-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathpreprocessing.Rmd
686 lines (564 loc) · 37.1 KB
/
preprocessing.Rmd
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
---
title: "Data Preprocessing for the VQI TEVAR Dataset"
author: "Jennifer Ci, Thu Vu, Lily Hanyi Wang"
output: pdf_document
---
```{r library, include=FALSE}
knitr::opts_chunk$set(echo = FALSE,message = FALSE,warning = FALSE)
library(tidyverse)
library(plyr)
library(Hmisc)
library(table1)
```
```{r setup wd}
## ------------- working directories for Lily ----------
wd_lily = '/Users/hanyiwang/Desktop/Comparative-analysis-of-treatments-of-CAA'
path_lily = c(
"../data/TEVAR_International_20210712/TEVAR_International_LTF_r12_2_14_20210701.csv",
"../data/TEVAR_International_20210712/TEVAR_International_PROC_r12_2_14_20210701.csv",
"../data/TEVAR_International_20210901/TEVAR_International_LTF_r12_2_14_20210901.csv",
"../data/TEVAR_International_20210901/TEVAR_International_PROC_r12_2_14_20210901.csv",
"../data/TEVAR_PROC.csv",
"../data/TEVAR_International_202301/TEVAR_International_LTF_20230103.csv",
"../data/TEVAR_International_202301/TEVAR_International_PROC_20230103.csv")
## ------------- working directories for Jennifer ----------
wd_jenn = '/Users/jenniferci/Desktop/Comparative-analysis-of-treatments-of-CAA'
path_jenn = c(
"../data/TEVAR_International_20210712/TEVAR_International_LTF_r12_2_14_20210701.csv",
"../data/TEVAR_International_20210712/TEVAR_International_PROC_r12_2_14_20210701.csv",
"../data/TEVAR_International_20210901/TEVAR_International_LTF_r12_2_14_20210901.csv",
"../data/TEVAR_International_20210901/TEVAR_International_PROC_r12_2_14_20210901.csv",
"../data/TEVAR_PROC.csv",
"../data/TEVAR_International_202301/TEVAR_International_LTF_20230103.csv",
"../data/TEVAR_International_202301/TEVAR_International_PROC_20230103.csv")
## ------------- read data ----------
# setwd(wd_lily)
# TEVAR_LTF_07 = read.csv(path_lily[1])
# TEVAR_LTF_09 = read.csv(path_lily[3])
# TEVAR_LTF_2301 = read.csv(path_lily[6])
# TEVAR_PROC_07 = read.csv(path_lily[2])
# TEVAR_PROC_09 = read.csv(path_lily[4])
# TEVAR_PROC_2301 = read.csv(path_lily[7])
setwd(wd_jenn)
# TEVAR_LTF_07 = read.csv(path_jenn[1])
# TEVAR_LTF_09 = read.csv(path_jenn[3])
# TEVAR_LTF_2301 = read.csv(path_jenn[6])
TEVAR_PROC_07 = read.csv(path_jenn[2])
TEVAR_PROC_09 = read.csv(path_jenn[4])
TEVAR_PROC_2301 = read.csv(path_jenn[7])
```
## Datasets Merging
Compare the data from July 2021, September 2021 and January 2023. Keep the most updated ones by merging LTF and PROC datasets separately.
```{r}
## ------------- merge July and September for PROC and LTF ----------
# # select mutual variables
# TEVAR_LTF_2301 = (TEVAR_LTF_2301 %>% select(colnames(TEVAR_LTF_2301)[colnames(TEVAR_LTF_2301) %in% colnames(TEVAR_LTF_09)]))
#
# # find new data and merge the 3 datasets
# TEVAR_LTF <- rbind(TEVAR_LTF_07[! TEVAR_LTF_07$PATIENTID %in% TEVAR_LTF_09$PATIENTID,],
# TEVAR_LTF_09)
# TEVAR_LTF <- rbind(TEVAR_LTF_2301[! TEVAR_LTF_2301$PATIENTID %in% TEVAR_LTF$PATIENTID,],
# TEVAR_LTF)
#
# # filter the varaibles in the LTF dataset
# TEVAR_LTF <- TEVAR_LTF %>% select(PATIENTID,PRIMPROCID,DEAD,PROC_SURVIVALDAYS,LTF_NUM_REINT)
# Similar for PROC data
TEVAR_PROC_2301 = (TEVAR_PROC_2301 %>% select(colnames(TEVAR_PROC_2301)[colnames(TEVAR_PROC_2301) %in% colnames(TEVAR_PROC_09)]))
TEVAR_PROC <-rbind(TEVAR_PROC_07[! TEVAR_PROC_07$PATIENTID %in% TEVAR_PROC_09$PATIENTID,],
TEVAR_PROC_09)
TEVAR_PROC <- rbind(TEVAR_PROC[! TEVAR_PROC$PATIENTID %in% TEVAR_PROC_2301$PATIENTID,],
TEVAR_PROC_2301)
```
We will work on the PROC and LTF datasets separately. The only variable we want to study in the LTF dataset is the re-intervention variable, `LTF_NUM_REINT`.
For the time-to-event analysis of re-intervention, we work on the LTF dataset and treat it as a multi-event recurrent survival analysis.
For the logistic regression model of re-intervention, we merge it with the PROC dataset to account for the variables as we did for other outcomes. Here we treated re-intervention as a binary outcome.
```{r}
## ------------- clean the LTF_NUM_REINT in LTF dataset----------
## ------------- merge LTF_NUM_REINT into the PROC dataset----------
## ------------- clean the LTF dataset----------
## ------------- select the variables needed in the LTF dataset----------
```
## Exclusion criteria:
- `PRESENTATION`: exclude rupture patients
- `PATHOLOGY`: exclude groups with pathology: 4 = trauma, 8 = Aortic Thrombus,9 = Other,10 = Aorto-esophageal Fistula,11 = Aorto-bronchial Fistula
- `URGENCY`: exclude rupture. (`elective` is the same as `asymptomatic`)
- `PROXZONE_DISEASE`: exclude 0 and 1
- `DISTZONE_DISEASE`: exclude 0
- `PROXZONE_DISEASE < DISTZONE_DISEASE`: disease starting point should be earlier than ending point. 35 wrong data points with distal zone < proximal zone are excluded.
