Transplant yes = 2 no = 0, transplant_lt_status = 2
table(final_master_listed_transplant$transplant_lt_status)
##
## 0 2
## 22 60
rrt_status
table(final_master_listed_transplant$rrt_status)
##
## 0 1 2
## 4 14 7
Death in 90 days yes = 1 no = 0, time_to_death_status_90days =
1
table(final_master_listed_transplant$time_to_death_status_90days)
##
## 0 1
## 65 17
rrt_status, hrs_responders_cat_2
table(final_master_listed_transplant$rrt_status,final_master_listed_transplant$hrs_responders_cat_2)
##
## 0 1
## 0 3 1
## 1 10 4
## 2 4 3
fisher.test(table(final_master_listed_transplant$rrt_status,final_master_listed_transplant$hrs_responders_cat_2))
##
## Fisher's Exact Test for Count Data
##
## data: table(final_master_listed_transplant$rrt_status, final_master_listed_transplant$hrs_responders_cat_2)
## p-value = 0.8445
## alternative hypothesis: two.sided
(listed_transplant=1) and transplanted (transplant_lt_status = 2)
new\(rrt_90days,new\)hrs_responders_cat_2
new <- final_master_listed_transplant %>% filter(listed_transplant==1 & transplant_lt_status == 2)
table(new$rrt_90days,new$hrs_responders_cat_2)
##
## 0 1
## 0 10 25
## 1 17 8
chisq.test(table(new$rrt_90days,new$hrs_responders_cat_2))
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: table(new$rrt_90days, new$hrs_responders_cat_2)
## X-squared = 7.6364, df = 1, p-value = 0.00572
transplant_lt_status vs hrs_responders_cat_2
table(final_master_listed_transplant$transplant_lt_status,final_master_listed_transplant$hrs_responders_cat_2)
##
## 0 1
## 0 9 13
## 2 27 33
chisq.test(table(final_master_listed_transplant$transplant_lt_status,final_master_listed_transplant$hrs_responders_cat_2))
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: table(final_master_listed_transplant$transplant_lt_status, final_master_listed_transplant$hrs_responders_cat_2)
## X-squared = 0.0063397, df = 1, p-value = 0.9365
transplant_lt_status = 2 transplant_slkt vs
hrs_responders_cat_2
new <- final_master_listed_transplant %>% filter(transplant_lt_status == 2)
table(new$transplant_slkt,new$hrs_responders_cat_2)
##
## 0 1
## 0 23 25
## 1 4 8
chisq.test(table(new$transplant_slkt,new$hrs_responders_cat_2))
##
## Pearson's Chi-squared test with Yates' continuity correction
##
## data: table(new$transplant_slkt, new$hrs_responders_cat_2)
## X-squared = 0.34091, df = 1, p-value = 0.5593
dc_days_to_death mean and sd
mean(final_master_listed_transplant$dc_days_to_death,na.rm = T)
## [1] 74.01235
sd(final_master_listed_transplant$dc_days_to_death,na.rm = T)
## [1] 34.0872
summary(final_master_listed_transplant$dc_days_to_death)
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.00 90.00 90.00 74.01 90.00 90.00 1
remove time_to_death_status_90days=0
final_master_listed_transplant_alive <- final_master_listed_transplant %>% filter(time_to_death_status_90days!=0)
mean(final_master_listed_transplant_alive$dc_days_to_death,na.rm = T)
## [1] 9.0625
sd(final_master_listed_transplant_alive$dc_days_to_death,na.rm = T)
## [1] 24.28297
summary(final_master_listed_transplant_alive$dc_days_to_death)
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.000 0.000 0.000 9.062 1.750 90.000 1
time_to_transplant_90days mean and sd
mean(final_master_listed_transplant$time_to_transplant_90days,na.rm = T)
## [1] 44.21951
sd(final_master_listed_transplant$time_to_transplant_90days,na.rm = T)
## [1] 35.76916
summary(final_master_listed_transplant$time_to_transplant_90days)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.00 11.25 29.00 44.22 90.00 90.00
dc_days_to_death mean and sd
mean(final_master_listed_transplant$dc_days_to_death,na.rm = T)
## [1] 74.01235
sd(final_master_listed_transplant$dc_days_to_death,na.rm = T)
## [1] 34.0872
summary(final_master_listed_transplant$dc_days_to_death)
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.00 90.00 90.00 74.01 90.00 90.00 1
Competing risk model outcome transplant=2, death=1
table(final_master_listed_transplant$time_to_death_status_90days_cmp)
##
## 0 1 2
## 15 14 53
Competing risk model outcome 2 competing event 1
covariates:hrs_responders_cat_2+age+sex_male+admit_meld_3
final_master_listed_transplant$time_to_death_status_90days_cmp <- factor(final_master_listed_transplant$time_to_death_status_90days_cmp)
tidycmprsk::crr(Surv(time_to_death_90days_cmp,time_to_death_status_90days_cmp)~ hrs_responders_cat_2+age+sex_male+admit_meld_3,failcode=2,cencode=0, data = final_master_listed_transplant) %>% tbl_regression(exp = TRUE) %>% add_n()%>%
bold_p(0.05) %>% # bold p-values under a given threshold (default 0.05)
bold_labels()
| Characteristic |
N |
HR |
95% CI |
p-value |
| hrs_responders_cat_2 |
82 |
|
|
|
| 0 |
|
— |
— |
|
| 1 |
|
0.85 |
0.50, 1.44 |
0.6 |
| age |
82 |
0.99 |
0.96, 1.02 |
0.6 |
| sex_male |
82 |
|
|
|
| 0 |
|
— |
— |
|
| 1 |
|
0.86 |
0.49, 1.51 |
0.6 |
| admit_meld_3 |
82 |
1.02 |
0.99, 1.06 |
0.2 |
logistic regression outcome:hrs_responders_cat_2
covariates:age+sex_male+admit_meld_3+map_day0+refascites_previous_comp
glm(hrs_responders_cat_2~age+sex_male+admit_meld_3+map_day0+refascites_previous_comp, data = final_master_listed_transplant, family = binomial) %>% tbl_regression(exp = TRUE,pvalue_fun = function(x) style_pvalue(x, digits = 3))
| Characteristic |
OR |
95% CI |
p-value |
| age |
0.99 |
0.94, 1.04 |
0.707 |
| sex_male |
|
|
|
| 0 |
— |
— |
|
| 1 |
0.76 |
0.27, 2.17 |
0.613 |
| admit_meld_3 |
1.03 |
0.96, 1.11 |
0.448 |
| map_day0 |
1.03 |
0.97, 1.09 |
0.331 |
| refascites_previous_comp |
2.15 |
0.63, 7.75 |
0.226 |