utla_name == "Lincolnshire"
replace utla_group = "Bolton and Tameside" if utla_name == "Bolton"
replace utla_group = "Bolton and Tameside" if utla_name == "Tameside"
tab utla_group, m
* NHS England regions
tab region, m
gen region2=.
replace region2=0 if region=="East"
replace region2=1 if region=="East Midlands"
replace region2=2 if region=="London"
replace region2=3 if region=="North East"
replace region2=4 if region=="North West"
replace region2=5 if region=="South East"
replace region2=6 if region=="South West"
replace region2=7 if region=="West Midlands"
replace region2=8 if region=="Yorkshire and The Humber"
drop region
rename region2 region
label define regionLab 0 "East" ///
1 "East Midlands" ///
2 "London" ///
3 "North East" ///
4 "North West" ///
5 "South East" ///
6 "South West" ///
7 "West Midlands" ///
8 "Yorkshire and the Humber"
label values region regionLab
**************************
* Categorise variables *
**************************
/* Age variables */
noi di "DROPPING IF NO AGE"
drop if age>=.
* Create categorised age
recode age 0/17.9999=0 ///
18/29.9999 = 1 ///
30/39.9999 = 2 ///
40/49.9999 = 3 ///
50/59.9999 = 4 ///
60/69.9999 = 5 ///
70/79.9999 = 6 ///
80/max = 7, gen(agegroup)
label define agegroupLab 0 "0-<18" ///
1 "18-<30" ///
2 "30-<40" ///
3 "40-<50" ///
4 "50-<60" ///
5 "60-<70" ///
6 "70-<80" ///
7 "80+"
label values agegroup agegroupLab
* For subgroup analysis
recode age 0/64.9999=1 ///
65/74.9999=2 ///
75/84.9999=3 ///
85/max=4, gen(agegroupA)
label define agegroupALab 1 "0-<65" ///
2 "65-<75" ///
3 "75-<85" ///
4 "85+"
label values agegroupA agegroupALab
* More age categories
recode age 0/39.9999=0 ///
40/54.9999 = 1 ///
55/64.9999 = 2 ///
65/74.9999 = 3 ///
75/84.9999 = 4 ///
85/max = 5, gen(agegroup6)
label define agegroup6Lab 0 "0-<40" ///
1 "40-<55" ///
2 "55-<65" ///
3 "65-<75" ///
4 "75-<85" ///
5 "85+"
label values agegroup6 agegroup6Lab
* Create binary age
recode age min/69.999=0 70/max=1, gen(age70)
* Check there are no missing ages
assert age<.
assert agegroup<.
assert age70<.
* Create restricted cubic splines for age centred on 65
gen age65 = age - 65
mkspline age = age65, cubic nknots(4)
/* Body Mass Index */
* BMI (NB: watch for missingness)
gen bmicat = .
recode bmicat . = 1 if bmi<18.5
recode bmicat . = 2 if bmi<25
recode bmicat . = 3 if bmi<30
recode bmicat . = 4 if bmi<35
recode bmicat . = 5 if bmi<40
recode bmicat . = 6 if bmi<.
replace bmicat = . if bmi>=.