```{r}
## ------------- exclusion----------
TEVAR_PROC = TEVAR_PROC %>%
filter(PRESENTATION !=2) %>%
filter(PATHOLOGY %in% c(1,2,3,5,6,7)) %>%
filter(URGENCY %in% c(1,2,3)) %>%
filter(PROXZONE_DISEASE %in% c(2,3,4,5,6,7,8,9)) %>%
filter(DISTZONE_DISEASE > PROXZONE_DISEASE)
```
## Data Cleaning
### Patient demographic and co-morbidities
- Comorbidity history variables: changed to Yes/No scale.
- `PREOP_CREAT`: merge `PREOP_CREAT` with retired `R_CR_PRESENT` (mg/dL)
```{r}
## ------------- variables cleaning, patient demographic and co-morbidities----------
TEVAR_PROC = TEVAR_PROC %>%
mutate(AGECAT = factor(AGECAT,levels = c(1,2,3,4,5,6,7),
labels = c('<50','<50','50-59','60-69','70-79','>79','>79'))) %>%
mutate(URGENCY=factor(URGENCY,levels = c(1,2,3),labels = c('Elective','Urgent','Emergent'))) %>%
mutate(GENDER=factor(GENDER,levels=c(1,2),labels=c('male','female'))) %>%
mutate(R_PREOP_AMBUL = factor(R_PREOP_AMBUL,levels = c(1,2,3,4),
labels=c("Amb","Amb w/ Assistance","Wheelchair","Bedridden"))) %>%
mutate(ETHNICITY = factor(ETHNICITY,levels=c(0,1),
labels = c('None Hispanic or Latino','Hispanic or Latino'))) %>%
mutate(RACE=factor(RACE,levels = c(5,3,2,1,4,6,7),
labels = c('White','Black or African American','Asian',
'American Indian or Alaskan Native',
'Native Hawaiian or other Pacific Islander','More than 1 race',
'Unknown/Other'))) %>%
mutate(TRANSFER=factor(TRANSFER,levels = c(0,1,2),labels = c('No','Hospital','Rehab Unit'))) %>%
mutate(PRIMARYINSURER=factor(PRIMARYINSURER,levels=c(1,2,3,4,5,6),
labels = c('Medicare','Medicaid','Commercial', 'Military/VA',
'Non US Insurance','Self Pay'))) %>%
mutate(LIVINGSTATUS=factor(LIVINGSTATUS,levels=c(1,2,3),
labels=c('Home','Nursing home','Homeless'))) %>%
mutate(PREOP_FUNCSTATUS=factor(PREOP_FUNCSTATUS,levels = c(0,1,2,3,4),
labels = c('Full','Light work','Self care','Assisted care',
'Bed bound'))) %>%
mutate(PRIOR_CVD = factor(PRIOR_CVD,levels =c(0,1,2,3),labels = c('No','Yes','Yes','Yes'))) %>%
mutate(PRIOR_CAD = factor(PRIOR_CAD,levels =c(0,1,2,3,4,5),
labels = c('No','Yes','Yes','Yes','Yes','Yes'))) %>%
mutate(PRIOR_CHF = factor(PRIOR_CHF,levels =c(0,1,2,3,4),
labels = c('No','Yes','Yes','Yes','Yes'))) %>%
mutate(COPD = factor(COPD,levels = c(0,1,2,3),labels = c('No','Yes','Yes','Yes'))) %>%
mutate(DIABETES=factor(DIABETES,levels = c(0,1,2,3),labels = c('No','Yes','Yes','Yes'))) %>%
mutate(PREOP_DIALYSIS=factor(PREOP_DIALYSIS,levels=c(0,1,2),labels=c('No','Yes','Yes'))) %>%
mutate(HTN=factor(HTN,levels = c(0,1,2,3),labels = c('No','Yes','Yes','Yes'))) %>%
mutate(PREOP_SMOKING=factor(PREOP_SMOKING,levels=c(0,1,2),labels=c('No','Yes','Yes'))) %>%
mutate(PRIOR_CABG = factor(PRIOR_CABG,levels = c(0,1,2),labels = c('No','Yes','Yes'))) %>%
mutate(PRIOR_PCI = factor(PRIOR_PCI,levels = c(0,1,2),labels = c('No','Yes','Yes'))) %>%
mutate(PRIOR_ANEURREP = factor(PRIOR_ANEURREP,levels =c(0,1,2,3,4,5),
labels = c('No','Yes','Yes','Yes','Yes','Yes'))) %>%
mutate(STRESS = factor(STRESS,levels =c(0,1,2,3,4),
labels = c('No','Yes','Yes','Yes','Yes'))) %>%
mutate(DC_ASA = factor(DC_ASA,levels = c(0,1,2,3),labels = c('No','Yes','No','No'))) %>%
mutate(DC_P2Y = factor(DC_P2Y,levels =c(0,1,2,3,4,5,6,7),
labels = c('No','Yes','Yes','Yes','Yes','Yes','No','No'))) %>%
mutate(DC_STATIN = factor(DC_STATIN,levels = c(0,1,2,3),labels = c('No','Yes','No','No')))
#---------- GFR ----------
TEVAR_PROC = TEVAR_PROC %>%
mutate(GFR_k = case_when(GENDER == 'male' ~ 0.9,
GENDER == 'female' ~ 0.7)) %>%
mutate(GFR_alpha = case_when(GENDER == 'male' ~ -0.302,
GENDER == 'female' ~ -0.241)) %>%
mutate(isfemale = case_when(GENDER == 'male' ~ 1,
GENDER == 'female' ~ 1.012))
TEVAR_PROC = TEVAR_PROC %>%
mutate(PREOP_min = with(TEVAR_PROC,pmin(PREOP_CREAT/GFR_k,1))) %>%
mutate(PREOP_max = with(TEVAR_PROC,pmax(PREOP_CREAT/GFR_k,1))) %>%
mutate(POSTOP_min = with(TEVAR_PROC,pmin(POSTOP_HIGHCREAT/GFR_k,1))) %>%
mutate(POSTOP_max = with(TEVAR_PROC,pmax(POSTOP_HIGHCREAT/GFR_k,1)))
TEVAR_PROC = TEVAR_PROC %>%
mutate(PREOP_GFR = 142*(PREOP_min^GFR_alpha)*(PREOP_max^(-1.2))*(0.9938^AGE)*(isfemale)) %>%
mutate(POSTOP_GFR = 142*(POSTOP_min^GFR_alpha)*(POSTOP_max^(-1.2))*(0.9938^AGE)*(isfemale))
TEVAR_PROC = TEVAR_PROC %>%
mutate(PREOP_GFR_CAT = case_when(PREOP_GFR > 89 ~ 1,
PREOP_GFR > 59 & PREOP_GFR < 89 ~ 2,
PREOP_GFR > 29 & PREOP_GFR < 59 ~ 3,
PREOP_GFR > 15 & PREOP_GFR < 29 ~ 4,
PREOP_GFR < 15 ~ 5)) %>%
mutate(POSTOP_GFR_CAT = case_when(POSTOP_GFR > 89 ~ 1,
POSTOP_GFR > 59 & POSTOP_GFR < 89 ~ 2,
POSTOP_GFR > 29 & POSTOP_GFR < 59 ~ 3,
POSTOP_GFR > 15 & POSTOP_GFR < 29 ~ 4,
POSTOP_GFR < 15 ~ 5))
TEVAR_PROC = TEVAR_PROC %>%
mutate(PREOP_GFR_CAT = factor(PREOP_GFR_CAT,levels = c(1,2,3,4,5),
labels = c("Normal or increased","Mildly decreased",
"Mildly to severely decreased","Severely decreased",
"End-stage renal disease"))) %>%
mutate(POSTOP_GFR_CAT = factor(POSTOP_GFR_CAT,levels = c(1,2,3,4,5),
labels = c("Normal or increased","Mildly decreased",
"Mildly to severely decreased","Severely decreased",
"End-stage renal disease")))
```
### Operative variables
- `PATHOLOGY`: merge levels PAU and IMH
- `URGENCY`: duplicate with `PRESENTATION` and doesn’t make sense, but leave it there.
