Univariate subdistribution hazard model hrs+age_admission+sex+White+hispanic_race+study_site+pressor+initial_rrt+MELD_Na_baseline+liver_transplant_listed

tidycmprsk::crr(Surv(time_90days,status_90days) ~ age_admission, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
age_admission 374 1.00 0.99, 1.01 0.8
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ sex, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
sex 374
    1 — —
    2 0.91 0.70, 1.18 0.5
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ White, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
White 374
    0 — —
    1 1.08 0.80, 1.46 0.6
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ hispanic_race, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
hispanic_race 374
    0 — —
    1 0.69 0.44, 1.08 0.10
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ hrs, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
hrs 374
    Non-HRS — —
    HRS 0.72 0.50, 1.04 0.077
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ study_site, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 36 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
study_site 338
    High_volume_RRT — —
    Low_volume_RRT 1.03 0.78, 1.37 0.8
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ MELD_Na_baseline, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 3 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
MELD_Na_baseline 371 1.02 1.01, 1.04 0.004
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ pressor, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 2 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
pressor 372
    0 — —
    1 1.94 1.42, 2.65 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ initial_rrt, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 2 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
initial_rrt 372
    1 — —
    2 2.58 1.86, 3.57 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ liver_transplant_listed, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
liver_transplant_listed 374
    0 — —
    1 0.23 0.15, 0.34 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval

Model 1 hrs+age_admission+sex+White+hispanic_race+study_site+pressor+initial_rrt+MELD_Na_baseline+liver_transplant_listed

m_cmprsk_model <- tidycmprsk::crr(Surv(time=time_90days,status_90days) ~ hrs+age_admission+sex+White+hispanic_race+study_site+pressor+initial_rrt+MELD_Na_baseline+liver_transplant_listed,data=master_rrt)
## 42 cases omitted due to missing values
m_cmprsk_model %>%  tbl_regression(exponentiate = TRUE,
                      
                       pvalue_fun = ~style_pvalue(.x, digits = 3)) %>% bold_p() %>% # bold p-values under a given threshold (default 0.05)
  bold_labels()%>% 
  modify_spanning_header(
    c(estimate, ci, p.value) ~  
      "**Model 1 cmprsk regression**")%>%
  add_n()
Characteristic N Model 1 cmprsk regression
HR1 95% CI1 p-value
hrs 332
    Non-HRS — —
    HRS 1.36 0.95, 1.94 0.089
age_admission 332 1.01 1.00, 1.02 0.150
sex 332
    1 — —
    2 0.94 0.71, 1.25 0.670
White 332
    0 — —
    1 1.41 1.01, 1.96 0.042
hispanic_race 332
    0 — —
    1 0.69 0.44, 1.06 0.092
study_site 332
    High_volume_RRT — —
    Low_volume_RRT 1.24 0.91, 1.69 0.170
pressor 332
    0 — —
    1 1.62 1.15, 2.28 0.006
initial_rrt 332
    1 — —
    2 2.65 1.87, 3.77 <0.001
MELD_Na_baseline 332 1.04 1.02, 1.05 <0.001
liver_transplant_listed 332
    0 — —
    1 0.19 0.12, 0.31 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval

Model 2 Univariate subdistribution hazard model hrs+age_admission+sex+White+hispanic_race+study_site+pressor+initial_rrt+MELD_Na_baseline+liver_transplant_listed+ hrs*study_site