label define bmicat 1 "Underweight (<18.5)" ///
2 "Normal (18.5-24.9)" ///
3 "Overweight (25-29.9)" ///
4 "Obese I (30-34.9)" ///
5 "Obese II (35-39.9)" ///
6 "Obese III (40+)"
label values bmicat bmicat
* Create more granular categorisation
recode bmicat 1/3 . = 1 4=2 5=3 6=4, gen(obese4cat)
label define obese4catLab 1 "No record of obesity" ///
2 "Obese I (30-34.9)" ///
3 "Obese II (35-39.9)" ///
4 "Obese III (40+)"
label values obese4cat obese4catLab
order obese4cat, after(bmicat)
tab obese4cat, m
/* Smoking */
* Create non-missing 3-category variable for current smoking
recode smoke .=1, gen(smoke_nomiss)
order smoke_nomiss, after(smoke)
label values smoke_nomiss smoke_nomissLab
recode smoke_nomiss 3=2, gen(smoke_nomiss2)
order smoke_nomiss2, after(smoke_nomiss)
label values smoke_nomiss2 smoke_nomissLab
tab smoke_nomiss2, m
/* Asthma */
* Asthma (coded: 0 No, 1 Yes no OCS, 2 Yes with OCS)
rename asthma asthmacat
recode asthmacat 0=1 1=2 2=3 .=1
label define asthmacat 1 "No" 2 "Yes, no OCS" 3 "Yes with OCS"
label values asthmacat asthmacat
gen asthma = (asthmacat==2|asthmacat==3)
/* Blood pressure */
* Categorise
gen bpcat = 1 if bp_sys < 120 & bp_dias < 80
replace bpcat = 2 if inrange(bp_sys, 120, 130) & bp_dias<80
replace bpcat = 3 if inrange(bp_sys, 130, 140) | inrange(bp_dias, 80, 90)
replace bpcat = 4 if (bp_sys>=140 & bp_sys<.) | (bp_dias>=90 & bp_dias<.)
replace bpcat = . if bp_sys>=. | bp_dias>=. | bp_sys==0 | bp_dias==0
label define bpcat 1 "Normal" 2 "Elevated" 3 "High, stage I" ///
4 "High, stage II"
label values bpcat bpcat
recode bpcat .=1, gen(bpcat_nomiss)
label values bpcat_nomiss bpcat
* Create non-missing indicator of known high blood pressure
gen bphigh = (bpcat==4)
order bpcat bphigh, after(bp_dias_date)
/* IMD */
* Group into 5 groups
rename imd imd_o
egen imd = cut(imd_o), group(5) icodes
replace imd = imd + 1
replace imd = . if imd_o==-1
drop imd_o
tab imd
* Reverse the order (so high is more deprived)
recode imd 5=1 4=2 3=3 2=4 1=5 .=.
tab imd
label define imdLab 1 "1 least deprived" 2 "2" 3 "3" 4 "4" 5 "5 most deprived"
label values imd imdLab
noi di "DROPPING IF NO IMD"
drop if imd>=.
/* HOUSEHOLD SIZE */
gen hh_total_cat=.
replace hh_total_cat=1 if household_size >=1 & household_size<=2
replace hh_total_cat=2 if household_size >=3 & household_size<=5
replace hh_total_cat=3 if household_size >=6 & household_size<=10
replace hh_total_cat=4 if household_size >=11 & household_size !=.
label define hh_total_catLab 1 "1-2" ///
2 "3-5" ///
3 "6-10" ///
4 "11+"
label values hh_total_cat hh_total_catLab
tab hh_total_cat, m
/* RURAL OR URBAN */
* Create a 5 category rural urban variable based upon meeting with Roz 21st October
gen rural_urban5=.