- `extent`: type of TAAA based on certain criteria calculated by `PROXZONE_DISEASE` and `DISTZONE_DISEASE`.
- `ILIACDEV_END`: from merging `ILIACDEV_END_R`, `ILIACDEV_END_L`
- `ACCESS`: from merging `ACCESS_R`, `ACCESS_L`: Percutaneous if both are Percutaneous, Open o.w.
- `DEV_GTYPE`: merge `DEV1_GTYPE`, `DEV2_GTYPE`, `DEV3_GTYPE`: If one device is 'Custom' or 'Physician modified', classified to this instead of 'Standard'
#### Filter FBVAR patients based on having at least one branch, re-leveled as following.
- `lrenal`: re-leveled `BRANCH_LRENAL_TRT`, retired version `R_LT_RENAL` ignored.
- `rrenal`: re-leveled `BRANCH_RRENAL_TRT`, retired version `R_RT_RENAL` ignored.
- `sma`: re-leveled `BRANCH_SMA_TRT`, retired version `R_SMA` ignored.
- `celiac`: re-leveled `BRANCH_CELIAC_TRT`, retired version `R_CELIAC` ignored.
- `lsub`: re-leveled `BRANCH_LSUB_TRT`, retired version `R_L_SUBCLAV` ignored.
Current levels: 0 = None,1 = Purposely covered,2 = Unintentionally covered,3 = Occluded - coil,4 = Occluded - plug,5 = Occluded - open,6 = Stent,7 = Stent-graft,8 = Chimney,9 = Scallop,10 = Stented Scallop,11 = Fenestration,12 = Stented-fen,13 = Fen branch,14 = Side-arm branch,15 = Surgical bypass,16 = Thromboembolectomy,17 = Iliac Device
#### ignore some retired variables without current version
- `R_DISTATTZONE`: Distal Attachment Zone
- `R_GDPROXIMAL`: Graft Diameter Proximal
- `R_GRFTCONFIG`: Graft Configuration
- `R_PRATTZONE`: Prox. Attachment Zone
```{r}
## ------------- variables cleaning, operative variables----------
TEVAR_PROC = TEVAR_PROC %>% mutate(
PRESENTATION = factor(PRESENTATION,levels = c(0,1),labels = c('Asymptomatic','Symptomatic')),
extent = ifelse((PROXZONE_DISEASE %in% c(2,3)) & DISTZONE_DISEASE<6, 1,
ifelse((PROXZONE_DISEASE %in% c(2,3)) & DISTZONE_DISEASE>=8, 2,
ifelse((PROXZONE_DISEASE %in% c(4,5)) & DISTZONE_DISEASE>8, 3,
ifelse((PROXZONE_DISEASE <=7)& DISTZONE_DISEASE>=8,4,
ifelse((PROXZONE_DISEASE %in% c(4,5)) & DISTZONE_DISEASE<9, 5,
ifelse( PROXZONE_DISEASE<=8 & DISTZONE_DISEASE>=9, 6,NA))))))) %>%
mutate(extent = factor(extent,levels=c(1,2,3,4,5,6),
labels = c("Type 1 TAAA", "Type 2 TAAA" ,"Type 3 TAAA" ,"Type 4 TAAA" ,
"Type 5 TAAA" ,"Juxtarenal AAA"))) %>%
mutate(PROXZONE_DISEASE=factor(PROXZONE_DISEASE)) %>%
mutate(DISTZONE_DISEASE=
factor(DISTZONE_DISEASE, levels = c(0:15),
labels = c(0,1,2,3,4,5,6,7,8,9,'10R','10L','10B','11R','11L','11B')))
TEVAR_PROC = TEVAR_PROC %>%
mutate(PATHOLOGY=factor(PATHOLOGY,levels=c(1,2,3,5,6,7),
labels = c('Aneurysm','Dissection','Aneurysm from dissection',
'PAU/IMH','PAU/IMH','PAU/IMH'))) %>%
mutate(PRIOR_AORSURG=factor(PRIOR_AORSURG,levels=c(0,1,2,3,4),
labels=c('None','Open','Endo','Both','Other'))) %>%
mutate(PATHOLOGY_ANEURYSM_TYPE=
factor(PATHOLOGY_ANEURYSM_TYPE,levels = c(1,2,3,4,5),
labels = c('Degenerative, fusiform','Degenerative, saccular','Anastomotic',
'Prior trauma','Intercostal or visceral patch'))) %>%
mutate(PATHOLOGY_DISSECT_TYPE=
factor(PATHOLOGY_DISSECT_TYPE,levels = c(1,2),
labels = c('Acute, <= 30 days','Chronic, >30 days'))) %>%
mutate(GENHIST = factor(GENHIST,levels = c(0,1,2,3,4,5),
labels = c('None','Marfans','Ehlers-Danlos','Loeys-Dietz',
'Non-specific','Other'))) %>%
mutate(ANESTHESIA=factor(ANESTHESIA,levels = c(1,2,3),labels = c('Local','Regional','General')))%>%
mutate(IVUSTEE=factor(IVUSTEE,levels = c(0:5),labels = c('No','IVUS','TEE','Both','No','IVUS')))%>%