tidycmprsk::crr(Surv(time_90days,status_90days) ~ age_admission, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
age_admission 374 1.00 0.99, 1.01 0.8
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ sex, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
sex 374
    1 — —
    2 0.91 0.70, 1.18 0.5
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ White, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
White 374
    0 — —
    1 1.08 0.80, 1.46 0.6
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ hispanic_race, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
hispanic_race 374
    0 — —
    1 0.69 0.44, 1.08 0.10
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ hrs, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
hrs 374
    Non-HRS — —
    HRS 0.72 0.50, 1.04 0.077
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ study_site, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 36 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
study_site 338
    High_volume_RRT — —
    Low_volume_RRT 1.03 0.78, 1.37 0.8
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ MELD_Na_baseline, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 3 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
MELD_Na_baseline 371 1.02 1.01, 1.04 0.004
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ pressor, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 2 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
pressor 372
    0 — —
    1 1.94 1.42, 2.65 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ initial_rrt, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 2 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
initial_rrt 372
    1 — —
    2 2.58 1.86, 3.57 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ liver_transplant_listed, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
liver_transplant_listed 374
    0 — —
    1 0.23 0.15, 0.34 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ hrs*study_site, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 36 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
hrs 338
    Non-HRS — —
    HRS 0.78 0.46, 1.31 0.4
study_site 338
    High_volume_RRT — —
    Low_volume_RRT 1.05 0.76, 1.45 0.8
hrs * study_site 338
    HRS * Low_volume_RRT 1.07 0.51, 2.28 0.9
1 HR = Hazard Ratio, CI = Confidence Interval

Model 2 hrs+age_admission+sex+White+hispanic_race+study_site+pressor+initial_rrt+MELD_Na_baseline+liver_transplant_listed+ hrs*study_site

m2_cmprsk_model <- tidycmprsk::crr(Surv(time=time_90days,status_90days) ~ hrs+age_admission+sex+White+hispanic_race+study_site+pressor+initial_rrt+MELD_Na_baseline+liver_transplant_listed+hrs*study_site,data=master_rrt)
## 42 cases omitted due to missing values
m2_cmprsk_model %>%  tbl_regression(exponentiate = TRUE,
                      
                       pvalue_fun = ~style_pvalue(.x, digits = 3)) %>% bold_p() %>% # bold p-values under a given threshold (default 0.05)
  bold_labels()%>% 
  modify_spanning_header(
    c(estimate, ci, p.value) ~  
      "**Model 2 cmprsk regression**")%>%
  add_n()
Characteristic N Model 2 cmprsk regression
HR1 95% CI1 p-value
hrs 332
    Non-HRS — —
    HRS 1.35 0.78, 2.32 0.280
age_admission 332 1.01 1.00, 1.02 0.150
sex 332
    1 — —
    2 0.94 0.71, 1.25 0.670
White 332
    0 — —
    1 1.41 1.01, 1.96 0.042
hispanic_race 332
    0 — —
    1 0.69 0.44, 1.06 0.092
study_site 332
    High_volume_RRT — —
    Low_volume_RRT 1.24 0.88, 1.75 0.220
pressor 332
    0 — —
    1 1.62 1.15, 2.28 0.006
initial_rrt 332
    1 — —
    2 2.65 1.87, 3.77 <0.001
MELD_Na_baseline 332 1.04 1.02, 1.05 <0.001
liver_transplant_listed 332
    0 — —
    1 0.19 0.12, 0.31 <0.001
hrs * study_site 332
    HRS * Low_volume_RRT 1.02 0.51, 2.05 0.960
1 HR = Hazard Ratio, CI = Confidence Interval

Model 3 Univariate subdistribution hazard model hrs+age_admission+sex+White+hispanic_race+study_site+pressor+initial_rrt+MELD_Na_baseline+liver_transplant_listed+ hrs*study_site

tidycmprsk::crr(Surv(time_90days,status_90days) ~ encephalopathy_admission, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 1 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
encephalopathy_admission 373
    0 — —
    1 1.34 1.00, 1.80 0.054
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ MELD_Na_baseline, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 3 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
MELD_Na_baseline 371 1.02 1.01, 1.04 0.004
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ pressor, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 2 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
pressor 372
    0 — —
    1 1.94 1.42, 2.65 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ initial_rrt, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 2 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
initial_rrt 372
    1 — —
    2 2.58 1.86, 3.57 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval

Model 3 hrs+study_site+encephalopathy_admission+pressor+initial_rrt+MELD_Na_baseline

m3_cmprsk_model <- tidycmprsk::crr(Surv(time=time_90days,status_90days) ~ hrs+study_site+encephalopathy_admission+pressor+initial_rrt+MELD_Na_baseline,data=master_rrt)
## 43 cases omitted due to missing values
m3_cmprsk_model %>%  tbl_regression(exponentiate = TRUE,
                      
                       pvalue_fun = ~style_pvalue(.x, digits = 3)) %>% bold_p() %>% # bold p-values under a given threshold (default 0.05)
  bold_labels()%>% 
  modify_spanning_header(
    c(estimate, ci, p.value) ~  
      "**Model 3 cmprsk regression**")%>%
  add_n()
Characteristic N Model 3 cmprsk regression
HR1 95% CI1 p-value
hrs 331
    Non-HRS — —
    HRS 0.82 0.54, 1.24 0.350
study_site 331
    High_volume_RRT — —
    Low_volume_RRT 1.04 0.77, 1.40 0.820
encephalopathy_admission 331
    0 — —
    1 1.28 0.93, 1.78 0.130
pressor 331
    0 — —
    1 1.62 1.14, 2.29 0.007
initial_rrt 331
    1 — —
    2 1.92 1.36, 2.70 <0.001
MELD_Na_baseline 331 1.02 1.01, 1.04 0.004
1 HR = Hazard Ratio, CI = Confidence Interval

Model 4 Univariate subdistribution hazard model hrs+age_admission+sex+White+hispanic_race+study_site+pressor+initial_rrt+MELD_Na_baseline+liver_transplant_listed+ hrs*study_site

tidycmprsk::crr(Surv(time_90days,status_90days) ~ age_admission, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
age_admission 374 1.00 0.99, 1.01 0.8
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ sex, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
sex 374
    1 — —
    2 0.91 0.70, 1.18 0.5
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ White, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
White 374
    0 — —
    1 1.08 0.80, 1.46 0.6
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ hispanic_race, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
hispanic_race 374
    0 — —
    1 0.69 0.44, 1.08 0.10
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ hrs, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
hrs 374
    Non-HRS — —
    HRS 0.72 0.50, 1.04 0.077
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ study_site, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 36 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
study_site 338
    High_volume_RRT — —
    Low_volume_RRT 1.03 0.78, 1.37 0.8
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ MELD_Na_baseline, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 3 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
MELD_Na_baseline 371 1.02 1.01, 1.04 0.004
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ pressor, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 2 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
pressor 372
    0 — —
    1 1.94 1.42, 2.65 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ initial_rrt, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 2 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
initial_rrt 372
    1 — —
    2 2.58 1.86, 3.57 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ liver_transplant_listed, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
liver_transplant_listed 374
    0 — —
    1 0.23 0.15, 0.34 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ hrs*liver_transplant_listed, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
hrs 374
    Non-HRS — —
    HRS 1.17 0.78, 1.74 0.5
liver_transplant_listed 374
    0 — —
    1 0.25 0.16, 0.41 <0.001
hrs * liver_transplant_listed 374
    HRS * 1 0.65 0.25, 1.66 0.4
1 HR = Hazard Ratio, CI = Confidence Interval

Model 4 hrs+age_admission+sex+White+hispanic_race+study_site+pressor+initial_rrt+MELD_Na_baseline+liver_transplant_listed+ hrs*liver_transplant_listed

m3_cmprsk_model <- tidycmprsk::crr(Surv(time=time_90days,status_90days) ~ hrs+age_admission+sex+White+hispanic_race+study_site+pressor+initial_rrt+MELD_Na_baseline+liver_transplant_listed+ hrs*liver_transplant_listed,data=master_rrt)
## 42 cases omitted due to missing values
m3_cmprsk_model %>%  tbl_regression(exponentiate = TRUE,
                      
