Table 1 without transplant no missing, used for analysis
# table1 <- final_cohort_1_no_missing %>%
# tbl_summary(
# by = group,
# # first row: mean (SD), second row: median [IQR]
# statistic = all_continuous() ~ "{mean} ({sd})",
# missing_text = "Missing"
# ) %>%add_p()
#
var1 <- names(final_cohort_1_no_missing)
var1_num <- names(final_cohort_1_no_missing)[sapply(final_cohort_1_no_missing, is.numeric)]
var1_cat <- setdiff(var1,var1_num)
#create table one for expourse response#
T1 <- CreateTableOne(vars = var1,strata ="group" ,includeNA = F,addOverall = TRUE,data = final_cohort_1_no_missing, factorVars = var1_cat)
#print table one
T1_print <- print(T1,showAllLevels = T,missing = T,quote = FALSE, noSpaces = TRUE, printToggle = FALSE)
#save
write.csv(T1_print, file = "/Users/to909/Desktop/Annie final/Table1_3year_0313.csv")
T1_2 <- CreateTableOne(vars = var1,strata ="group" ,includeNA = F,addOverall = TRUE,data = final_cohort_1_no_missing, factorVars = var1_cat)
#print table one
T1_2_print <- print(T1_2,nonnormal =var1_num,showAllLevels = T,missing = T,quote = FALSE, noSpaces = TRUE, printToggle = FALSE)
#save
write.csv(T1_2_print, file = "/Users/to909/Desktop/Annie final/Table1_3year_nonnormal_0313.csv")
# final_cohort_1_no_missing %>%
# tbl_summary(
# by = transplant_dec_v2,
# # first row: mean (SD), second row: median [IQR]
# statistic = all_continuous() ~ "{median} [{p25}, {p75}]",
# missing_text = "Missing"
# ) %>% add_p()
feature selection cohort without transplant
3 year
Model1 : age sex_cat
## Area under the curve: 0.6635
## Confusion Matrix and Statistics
##
## Reference
## Prediction alive died
## alive 3185 828
## died 37568 30736
##
## Accuracy : 0.4691
## 95% CI : (0.4654, 0.4727)
## No Information Rate : 0.5635
## P-Value [Acc > NIR] : 1
##
## Kappa : 0.0459
##
## Mcnemar's Test P-Value : <2e-16
##
## Sensitivity : 0.97377
## Specificity : 0.07815
## Pos Pred Value : 0.44999
## Neg Pred Value : 0.79367
## Prevalence : 0.43647
## Detection Rate : 0.42502
## Detection Prevalence : 0.94451
## Balanced Accuracy : 0.52596
##
## 'Positive' Class : died
##
##
## Call:
## NULL
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.335130 0.006014 -55.725 <2e-16 ***
## age 0.619440 0.004335 142.895 <2e-16 ***
## sex_catMale 0.067073 0.007902 8.488 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 395983 on 289267 degrees of freedom
## Residual deviance: 372662 on 289265 degrees of freedom
## AIC: 372668
##
## Number of Fisher Scoring iterations: 4
| Characteristic |
OR |
95% CI |
p-value |
| age |
1.86 |
1.84, 1.87 |
<0.001 |
| sex_catMale |
1.07 |
1.05, 1.09 |
<0.001 |
Model2 : age sex_cat ALBUMIN
## Area under the curve: 0.7309
##
## Call:
## NULL
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.413269 0.006294 -65.66 <2e-16 ***
## age 0.607550 0.004516 134.52 <2e-16 ***
## sex_catMale 0.181555 0.008308 21.85 <2e-16 ***
## ALBUMIN -0.690252 0.004610 -149.72 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 395983 on 289267 degrees of freedom
## Residual deviance: 346451 on 289264 degrees of freedom
## AIC: 346459
##
## Number of Fisher Scoring iterations: 3
| Characteristic |
OR |
95% CI |
p-value |
| age |
1.84 |
1.82, 1.85 |
<0.001 |
| sex_catMale |
1.20 |
1.18, 1.22 |
<0.001 |
| ALBUMIN |
0.50 |
0.50, 0.51 |
<0.001 |
Model_3 : age sex_cat ALBUMIN COMO_CHF
## Area under the curve: 0.7374
##
## Call:
## NULL
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.569073 0.007008 -81.20 <2e-16 ***