## merge ACCESS_L and ACCESS_R
mutate(ACCESS = ifelse(ACCESS_L == 1 & ACCESS_R ==1, 'Percutaneous','Open')) %>%
mutate(ACCESS=factor(ACCESS)) %>%
mutate(ARMNECK_ACCESS=factor(ARMNECK_ACCESS,levels =c(0,1,2,3),
labels = c('No','Yes','Yes','Yes')))%>%
mutate(AORDEV_NUM=factor(AORDEV_NUM))%>%
mutate(AORDEV_CMOD=factor(AORDEV_CMOD,levels=c(0,1),labels=c('No','Yes'))) %>%
mutate(STAGEDAORTRT=factor(STAGEDAORTRT,levels=c(0,1),labels=c('No','Yes'))) %>%
## DEV_GTYPE: merge DEV1_GTYPE, DEV2_GTYPE, DEV3_GTYPE
mutate(DEV_GTYPE = case_when(DEV1_GTYPE==2|DEV2_GTYPE==2|DEV3_GTYPE==2 ~ 'Custom',
DEV1_GTYPE==3|DEV2_GTYPE==3|DEV3_GTYPE==3 ~ 'Physician modified',
TRUE ~ 'Standard')) %>%
mutate(DEV1_GTYPE=factor(DEV1_GTYPE,levels=c(1,2,3),
labels=c('Standard','Custom','Physician modified'))) %>%
mutate(DEV2_GTYPE=factor(DEV2_GTYPE,levels=c(1,2,3),
labels=c('Standard','Custom','Physician modified'))) %>%
mutate(DEV3_GTYPE=factor(DEV3_GTYPE,levels=c(1,2,3),
labels=c('Standard','Custom','Physician modified')))
TEVAR_PROC = TEVAR_PROC %>%
mutate(ILIACDEV_END_R= factor(ILIACDEV_END_R, levels = c(0,1,2,3),
labels = c('None','Common',
'External,Intended','External, Unintended'))) %>%
mutate(ILIACDEV_END_L= factor(ILIACDEV_END_L, levels = c(0,1,2,3),
labels = c('None','Common',
'External,Intended','External, Unintended'))) %>%
mutate(BRANCH_STAGED=factor(BRANCH_STAGED,levels=c(0,1),labels=c('No','Yes'))) %>%
mutate(BRANCH_LSUB=factor(BRANCH_LSUB,levels=c(0,1),labels=c('No','Yes'))) %>%
mutate(BRANCH_CELIAC=factor(BRANCH_CELIAC,levels=c(0,1),labels=c('No','Yes'))) %>%
mutate(BRANCH_SMA=factor(BRANCH_SMA,levels=c(0,1),labels=c('No','Yes'))) %>%
mutate(BRANCH_RRENAL=factor(BRANCH_RRENAL,levels=c(0,1),labels=c('No','Yes'))) %>%
mutate(BRANCH_LRENAL=factor(BRANCH_LRENAL,levels=c(0,1),labels=c('No','Yes'))) %>%
mutate(BRANCH_INNO_POST=factor(BRANCH_INNO_POST,levels=c(1,2,3),
labels=c('Patent','Stenosis/Partial Coverage > 50%','Occluded'))) %>%
mutate(BRANCH_LSUB_VERTPAT=
factor(BRANCH_LSUB_VERTPAT,levels=c(1:7),
labels=c('Patent bilat','Patent bilat, L dominant','Patent bilat, R dominant',
'Occluded L, patent R','Occluded R, patent L','Occluded bilat',
'Not imaged'))) %>%
mutate(ANESTHESIA_GEN_TIMEEXT=factor(ANESTHESIA_GEN_TIMEEXT,levels=c(1,2,4,5),
labels=c('In OR','<12 hrs','12-24 hrs','>24 hrs'))) %>%
mutate(POSTOP_SPINALDRAIN=factor(POSTOP_SPINALDRAIN,levels=c(0,1,2,3),
labels=c('No','Yes','Yes','Yes')))
## ------------- BRANCH_TRT filtering----------
TEVAR_PROC<-TEVAR_PROC %>%
mutate(lrenal = ifelse(BRANCH_LRENAL_TRT %in% c(0,6,7), 0,
ifelse(BRANCH_LRENAL_TRT %in% c(9,10,11,12,13,14), 1,
ifelse(BRANCH_LRENAL_TRT %in% c(1,2,3,4), 2,
ifelse(BRANCH_LRENAL_TRT == 8, 3,NA)))),
rrenal = ifelse(BRANCH_RRENAL_TRT %in% c(0,6,7), 0,
ifelse(BRANCH_LRENAL_TRT %in% c(9,10,11,12,13,14), 1,
ifelse(BRANCH_LRENAL_TRT %in% c(1,2,3,4), 2,
ifelse(BRANCH_LRENAL_TRT == 8, 3,NA)))),
sma = ifelse(BRANCH_SMA_TRT %in% c(0,6,7), 0,
ifelse(BRANCH_SMA_TRT %in% c(9,10,11,12,13,14), 1,
ifelse(BRANCH_SMA_TRT %in% c(1,2,3,4), 2,
ifelse(BRANCH_SMA_TRT == 8,3,NA)))),
celiac = ifelse(BRANCH_CELIAC_TRT %in% c(0,6,7), 0,
ifelse(BRANCH_CELIAC_TRT %in% c(9,10,11,12,13,14), 1,
ifelse(BRANCH_CELIAC_TRT %in% c(1,2,3,4), 2,
ifelse(BRANCH_CELIAC_TRT == 8,3,NA)))),
lsub = ifelse(BRANCH_LSUB_TRT %in% c(0,6,7), 0,
ifelse(BRANCH_LSUB_TRT %in% c(9,10,11,12,13,14), 1,
ifelse(BRANCH_LSUB_TRT %in% c(1,2,3,4), 2,
ifelse(BRANCH_LSUB_TRT == 8,3,NA)))))
## ------------- FBVAR filtering----------
TEVAR_PROC = TEVAR_PROC %>%