replace rural_urban5=1 if rural_urban==1
replace rural_urban5=2 if rural_urban==2
replace rural_urban5=3 if rural_urban==3|rural_urban==4
replace rural_urban5=4 if rural_urban==5|rural_urban==6
replace rural_urban5=5 if rural_urban==7|rural_urban==8
label define rural_urban5Lab 1 "Urban major conurbation" ///
2 "Urban minor conurbation" ///
3 "Urban city and town" ///
4 "Rural town and fringe" ///
5 "Rural village and dispersed"
label values rural_urban5 rural_urban5Lab
tab rural_urban5, m
/* CARE HOME TYPE */
tab care_home_type, m
gen home_bin=0
replace home_bin=1 if care_home_type=="PC" | care_home_type=="PN" | care_home_type=="PS"
tab care_home_type home_bin, m
label define home_binLab 0 "Private home" ///
1 "Care home"
label values home_bin home_binLab
/* Centred age, sex, IMD, ethnicity (for adjusted KM plots) */
* Centre age (linear)
summ age
gen c_age = age-r(mean)
* "Centre" sex to be coded -1 +1
recode male 0=-1, gen(c_male)
* "Centre" IMD
gen c_imd = imd - 3
* "Centre" ethnicity
gen c_ethnicity = ethnicity - 3
**************************************************
* Create binary comorbidity indices from dates *
**************************************************
* Comorbidities ever before study_start
foreach var of varlist chronic_respiratory_disease_date ///
chronic_cardiac_disease_date ///
diabetes_date ///
chronic_liver_disease_date ///
stroke_date ///
dementia_date ///
other_neuro_date ///
organ_transplant_date ///
aplastic_anaemia_date ///
hypertension_date ///
dysplenia_date ///
sickle_cell_date ///
hiv_date ///
permanent_immunodeficiency_date ///
temporary_immunodeficiency_date ///
ra_sle_psoriasis_date dialysis_date {
local newvar = substr("`var'", 1, length("`var'") - 5)
gen `newvar' = (`var'< study_start)
order `newvar', after(`var')
}
**************************
* Epidemiological week *
**************************
gen start_week = 12 if study_start <= date("02jul2021", "DMY")
replace start_week = 11 if study_start <= date("23jun2021", "DMY")
replace start_week = 10 if study_start <= date("16jun2021", "DMY")
replace start_week = 9 if study_start <= date("09may2021", "DMY")
replace start_week = 8 if study_start <= date("02jun2021", "DMY")
replace start_week = 7 if study_start <= date("26may2021", "DMY")
replace start_week = 6 if study_start <= date("19may2021", "DMY")
replace start_week = 5 if study_start <= date("12may2021", "DMY")
replace start_week = 4 if study_start <= date("05may2021", "DMY")
replace start_week = 3 if study_start <= date("28apr2021", "DMY")
replace start_week = 2 if study_start <= date("21apr2021", "DMY")
replace start_week = 1 if study_start <= date("14apr2021", "DMY")
tab start_week, m
label define start_weekLab 1 "07Apr-14Apr" ///
2 "15Apr-21Apr" ///
3 "22Apr-28Apr" ///
4 "29Apr-05May" ///
5 "06May-12May" ///
6 "13May-19May" ///
7 "20May-26May" ///
8 "27May-02Jun" ///
9 "03Jun-09Jun" ///
10 "10Jun-16Jun" ///
11 "17Jun-23Jun" ///
12 "24Jun-02Jul"
label values start_week start_weekLab
tab start_week, m
/*
* Recode small epi weeks 1 and 2 for epi week interaction
recode start_week 1=2, gen(start_weekA)
label define start_weekLabA 2 "16Nov-29Nov" ///
3 "30Nov-06Dec" ///
4 "07Dec-13Dec" ///
5 "14Dec-20Dec" ///
6 "21Dec-27Dec" ///
7 "28Dec-03Jan" ///
8 "04Jan-11Jan"
label values start_weekA start_weekLabA
tab start_week start_weekA
*/
***************************
* Grouped comorbidities *
***************************
/* Neurological */
* Stroke and dementia
egen stroke_dementia = rowmax(stroke dementia)