## age 0.587618 0.004550 129.15 <2e-16 ***
## sex_catMale 0.185538 0.008352 22.21 <2e-16 ***
## ALBUMIN -0.681172 0.004621 -147.42 <2e-16 ***
## COMO_CHFY 0.457387 0.008682 52.68 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 395983 on 289267 degrees of freedom
## Residual deviance: 343675 on 289263 degrees of freedom
## AIC: 343685
##
## Number of Fisher Scoring iterations: 3
| Characteristic |
OR |
95% CI |
p-value |
| age |
1.80 |
1.78, 1.82 |
<0.001 |
| sex_catMale |
1.20 |
1.18, 1.22 |
<0.001 |
| ALBUMIN |
0.51 |
0.50, 0.51 |
<0.001 |
| COMO_CHFY |
1.58 |
1.55, 1.61 |
<0.001 |
model_4 : age sex_cat ALBUMIN COMO_CHF COMO_DM_INS
## Area under the curve: 0.7376
##
## Call:
## NULL
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.593365 0.007968 -74.469 < 2e-16 ***
## age 0.592089 0.004608 128.491 < 2e-16 ***
## sex_catMale 0.187209 0.008356 22.403 < 2e-16 ***
## ALBUMIN -0.678758 0.004634 -146.488 < 2e-16 ***
## COMO_CHFY 0.451465 0.008729 51.718 < 2e-16 ***
## COMO_DM_INSY 0.054199 0.008424 6.434 1.24e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 395983 on 289267 degrees of freedom
## Residual deviance: 343633 on 289262 degrees of freedom
## AIC: 343645
##
## Number of Fisher Scoring iterations: 3
| Characteristic |
OR |
95% CI |
p-value |
| age |
1.81 |
1.79, 1.82 |
<0.001 |
| sex_catMale |
1.21 |
1.19, 1.23 |
<0.001 |
| ALBUMIN |
0.51 |
0.50, 0.51 |
<0.001 |
| COMO_CHFY |
1.57 |
1.54, 1.60 |
<0.001 |
| COMO_DM_INSY |
1.06 |
1.04, 1.07 |
<0.001 |
model_5 : age sex_cat ALBUMIN COMO_CHF COMO_DM_INS COMO_HTN
## Area under the curve: 0.7383
##
## Call:
## NULL
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.382622 0.013970 -27.388 < 2e-16 ***
## age 0.593702 0.004612 128.727 < 2e-16 ***
## sex_catMale 0.185036 0.008362 22.128 < 2e-16 ***
## ALBUMIN -0.675364 0.004638 -145.616 < 2e-16 ***
## COMO_CHFY 0.453370 0.008736 51.896 < 2e-16 ***
## COMO_DM_INSY 0.059086 0.008434 7.006 2.45e-12 ***
## COMO_HTNY -0.239224 0.013062 -18.314 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 395983 on 289267 degrees of freedom
## Residual deviance: 343298 on 289261 degrees of freedom
## AIC: 343312
##
## Number of Fisher Scoring iterations: 3
| Characteristic |
OR |
95% CI |
p-value |
| age |
1.81 |
1.79, 1.83 |
<0.001 |
| sex_catMale |
1.20 |
1.18, 1.22 |
<0.001 |
| ALBUMIN |
0.51 |
0.50, 0.51 |
<0.001 |
| COMO_CHFY |
1.57 |
1.55, 1.60 |
<0.001 |
| COMO_DM_INSY |
1.06 |
1.04, 1.08 |
<0.001 |
| COMO_HTNY |
0.79 |
0.77, 0.81 |
<0.001 |
model_6 : age sex_cat ALBUMIN COMO_CHF COMO_DM_INS COMO_HTN
CLM_FROM_3year_cat
## Area under the curve: 0.7489
##
## Call:
## NULL
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.394771 0.014096 -28.01 < 2e-16 ***
## age 0.600553 0.004649 129.18 < 2e-16 ***
## sex_catMale 0.203954 0.008439 24.17 < 2e-16 ***
## ALBUMIN -0.649967 0.004662 -139.42 < 2e-16 ***
## COMO_CHFY 0.432255 0.008812 49.05 < 2e-16 ***
## COMO_DM_INSY 0.051478 0.008508 6.05 1.45e-09 ***
## COMO_HTNY -0.237231 0.013176 -18.00 < 2e-16 ***
## CLM_FROM_3year_cat 0.291374 0.004271 68.23 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 395983 on 289267 degrees of freedom
## Residual deviance: 338541 on 289260 degrees of freedom
## AIC: 338557
##
## Number of Fisher Scoring iterations: 4
| Characteristic |
OR |
95% CI |
p-value |
| age |
1.82 |
1.81, 1.84 |
<0.001 |
| sex_catMale |
1.23 |
1.21, 1.25 |
<0.001 |
| ALBUMIN |
0.52 |
0.52, 0.53 |
<0.001 |
| COMO_CHFY |
1.54 |
1.51, 1.57 |
<0.001 |
| COMO_DM_INSY |
1.05 |
1.04, 1.07 |
<0.001 |
| COMO_HTNY |
0.79 |
0.77, 0.81 |
<0.001 |
| CLM_FROM_3year_cat |
1.34 |
1.33, 1.35 |
<0.001 |
model_ : age sex_cat ALBUMIN COMO_CHF COMO_DM_INS COMO_HTN
CLM_FROM_3year_cat ICU_DAYS_3year_cat
model_7 : age ALBUMIN COMO_CHF
## Area under the curve: 0.7367
##
## Call:
## NULL
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.462695 0.005077 -91.13 <2e-16 ***