filter(lrenal == 1 | rrenal== 1 | sma== 1 | celiac== 1)
## ------------- vessel treatment status ----------
TEVAR_PROC = TEVAR_PROC %>%
mutate(TREATED_LRENAL=case_when(lrenal==1|lrenal==3 ~ TRUE, TRUE~FALSE)) %>%
mutate(TREATED_RRENAL=case_when(rrenal==1|rrenal==3 ~ TRUE, TRUE~FALSE)) %>%
mutate(TREATED_SMA=case_when(sma==1|sma==3 ~ TRUE, TRUE~FALSE)) %>%
mutate(TREATED_CELIAC=case_when(celiac==1|celiac==3 ~ TRUE, TRUE~FALSE)) %>%
mutate(TREATED_LSUB=case_when(lsub==1|lsub==3 ~ TRUE, TRUE~FALSE)) %>%
##### Number of treated branches: 4,3,2,1
mutate(NUM_TREATED_BRANCHES =
TREATED_LRENAL+TREATED_RRENAL+TREATED_SMA+TREATED_CELIAC) %>%
mutate(NUM_TREATED_BRANCHES=factor(NUM_TREATED_BRANCHES)) %>%
##### Number of treated renals: 2,1,0
mutate(NUM_TREATED_RENALS = TREATED_LRENAL+TREATED_RRENAL) %>%
mutate(NUM_TREATED_RENALS=factor(NUM_TREATED_RENALS)) %>%
##### RENAL occluded/covered: yes or no
mutate(OCCLUDED_RENAL = case_when(lrenal == 2|rrenal == 2 ~ TRUE,TRUE ~ FALSE)) %>%
##### SMA occluded/covered: yes or no
mutate(OCCLUDED_SMA = case_when(sma == 2 ~ TRUE,TRUE ~ FALSE)) %>%
##### CELIAC occluded/covered: yes or no
mutate(OCCLUDED_CELIAC = case_when(celiac == 2 ~ TRUE,TRUE ~ FALSE))
## ------------- set BRANCHES labels----------
TEVAR_PROC = TEVAR_PROC %>%
mutate(lrenal=factor(lrenal,levels=c(0,1,2,3),
labels=c('None','Scallop/Fen/Branch/Chimney','Occluded/Covered','Scallop/Fen/Branch/Chimney'))) %>%
mutate(rrenal=factor(rrenal,levels=c(0,1,2,3),
labels=c('None','Scallop/Fen/Branch/Chimney','Occluded/Covered','Scallop/Fen/Branch/Chimney'))) %>%
mutate(sma=factor(sma,levels=c(0,1,2,3),
labels=c('None','Scallop/Fen/Branch/Chimney','Occluded/Covered','Scallop/Fen/Branch/Chimney'))) %>%
mutate(celiac=factor(celiac,levels=c(0,1,2,3),
labels=c('None','Scallop/Fen/Branch/Chimney','Occluded/Covered','Scallop/Fen/Branch/Chimney'))) %>%
mutate(lsub=factor(lsub,levels=c(0,1,2,3),
labels=c('None','Scallop/Fen/Branch/Chimney','Occluded/Covered','Scallop/Fen/Branch/Chimney')))
```
### Outcomes
- `POSTOP_LOS`: changed into binary, more than a week or not.
- Create `POSTOP_AH`: Combine `POSTOP_AH`, `POSTOP_MI`,`POSTOP_DYSRHYTHMIA` for post-procedure abnormal heart disease
- Create `BRANCH_POST`: `BRANCH_XXX_POST` changed to Yes/No scale. Then combine `BRANCH_LSUB_POST`, `BRANCH_CELIAC_POST`, `BRANCH_SMA_POST`, `BRANCH_RRENAL_POST`, `BRANCH_LRENAL_POST`, `BRANCH_RCOMILI_POST`, `BRANCH_LCOMILI_POST`
#### update some variables with current version
- `R_ENDOLEAK_AT_COMPLETION` => `LEAKATCOM_XXX` variables. Only use `LEAKATCOMP_NONE`. Ignore others or have a brief look
- `R_POSTOP_HEMATOMA` => `ACCESS_HEMATOMA_R`, `ACCESS_HEMATOMA_L`; `R_POSTOP_SITEOCC` => `ACCESS_OCCLUSION_R`, `ACCESS_OCCLUSION_L`. Merge hematoma and occlusion, create new variable: `ACCESS_COMPLICATION`
- `R_POSTOP_SSI` => `ACCESS_INFECTION_R`, `ACCESS_INFECTION_L` Merge left and right, create new variable: `ACCESS_INFECTION`
#### ignore some retired version variables, only use the current version
- `R_POSTOP_BOWELISCH` <= `POSTOP_INTISCH`: Bowel Ischemia
- `R_LE_ISCH` <= `POSTOP_LEGEMBO`: LE Ischemia
- `R_POSTOP_RENAL` <= `POSTOP_DIALYSIS`: change of renal function
#### record treatment status of the vessels
- `NUM_TREATED_BRANCHES`: number of treated branches: 4,3,2,1
- `NUM_TREATED_RENALS`: number of treated renals: 2,1,0
- `OCCLUDED_RENAL`,`OCCLUDED_SMA`,`OCCLUDED_CELIAC`,`OCCLUDED_LSUB`: whether this vessel is occluded or covered.