order stroke_dementia, after(dementia_date)
/* Spleen */
* Spleen problems (dysplenia/splenectomy/etc and sickle cell disease)
egen spleen = rowmax(dysplenia sickle_cell)
order spleen, after(sickle_cell)
/* Cancer */
label define cancer 1 "Never" 2 "Last year" 3 "2-5 years ago" 4 "5+ years"
local fiveybefore = study_start-5*365.25
local oneybefore = study_start-365.25
* Haematological malignancies
gen cancer_haem_cat = 4 if inrange(haem_cancer_date, d(1/1/1900), `fiveybefore')
replace cancer_haem_cat = 3 if inrange(haem_cancer_date, `fiveybefore', `oneybefore')
replace cancer_haem_cat = 2 if inrange(haem_cancer_date, `oneybefore', study_start)
recode cancer_haem_cat . = 1
label values cancer_haem_cat cancer
* All other cancers
gen cancer_exhaem_cat = 4 if inrange(lung_cancer_date, d(1/1/1900), `fiveybefore') | ///
inrange(other_cancer_date, d(1/1/1900), `fiveybefore')
replace cancer_exhaem_cat = 3 if inrange(lung_cancer_date, `fiveybefore', `oneybefore') | ///
inrange(other_cancer_date, `fiveybefore', `oneybefore')
replace cancer_exhaem_cat = 2 if inrange(lung_cancer_date, `oneybefore', study_start) | ///
inrange(other_cancer_date, `oneybefore', study_start)
recode cancer_exhaem_cat . = 1
label values cancer_exhaem_cat cancer
* Put variables together
order cancer_exhaem_cat cancer_haem_cat, after(other_cancer_date)
/* Immunosuppression */
* Immunosuppressed:
* HIV, permanent immunodeficiency ever, OR
* temporary immunodeficiency or aplastic anaemia last year
gen temp1 = max(hiv, permanent_immunodeficiency)
gen temp2 = inrange(temporary_immunodeficiency_date, `oneybefore', study_start)
gen temp3 = inrange(aplastic_anaemia_date, `oneybefore', study_start)
egen other_immunosuppression = rowmax(temp1 temp2 temp3)
drop temp1 temp2 temp3
order other_immunosuppression, after(temporary_immunodeficiency)
/* Hypertension */
gen htdiag_or_highbp = bphigh
recode htdiag_or_highbp 0 = 1 if hypertension==1
************
* eGFR *
************
* Set implausible creatinine values to missing (Note: zero changed to missing)
replace creatinine = . if !inrange(creatinine, 20, 3000)
* Divide by 88.4 (to convert umol/l to mg/dl)
gen SCr_adj = creatinine/88.4
gen min=.
replace min = SCr_adj/0.7 if male==0
replace min = SCr_adj/0.9 if male==1
replace min = min^-0.329 if male==0
replace min = min^-0.411 if male==1
replace min = 1 if min<1
gen max=.
replace max=SCr_adj/0.7 if male==0
replace max=SCr_adj/0.9 if male==1
replace max=max^-1.209
replace max=1 if max>1
* egfr calculated using CKD-EPI formula with no eth
gen egfr=min*max*141
replace egfr=egfr*(0.993^age)
replace egfr=egfr*1.018 if male==0
* Categorise into ckd stages
* CKD stage calc without eth
egen egfr_cat = cut(egfr), at(0, 15, 30, 45, 60, 5000)
recode egfr_cat 0=5 15=4 30=3 45=2 60=0, generate(ckd)
* 0 = "No CKD" 2 "stage 3a" 3 "stage 3b" 4 "stage 4" 5 "stage 5"
label define ckd 0 "No CKD" 1 "CKD"
label values ckd ckd
* Convert into CKD group
*recode ckd 2/5=1, gen(chronic_kidney_disease)
*replace chronic_kidney_disease = 0 if creatinine==.
recode ckd 0=1 2/3=2 4/5=3, gen(reduced_kidney_function_cat)
replace reduced_kidney_function_cat = 1 if creatinine==.
label define reduced_kidney_function_catlab ///
1 "None" 2 "Stage 3a/3b egfr 30-60 " 3 "Stage 4/5 egfr<30"
label values reduced_kidney_function_cat reduced_kidney_function_catlab
*More detailed version incorporating stage 5 or dialysis as a separate category
recode ckd 0=1 2/3=2 4=3 5=4, gen(reduced_kidney_function_cat2)
replace reduced_kidney_function_cat2 = 1 if creatinine==.