                       pvalue_fun = ~style_pvalue(.x, digits = 3)) %>% bold_p() %>% # bold p-values under a given threshold (default 0.05)
  bold_labels()%>% 
  modify_spanning_header(
    c(estimate, ci, p.value) ~  
      "**Model 4 cmprsk regression**")%>%
  add_n()
Characteristic N Model 4 cmprsk regression
HR1 95% CI1 p-value
hrs 332
    Non-HRS — —
    HRS 1.45 0.99, 2.12 0.059
age_admission 332 1.01 1.00, 1.02 0.150
sex 332
    1 — —
    2 0.94 0.71, 1.25 0.690
White 332
    0 — —
    1 1.41 1.02, 1.96 0.040
hispanic_race 332
    0 — —
    1 0.69 0.45, 1.07 0.094
study_site 332
    High_volume_RRT — —
    Low_volume_RRT 1.23 0.91, 1.68 0.180
pressor 332
    0 — —
    1 1.63 1.15, 2.29 0.006
initial_rrt 332
    1 — —
    2 2.67 1.88, 3.79 <0.001
MELD_Na_baseline 332 1.04 1.02, 1.05 <0.001
liver_transplant_listed 332
    0 — —
    1 0.21 0.12, 0.36 <0.001
hrs * liver_transplant_listed 332
    HRS * 1 0.76 0.29, 2.00 0.580
1 HR = Hazard Ratio, CI = Confidence Interval

Sensitivity Univariate subdistribution hazard models

tidycmprsk::crr(Surv(time_90days,status_90days) ~ age_admission, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
age_admission 374 1.00 0.99, 1.01 0.8
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ sex, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
sex 374
    1 — —
    2 0.91 0.70, 1.18 0.5
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ White, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
White 374
    0 — —
    1 1.08 0.80, 1.46 0.6
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ hispanic_race, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
hispanic_race 374
    0 — —
    1 0.69 0.44, 1.08 0.10
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ hrs_atn_group, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 75 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
hrs_atn_group 299
    ATN — —
    HRS 0.64 0.44, 0.93 0.020
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ study_site, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 36 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
study_site 338
    High_volume_RRT — —
    Low_volume_RRT 1.03 0.78, 1.37 0.8
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ MELD_Na_baseline, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 3 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
MELD_Na_baseline 371 1.02 1.01, 1.04 0.004
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ pressor, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 2 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
pressor 372
    0 — —
    1 1.94 1.42, 2.65 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ initial_rrt, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n() 
## 2 cases omitted due to missing values
Characteristic N HR1 95% CI1 p-value
initial_rrt 372
    1 — —
    2 2.58 1.86, 3.57 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ liver_transplant_listed, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
liver_transplant_listed 374
    0 — —
    1 0.23 0.15, 0.34 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval 
tidycmprsk::crr(Surv(time_90days,status_90days) ~ CLIF_C_Score, data = master_rrt) %>% 
  tbl_regression(exp = TRUE) %>% add_n()
Characteristic N HR1 95% CI1 p-value
CLIF_C_Score 374 1.04 1.03, 1.05 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval

Sensitivity 1: hrs_atn_group+age_admission+sex+White+hispanic_race+study_site+pressor+initial_rrt+MELD_Na_baseline+liver_transplant_listed

s1_cmprsk_model <- tidycmprsk::crr(Surv(time=time_90days,status_90days) ~  hrs_atn_group+age_admission+sex+White+hispanic_race+study_site+pressor+initial_rrt+MELD_Na_baseline+liver_transplant_listed,data=master_rrt)
## 114 cases omitted due to missing values
s1_cmprsk_model %>%  tbl_regression(exponentiate = TRUE,
                      