```{r}
## ------------- variables cleaning, outcomes----------
TEVAR_PROC = TEVAR_PROC %>%
mutate(DEAD=factor(DEAD,levels=c(0,1),labels = c(FALSE,TRUE))) %>%
mutate(AORDEV_TECHSUCC=factor(AORDEV_TECHSUCC,levels=c(0,1),labels=c('No','Yes'))) %>%
mutate(CONVTOOPEN=factor(CONVTOOPEN,levels=c(0,1),labels=c('No','Yes'))) %>%
mutate(LEAKATCOMP_NONE=factor(LEAKATCOMP_NONE,levels=c(0,1),labels = c('No','Yes'))) %>%
mutate(POSTOP_VASO=factor(POSTOP_VASO,levels=c(0,1,2,3),labels=c('No','Yes','Yes','Yes'))) %>%
mutate(POSTOP_COMPLICATIONS=factor(POSTOP_COMPLICATIONS,levels=c(0,1),labels=c('No','Yes'))) %>%
# ACCESS_COMPLICATION
mutate (ACCESS_COMPLICATION=
case_when(ACCESS_HEMATOMA_R!=0 | ACCESS_HEMATOMA_L!=0 |
ACCESS_OCCLUSION_R !=0 | ACCESS_OCCLUSION_L !=0 ~ "Yes",
ACCESS_HEMATOMA_R==0 & ACCESS_HEMATOMA_L==0 &
ACCESS_OCCLUSION_R ==0 & ACCESS_OCCLUSION_L ==0 ~ "No")) %>%
## POSTOP_AH: merge POSTOP_MI,POSTOP_DYSRHYTHMIA,POSTOP_CHF
mutate(POSTOP_MI=factor(POSTOP_MI,levels=c(0,1,2),labels=c('No','Yes','Yes'))) %>%
mutate(POSTOP_DYSRHYTHMIA=factor(POSTOP_DYSRHYTHMIA,levels=c(0,1),labels=c('No','Yes'))) %>%
mutate(POSTOP_CHF=factor(POSTOP_CHF,levels=c(0,1),labels=c('No','Yes'))) %>%
mutate(POSTOP_AH=case_when(
POSTOP_MI=='Yes'|POSTOP_DYSRHYTHMIA=='Yes'|POSTOP_CHF=='Yes' ~ "Yes",
POSTOP_MI=='No'|POSTOP_DYSRHYTHMIA=='No'|POSTOP_CHF=='No' ~ "No")) %>%
mutate(POSTOP_CEREBROSX = case_when(POSTOP_CEREBROSX >0 ~ 'Yes',
POSTOP_CEREBROSX ==0 ~ 'No')) %>%
mutate(POSTOP_RESPIRATORY=factor(POSTOP_RESPIRATORY,levels = c(0:3),
labels = c('No','Yes','Yes','Yes'))) %>%
mutate(POSTOP_DIALYSIS=factor(POSTOP_DIALYSIS,levels = c(0:2),
labels = c('No','Yes','Yes'))) %>%
mutate(POSTOP_ARMEMBO=factor(POSTOP_ARMEMBO,levels = c(0:5),
labels = c('No','Yes','Yes','Yes','Yes','Yes'))) %>%
mutate(POSTOP_INTISCH=factor(POSTOP_INTISCH,levels = c(0:4),
labels = c('No','Yes','Yes','Yes','Yes'))) %>%
mutate(POSTOP_LEGEMBO=factor(POSTOP_LEGEMBO,levels = c(0:5),
labels = c('No','Yes','Yes','Yes','Yes','Yes'))) %>%
mutate(POSTOP_LEGCOMPART=factor(POSTOP_LEGCOMPART,levels = c(0:4),
labels = c('No','Yes','Yes','Yes','Yes'))) %>%
mutate(POSTOP_RENALISCH=factor(POSTOP_RENALISCH,levels = c(0:3),
labels = c('No','Yes','Yes','Yes'))) %>%
mutate(POSTOP_SPINAL_ISCHEMIA=factor(POSTOP_SPINAL_ISCHEMIA,levels = c(0:2),
labels = c('No','Yes','Yes'))) %>%
## RETX_R_RTOR: merge RETX, R_RTOR
mutate(RETX=factor(RETX,levels = c(0:2),labels = c('No','Yes','Yes'))) %>%
mutate(R_RTOR=factor(R_RTOR,levels = c(0:5),labels = c('No','Yes','Yes','Yes','Yes','Yes'))) %>%
mutate (RETX_R_RTOR=case_when(RETX=="Yes"|R_RTOR=="Yes" ~ "Yes",
RETX=="No" & R_RTOR=="No" ~ "No",
RETX=="No"&is.na(R_RTOR) ~ "No",
R_RTOR=="No"&is.na(RETX) ~ "No",
is.na(R_RTOR) & is.na(RETX) ~ NA_character_)) %>%
mutate(DC_STATUS=factor(DC_STATUS,levels = c(1:6),
labels = c('Home','Rehab Unit','Nursing Home',
'Dead','Other Hospital','Homeless'))) %>%
## BRANCH_XXX_POST
mutate(BRANCH_LSUB_POST=factor(BRANCH_LSUB_POST,levels=c(1,2,3),
labels=c('No','Yes','Yes'))) %>%
mutate(BRANCH_CELIAC_POST=factor(BRANCH_CELIAC_POST,levels=c(1,2,3),
labels=c('No','Yes','Yes'))) %>%
mutate(BRANCH_SMA_POST=factor(BRANCH_SMA_POST,levels=c(1,2,3),
labels=c('No','Yes','Yes'))) %>%
mutate(BRANCH_RRENAL_POST=factor(BRANCH_RRENAL_POST,levels=c(1,2,3),
labels=c('No','Yes','Yes'))) %>%
mutate(BRANCH_LRENAL_POST=factor(BRANCH_LRENAL_POST,levels=c(1,2,3),
labels=c('No','Yes','Yes'))) %>%
mutate(BRANCH_RCOMILI_POST=factor(BRANCH_RCOMILI_POST,levels=c(1,2,3),
labels=c('No','Yes','Yes'))) %>%
mutate(BRANCH_LCOMILI_POST=factor(BRANCH_LCOMILI_POST,levels=c(1,2,3),
labels=c('No','Yes','Yes'))) %>%
## BRANCH_POST: merge BRANCH_XXX_POST
mutate(BRANCH_POST=case_when(BRANCH_LSUB_POST=="Yes"|BRANCH_CELIAC_POST=="Yes"|BRANCH_SMA_POST=="Yes"|BRANCH_RRENAL_POST=="Yes"|BRANCH_LRENAL_POST=="Yes"|BRANCH_RCOMILI_POST=="Yes"|BRANCH_LCOMILI_POST =="Yes" ~ "Yes",BRANCH_LSUB_POST=="No"|BRANCH_CELIAC_POST=="No"|BRANCH_SMA_POST=="No"|BRANCH_RRENAL_POST=="No"|BRANCH_LRENAL_POST=="No"|BRANCH_RCOMILI_POST=="No"|BRANCH_LCOMILI_POST=="No"~ "No"))
```
### Others
Variables we cleaned but are not needed after discussion goes here.