replace reduced_kidney_function_cat2 = 4 if dialysis==1
label define reduced_kidney_function_cat2lab ///
1 "None" 2 "Stage 3a/3b egfr 30-60 " 3 "Stage 4 egfr 15-<30" 4 "Stage 5 egfr <15 or dialysis"
label values reduced_kidney_function_cat2 reduced_kidney_function_cat2lab
***********
* Hba1c *
***********
/* Diabetes severity */
* Set zero or negative to missing
replace hba1c_percentage = . if hba1c_percentage<=0
replace hba1c_mmol_per_mol = . if hba1c_mmol_per_mol<=0
local fifteenmbefore = study_start-15*(365.25/12)
* Only consider measurements in last 15 months
replace hba1c_percentage = . if hba1c_percentage_date < `fifteenmbefore'
replace hba1c_mmol_per_mol = . if hba1c_mmol_per_mol_date < `fifteenmbefore'
/* Express HbA1c as percentage */
* Express all values as perecentage
noi summ hba1c_percentage hba1c_mmol_per_mol
gen hba1c_pct = hba1c_percentage
replace hba1c_pct = (hba1c_mmol_per_mol/10.929)+2.15 if hba1c_mmol_per_mol<.
* Valid % range between 0-20
replace hba1c_pct = . if !inrange(hba1c_pct, 0, 20)
replace hba1c_pct = round(hba1c_pct, 0.1)
/* Categorise hba1c and diabetes */
* Group hba1c
gen hba1ccat = 0 if hba1c_pct < 6.5
replace hba1ccat = 1 if hba1c_pct >= 6.5 & hba1c_pct < 7.5
replace hba1ccat = 2 if hba1c_pct >= 7.5 & hba1c_pct < 8
replace hba1ccat = 3 if hba1c_pct >= 8 & hba1c_pct < 9
replace hba1ccat = 4 if hba1c_pct >= 9 & hba1c_pct !=.
label define hba1ccat 0 "<6.5%" 1">=6.5-7.4" 2">=7.5-7.9" 3">=8-8.9" 4">=9"
label values hba1ccat hba1ccat
tab hba1ccat
* Create diabetes, split by control/not
gen diabcat = 1 if diabetes==0
replace diabcat = 2 if diabetes==1 & inlist(hba1ccat, 0, 1)
replace diabcat = 3 if diabetes==1 & inlist(hba1ccat, 2, 3, 4)
replace diabcat = 4 if diabetes==1 & !inlist(hba1ccat, 0, 1, 2, 3, 4)
label define diabcat 1 "No diabetes" ///
2 "Controlled diabetes" ///
3 "Uncontrolled diabetes" ///
4 "Diabetes, no hba1c measure"
label values diabcat diabcat
* Delete unneeded variables
drop hba1c_pct hba1c_percentage hba1c_mmol_per_mol
******************************
* Aggregated comorbidities *
******************************
/*
Create a comorbidities variable based upon Fizz's JCVI work that has 0, 1, 2 or more of
the following comorbdities:
(1) respiratory disease, (2) severe asthma, (3) chronic cardiac disease, (4) diabetes,
(5) non-haematological cancer (diagnosed in last year), (6) haematological cancer (diagnosed within 5 years),
(7) liver disease, (8) stroke, (9) dementia, (10) poor kidney function, (11) organ transplant,
(12) asplenia, (13) other immunosuppression.