                       pvalue_fun = ~style_pvalue(.x, digits = 3)) %>% bold_p() %>% # bold p-values under a given threshold (default 0.05)
  bold_labels()%>% 
  modify_spanning_header(
    c(estimate, ci, p.value) ~  
      "**Sensitivity 1 cmprsk regression**")%>%
  add_n()
Characteristic N Sensitivity 1 cmprsk regression
HR1 95% CI1 p-value
hrs_atn_group 260
    ATN — —
    HRS 1.14 0.77, 1.69 0.510
age_admission 260 1.00 0.99, 1.02 0.450
sex 260
    1 — —
    2 0.91 0.66, 1.25 0.550
White 260
    0 — —
    1 1.19 0.83, 1.70 0.330
hispanic_race 260
    0 — —
    1 0.74 0.46, 1.21 0.230
study_site 260
    High_volume_RRT — —
    Low_volume_RRT 1.39 1.00, 1.94 0.050
pressor 260
    0 — —
    1 1.26 0.86, 1.83 0.230
initial_rrt 260
    1 — —
    2 2.57 1.74, 3.80 <0.001
MELD_Na_baseline 260 1.04 1.02, 1.06 <0.001
liver_transplant_listed 260
    0 — —
    1 0.21 0.12, 0.36 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval

Sensitivity 2: hrs+sex+White+hispanic_race+study_site+initial_rrt+CLIF_C_Score +liver_transplant_listed

s2_cmprsk_model <- tidycmprsk::crr(Surv(time=time_90days,status_90days) ~ hrs+sex+White+hispanic_race+study_site+initial_rrt+CLIF_C_Score +liver_transplant_listed,data=master_rrt)
## 37 cases omitted due to missing values
s2_cmprsk_model %>%  tbl_regression(exponentiate = TRUE,
                      
                       pvalue_fun = ~style_pvalue(.x, digits = 3)) %>% bold_p() %>% # bold p-values under a given threshold (default 0.05)
  bold_labels()%>% 
  modify_spanning_header(
    c(estimate, ci, p.value) ~  
      "**Sensitivity 2 cmprsk regression**")%>%
  add_n()
Characteristic N Sensitivity 2 cmprsk regression
HR1 95% CI1 p-value
hrs 337
    Non-HRS — —
    HRS 1.40 0.99, 1.98 0.056
sex 337
    1 — —
    2 0.98 0.75, 1.28 0.890
White 337
    0 — —
    1 1.32 0.97, 1.81 0.081
hispanic_race 337
    0 — —
    1 0.72 0.46, 1.11 0.140
study_site 337
    High_volume_RRT — —
    Low_volume_RRT 1.26 0.93, 1.71 0.130
initial_rrt 337
    1 — —
    2 3.11 2.21, 4.37 <0.001
CLIF_C_Score 337 1.03 1.02, 1.05 <0.001
liver_transplant_listed 337
    0 — —
    1 0.21 0.14, 0.34 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval

Sensitivity 3: hrs+study_site+initial_rrt+CLIF_C_Score

s2_cmprsk_model <- tidycmprsk::crr(Surv(time=time_90days,status_90days) ~ hrs+study_site+initial_rrt+CLIF_C_Score,data=master_rrt)
## 37 cases omitted due to missing values
s2_cmprsk_model %>%  tbl_regression(exponentiate = TRUE,
                      
                       pvalue_fun = ~style_pvalue(.x, digits = 3)) %>% bold_p() %>% # bold p-values under a given threshold (default 0.05)
  bold_labels()%>% 
  modify_spanning_header(
    c(estimate, ci, p.value) ~  
      "**Sensitivity 3 cmprsk regression**")%>%
  add_n()
Characteristic N Sensitivity 3 cmprsk regression
HR1 95% CI1 p-value
hrs 337
    Non-HRS — —
    HRS 0.92 0.63, 1.34 0.650
study_site 337
    High_volume_RRT — —
    Low_volume_RRT 1.02 0.76, 1.37 0.900
initial_rrt 337
    1 — —
    2 2.38 1.72, 3.31 <0.001
CLIF_C_Score 337 1.04 1.02, 1.05 <0.001
1 HR = Hazard Ratio, CI = Confidence Interval