```{r}
# TEVAR = TEVAR %>%
# mutate(R_PREOP_AMBUL = factor(R_PREOP_AMBUL,levels = c(1,2,3,4),
# labels=c("Amb","Amb w/ Assistance","Wheelchair","Bedridden"))) %>%
# mutate(SURGYEAR=factor(SURGYEAR)) %>%
# mutate(PRIOR_AORSURG_OPENLOC1=factor(PRIOR_AORSURG_OPENLOC1,
# levels=c(0,1),labels=c('No','Yes'))) %>%
# mutate(PRIOR_AORSURG_OPENLOC2=factor(PRIOR_AORSURG_OPENLOC2,
# levels=c(0,1),labels=c('No','Yes'))) %>%
# mutate(PRIOR_AORSURG_OPENLOC3=factor(PRIOR_AORSURG_OPENLOC3,
# levels=c(0,1),labels=c('No','Yes'))) %>%
# mutate(PRIOR_AORSURG_OPENLOC4=factor(PRIOR_AORSURG_OPENLOC4,
# levels=c(0,1),labels=c('No','Yes'))) %>%
# mutate(PRIOR_AORSURG_ENDOLOC1=factor(PRIOR_AORSURG_ENDOLOC1,
# levels=c(0,1),labels=c('No','Yes'))) %>%
# mutate(PRIOR_AORSURG_ENDOLOC2=factor(PRIOR_AORSURG_ENDOLOC2,
# levels=c(0,1),labels=c('No','Yes'))) %>%
# mutate(PRIOR_AORSURG_ENDOLOC3=factor(PRIOR_AORSURG_ENDOLOC3,
# levels=c(0,1),labels=c('No','Yes'))) %>%
# mutate(PRIOR_AORSURG_ENDOLOC4=factor(PRIOR_AORSURG_ENDOLOC4,
# levels=c(0,1),labels=c('No','Yes'))) %>%
# mutate(ARMNECK_ACCESS_LOC=factor(ARMNECK_ACCESS_LOC,levels =c(1:7),
# labels = c('Right arm','Left arm','Right axillary',
# 'Left axillary','Right carotid',
# 'Left carotid','Multiple'))) %>%
# ## retired branch variables
# mutate(R_CELIAC=factor(R_CELIAC,levels=c(0:9),
# labels=c('Patent, no intervention','Chronically Occluded',
# 'Purposely Occluded','De-branch','Stent Only','Chimney',
# 'Fen/scallop Only','Stented-fen',
# 'Fenestrated Stentgraft Branch (Branched TEVAR)',
# 'Side-arm Stent-graft Branch'))) %>%
# mutate(R_LT_RENAL=factor(R_LT_RENAL,levels=c(0:9),
# labels=c('Patent, no intervention','Chronically Occluded',
# 'Purposely Occluded','De-branch','Stent Only','Chimney',
# 'Fen/scallop Only','Stented-fen',
# 'Fenestrated Stentgraft Branch (Branched TEVAR)',
# 'Side-arm Stent-graft Branch'))) %>%
# mutate(R_RT_RENAL=factor(R_RT_RENAL,levels=c(0:9),
# labels=c('Patent, no intervention','Chronically Occluded',
# 'Purposely Occluded','De-branch','Stent Only','Chimney',
# 'Fen/scallop Only','Stented-fen',
# 'Fenestrated Stentgraft Branch (Branched TEVAR)',
# 'Side-arm Stent-graft Branch'))) %>%
# mutate(R_SMA=factor(R_SMA,levels=c(0:9),
# labels=c('Patent, no intervention','Chronically Occluded',
# 'Purposely Occluded','De-branch','Stent Only','Chimney',
# 'Fen/scallop Only','Stented-fen',
# 'Fenestrated Stentgraft Branch (Branched TEVAR)',
# 'Side-arm Stent-graft Branch')))
#
# ## ------------- DEV_PROXZONE and DEV_DISTZONE filtering----------
# TEVAR<-TEVAR %>%
# mutate(distal_seal= DEV1_DISTZONE,prox_seal= DEV1_PROXZONE)
#
# for (i in 1:nrow(TEVAR)){
# if ((!(is.na(TEVAR$DEV2_DISTZONE[i])) && (!is.na(TEVAR$DEV2_DISTZONE[i]>TEVAR$DEV1_DISTZONE[i]))&&
# (TEVAR$DEV2_DISTZONE[i]>TEVAR$DEV1_DISTZONE[i]))) {
# TEVAR$distal_seal[i] = TEVAR$DEV2_DISTZONE[i]}
# else if((is.na(TEVAR$DEV1_DISTZONE[i])) && (!(is.na(TEVAR$DEV2_DISTZONE[i])))){
# TEVAR$distal_seal[i] = TEVAR$DEV2_DISTZONE[i]}
# if ((!(is.na(TEVAR$DEV3_DISTZONE[i])) && (!is.na(TEVAR$DEV3_DISTZONE[i]>TEVAR$DEV2_DISTZONE[i]))&&
# (TEVAR$DEV3_DISTZONE[i]>TEVAR$DEV2_DISTZONE[i]))) {
# TEVAR$distal_seal[i] = TEVAR$DEV3_DISTZONE[i]}
# if ((!(is.na(TEVAR$DEV4_DISTZONE[i])) && (!is.na(TEVAR$DEV4_DISTZONE[i]>TEVAR$DEV3_DISTZONE[i]))&&
# (TEVAR$DEV4_DISTZONE[i]>TEVAR$DEV3_DISTZONE[i]))) {
# TEVAR$distal_seal[i] = TEVAR$DEV4_DISTZONE[i]}
# if ((!(is.na(TEVAR$DEV5_DISTZONE[i])) && (!is.na(TEVAR$DEV5_DISTZONE[i]>TEVAR$DEV4_DISTZONE[i]))&&
# (TEVAR$DEV5_DISTZONE[i]>TEVAR$DEV4_DISTZONE[i]))) {
# TEVAR$distal_seal[i] = TEVAR$DEV5_DISTZONE[i]}
# if ((!(is.na(TEVAR$DEV6_DISTZONE[i])) && (!is.na(TEVAR$DEV6_DISTZONE[i]>TEVAR$DEV5_DISTZONE[i]))&&
# (TEVAR$DEV6_DISTZONE[i]>TEVAR$DEV5_DISTZONE[i]))) {
# TEVAR$distal_seal[i] = TEVAR$DEV6_DISTZONE[i]}
# }
#
# for (i in 1:nrow(TEVAR)){
# if ((!(is.na(TEVAR$DEV2_PROXZONE[i])) && (!is.na(TEVAR$DEV2_PROXZONE[i]<TEVAR$DEV1_PROXZONE[i]))&&
# (TEVAR$DEV2_PROXZONE[i]<TEVAR$DEV1_PROXZONE[i]))) {
# TEVAR$prox_seal[i] = TEVAR$DEV2_PROXZONE[i]}
# else if((is.na(TEVAR$DEV1_PROXZONE[i])) && (!