*/
*(1) respiratory disease
tab chronic_respiratory_disease
*think I need level "3" of this, as this is asthma that requires OCS
*(2) severe asthma
tab asthmacat
generate asthma_severe=0
replace asthma_severe=1 if asthmacat==3
tab asthma_severe
*(3) cardiac disease
tab chronic_cardiac_disease
*(4) diabetes
tab diabcat
tab diabcat, nolabel
generate dm=0
replace dm=1 if diabcat>1
tab dm
tab dm diabcat
*(5) non-haem cancer (in previous year)
tab cancer_exhaem
tab cancer_exhaem, nolab
generate cancer_nonhaemPrevYear=0
replace cancer_nonhaemPrevYear=1 if cancer_exhaem_cat==2
tab cancer_nonhaemPrevYear
*(6) haem cancer (within previous 5 years)
tab cancer_haem
tab cancer_haem, nolab
generate cancer_haemPrev5Years=0
replace cancer_haemPrev5Years=1 if inrange(cancer_haem_cat,2,3)
tab cancer_haemPrev5Years
*(7) liver disease
tab chronic_liver_disease
*(8 and 9) stroke or dementia
tab stroke_dementia
*(10) poor kidney function
tab reduced_kidney_function_cat2
tab reduced_kidney_function_cat2, nolabel
gen egfr60 = 0
replace egfr60 = 1 if reduced_kidney_function_cat2 > 1
tab egfr60 reduced_kidney_function_cat2
*(11) organ transplant
tab organ_transplant
*(12) asplenia
tab spleen
*(13) other immunosuppression
tab other_immuno
*create a total comborb var
order chronic_respiratory_disease asthma_severe chronic_cardiac_disease dm cancer_nonhaemPrevYear cancer_haemPrev5Years chronic_liver_disease stroke_dementia egfr60 organ_transplant spleen other_immuno
egen totComorbsOfInterest=rowtotal(chronic_respiratory_disease - other_immuno)
summ totComorbsOfInterest, d
order totComorbsOfInterest
*create the covariate var I need
generate comorb_cat=.
replace comorb_cat=0 if totComorbsOfInterest==0
replace comorb_cat=1 if totComorbsOfInterest==1
replace comorb_cat=2 if totComorbsOfInterest>1
label define comorb_catLab 0 "No comorbidity" ///
1 "1 comorbidity" ///
2 "2+ comorbidities"
label values comorb_cat comorb_catLab
tab comorb_cat, m
********************************
* Outcomes and survival time *
********************************
/* 28-day risk censoring dates */
noi di "REMEMBER TO UPDATE DATE OF ONS DATA UPLOAD"
gen ons_data_date = date("18jun2021", "DMY")
gen ons_data_cens = ons_data_date-14 // Censor 14 days prior to ONS death data upload
gen risk_28_days = study_start+28
gen risk_40_days = study_start+40
* 28-day risk population
gen risk_pop = (risk_28_days <= ons_data_cens) // Indicator for has 28-days follow-up
gen time_check_28 = ons_data_cens-study_start
summ time_check_28 if risk_pop == 1, d
* 40-day risk population
gen risk_pop_40 = (risk_40_days <= ons_data_cens) // Indicator for has 40-days follow-up
gen time_check_40 = ons_data_cens-study_start
summ time_check_40 if risk_pop_40 == 1, d
/* Outcomes */
* 28-day risk indicator
gen died_pre_cens = (died_date_ons < ons_data_cens)
gen death_time = died_date_ons-study_start if died_pre_cens == 1
summ death_time, d
gen risk_28 = (death_time <= 28)
tab died_pre_cens risk_28, row
* 40-day risk indicator
gen risk_40 = (death_time <= 40)
tab died_pre_cens risk_40, row
/* Survival time */
* Censoring date for Cox
gen vacc_cens = covid_vacc_date - 7 if covid_vacc_date != .
gen cox_pop = (study_start < .) // Exclude if vaccinated within 7 days?
* Censor at death, ons data censor, or 7 days prior to vaccine
gen stime_death = min(died_date_ons, ons_data_cens, vacc_cens)
gen cox_death = (died_date_ons < .)
replace cox_death = 0 if (died_date_ons > stime_death)
gen cox_time = stime_death-study_start
gen cox_time_d = stime_death-study_start if cox_death==1
gen died = (died_date_ons < .)
/* Vaccination and previous infection */
gen vacc = (covid_vacc_date < sgss_pos_inrange)
gen first_covid = min(covid_tpp_probable, first_pos_test_sgss)