(is.na(TEVAR$DEV2_PROXZONE[i])))){
# TEVAR$prox_seal[i] = TEVAR$DEV2_PROXZONE[i]}
# if ((!(is.na(TEVAR$DEV3_PROXZONE[i])) && (!is.na(TEVAR$DEV3_PROXZONE[i]<TEVAR$DEV2_PROXZONE[i]))&&
# (TEVAR$DEV3_PROXZONE[i]<TEVAR$DEV2_PROXZONE[i]))) {
# TEVAR$prox_seal[i] = TEVAR$DEV3_PROXZONE[i]}
# if ((!(is.na(TEVAR$DEV4_PROXZONE[i])) && (!is.na(TEVAR$DEV4_PROXZONE[i]<TEVAR$DEV3_PROXZONE[i]))&&
# (TEVAR$DEV4_PROXZONE[i]<TEVAR$DEV3_PROXZONE[i]))) {
# TEVAR$prox_seal[i] = TEVAR$DEV4_PROXZONE[i]}
# if ((!(is.na(TEVAR$DEV5_PROXZONE[i])) && (!is.na(TEVAR$DEV5_PROXZONE[i]<TEVAR$DEV4_PROXZONE[i]))&&
# (TEVAR$DEV5_PROXZONE[i]<TEVAR$DEV4_PROXZONE[i]))) {
# TEVAR$prox_seal[i] = TEVAR$DEV5_PROXZONE[i]}
# if ((!(is.na(TEVAR$DEV6_PROXZONE[i])) && (!is.na(TEVAR$DEV6_PROXZONE[i]<TEVAR$DEV5_PROXZONE[i]))&&
# (TEVAR$DEV6_PROXZONE[i]<TEVAR$DEV5_PROXZONE[i]))) {
# TEVAR$prox_seal[i] = TEVAR$DEV6_PROXZONE[i]}
# }
#
```
### Volume variables
```{r}
## ------------- variables cleaning, volume variables----------
TEVAR_PROC = TEVAR_PROC %>%
mutate(REGIONID=factor(REGIONID)) %>%
mutate(CENTERID=factor(CENTERID)) %>%
mutate(PHYSICIANID=factor(PHYSICIANID))
```
## Duplicate variables
We checked the duplicate `PATIENTID` in the `PROC` dataset.These patients are transfered a few days or a few months followed the first procedure. We decided to exclude these abnormal data points.
```{r}
frequency = (count(TEVAR_PROC$PATIENTID))
view(frequency)
#
# duplicate = TEVAR_PROC %>%
# filter(PATIENTID==296651|PATIENTID==318785|PATIENTID==374667|PATIENTID==481088 |
# PATIENTID==517721|PATIENTID==616510|PATIENTID==686479|PATIENTID==686759 ) %>%
# select(PATIENTID,PROC_SURVIVALDAYS,SURGYEAR,SURGMONTH,TRANSFER,POSTOP_LOS)
# duplicate[order(duplicate$PATIENTID),] %>% knitr::kable()
TEVAR_PROC = TEVAR_PROC %>%
filter(PATIENTID!=296651&PATIENTID!=318785&PATIENTID!=374667&PATIENTID!=481088 &
PATIENTID!=517721&PATIENTID!=616510&PATIENTID!=686479&PATIENTID!=686759 &
PATIENTID!=671047&PATIENTID!=721266&PATIENTID!=723290&PATIENTID!=758461 &
PATIENTID!=784327&PATIENTID!=956326 )
```
## Store a new dataset for further study
Select the variable related to our study. Give them labels for better-looking tables. Finally store the new dataset as a seperate csv file, so that we could use the cleaned dataset in the future modeling.
```{r}
## -------------variables selection----------
TEVAR_PROC = TEVAR_PROC %>% select(
SURGMONTH,SURGYEAR, PRIMPROCID,
PRESENTATION,
# Patient demographic and co-morbidities
AGE, AGECAT, GENDER, ETHNICITY, RACE, TRANSFER, PRIMARYINSURER, LIVINGSTATUS, PREOP_FUNCSTATUS, PRIOR_CVD, PRIOR_CAD, PRIOR_CHF, COPD, DIABETES, PREOP_DIALYSIS, HTN, PREOP_SMOKING, PRIOR_CABG, PRIOR_PCI, PRIOR_ANEURREP, STRESS, PREOP_CREAT,PREOP_GFR,PREOP_GFR_CAT, DC_ASA,DC_P2Y, DC_STATIN,
# Operative Variables
PRIOR_AORSURG, PATHOLOGY, PREOP_MAXAAADIA, URGENCY, PATHOLOGY_ANEURYSM_TYPE, PATHOLOGY_DISSECT_TYPE, PROXZONE_DISEASE, GENHIST, DISTZONE_DISEASE, extent, ANESTHESIA, CONTRAST, EBL, FLUOROTIME, INTRAOP_PRBC,TOTALPROCTIME, IVUSTEE, ACCESS, ARMNECK_ACCESS, AORDEV_NUM, AORDEV_CMOD, DEV_GTYPE, ILIACDEV_END_R, ILIACDEV_END_L, BRANCH_STAGED, BRANCH_LSUB, BRANCH_CELIAC, BRANCH_SMA, BRANCH_RRENAL, BRANCH_LRENAL, ANESTHESIA_GEN_TIMEEXT, POSTOP_SPINALDRAIN, lrenal, rrenal, sma, celiac, lsub, NUM_TREATED_BRANCHES,NUM_TREATED_RENALS,OCCLUDED_RENAL,OCCLUDED_SMA,OCCLUDED_CELIAC,
# Outcomes
# LTF_NUM_REINT
DEAD, PROC_SURVIVALDAYS,TOTAL_LOS, POSTOP_LOS, AORDEV_TECHSUCC, CONVTOOPEN, LEAKATCOMP_NONE, ICUSTAY, POSTOP_PRBC, POSTOP_VASO, POSTOP_HIGHCREAT,POSTOP_GFR, POSTOP_GFR_CAT,POSTOP_COMPLICATIONS, ACCESS_COMPLICATION, POSTOP_AH, POSTOP_CEREBROSX, POSTOP_RESPIRATORY, POSTOP_DIALYSIS, POSTOP_ARMEMBO, POSTOP_LEGEMBO, POSTOP_LEGCOMPART, POSTOP_INTISCH, POSTOP_RENALISCH, POSTOP_SPINAL_ISCHEMIA, RETX_R_RTOR, DC_STATUS, BRANCH_POST,
# Volume variables,
REGIONID,CENTERID,PHYSICIANID,PATIENTID)
## ------------- store as new dataset 'TEVAR_PROC' to ensure easier access for modelling----------
write.csv(TEVAR_PROC,path_jenn[5])
#write.csv(TEVAR_PROC,path_lily[5])
```