## age 0.584412 0.004540 128.73 <2e-16 ***
## ALBUMIN -0.672429 0.004592 -146.43 <2e-16 ***
## COMO_CHFY 0.455627 0.008674 52.53 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 395983 on 289267 degrees of freedom
## Residual deviance: 344170 on 289264 degrees of freedom
## AIC: 344178
##
## Number of Fisher Scoring iterations: 3
| Characteristic |
OR |
95% CI |
p-value |
| age |
1.79 |
1.78, 1.81 |
<0.001 |
| ALBUMIN |
0.51 |
0.51, 0.52 |
<0.001 |
| COMO_CHFY |
1.58 |
1.55, 1.60 |
<0.001 |
model_8 : age ALBUMIN COMO_CHF IRON_SAT_PERCENT
## Area under the curve: 0.7424
##
## Call:
## NULL
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.456212 0.005103 -89.40 <2e-16 ***
## age 0.600756 0.004581 131.13 <2e-16 ***
## ALBUMIN -0.650195 0.004599 -141.38 <2e-16 ***
## COMO_CHFY 0.424024 0.008735 48.54 <2e-16 ***
## IRON_SAT_PERCENT -0.222513 0.004234 -52.55 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 395983 on 289267 degrees of freedom
## Residual deviance: 341365 on 289263 degrees of freedom
## AIC: 341375
##
## Number of Fisher Scoring iterations: 4
| Characteristic |
OR |
95% CI |
p-value |
| age |
1.82 |
1.81, 1.84 |
<0.001 |
| ALBUMIN |
0.52 |
0.52, 0.53 |
<0.001 |
| COMO_CHFY |
1.53 |
1.50, 1.55 |
<0.001 |
| IRON_SAT_PERCENT |
0.80 |
0.79, 0.81 |
<0.001 |
model_9 : age ALBUMIN COMO_CHF IRON_SAT_PERCENT HGB
## Area under the curve: 0.746
##
## Call:
## NULL
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.458925 0.005123 -89.58 <2e-16 ***
## age 0.609162 0.004599 132.46 <2e-16 ***
## ALBUMIN -0.591095 0.004773 -123.83 <2e-16 ***
## COMO_CHFY 0.435216 0.008773 49.61 <2e-16 ***
## IRON_SAT_PERCENT -0.194505 0.004288 -45.36 <2e-16 ***
## HGB -0.202541 0.004549 -44.52 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 395983 on 289267 degrees of freedom
## Residual deviance: 339349 on 289262 degrees of freedom
## AIC: 339361
##
## Number of Fisher Scoring iterations: 4
| Characteristic |
OR |
95% CI |
p-value |
| age |
1.84 |
1.82, 1.86 |
<0.001 |
| ALBUMIN |
0.55 |
0.55, 0.56 |
<0.001 |
| COMO_CHFY |
1.55 |
1.52, 1.57 |
<0.001 |
| IRON_SAT_PERCENT |
0.82 |
0.82, 0.83 |
<0.001 |
| HGB |
0.82 |
0.81, 0.82 |
<0.001 |
model_8 : age ALBUMIN COMO_CHF IRON_SAT_PERCENT
## Area under the curve: 0.7424
##
## Call:
## NULL
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.456212 0.005103 -89.40 <2e-16 ***
## age 0.600756 0.004581 131.13 <2e-16 ***
## ALBUMIN -0.650195 0.004599 -141.38 <2e-16 ***
## COMO_CHFY 0.424024 0.008735 48.54 <2e-16 ***
## IRON_SAT_PERCENT -0.222513 0.004234 -52.55 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 395983 on 289267 degrees of freedom
## Residual deviance: 341365 on 289263 degrees of freedom
## AIC: 341375
##
## Number of Fisher Scoring iterations: 4
| Characteristic |
OR |
95% CI |
p-value |
| age |
1.82 |
1.81, 1.84 |
<0.001 |
| ALBUMIN |
0.52 |
0.52, 0.53 |
<0.001 |
| COMO_CHFY |
1.53 |
1.50, 1.55 |
<0.001 |
| IRON_SAT_PERCENT |
0.80 |
0.79, 0.81 |
<0.001 |
model_10 : age ALBUMIN COMO_CHF IRON_SAT_PERCENT HGB
CLM_FROM_3year_cat
## Area under the curve: 0.7554
##
## Call:
## NULL
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.462347 0.005169 -89.44 <2e-16 ***
## age 0.614898 0.004630 132.81 <2e-16 ***
## ALBUMIN -0.569823 0.004797 -118.79 <2e-16 ***
## COMO_CHFY 0.414871 0.008841 46.92 <2e-16 ***
## IRON_SAT_PERCENT -0.188390 0.004318 -43.63 <2e-16 ***
## HGB -0.191165 0.004567 -41.85 <2e-16 ***
## CLM_FROM_3year_cat 0.276352 0.004299 64.28 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 395983 on 289267 degrees of freedom
## Residual deviance: 335138 on 289261 degrees of freedom
## AIC: 335152
##
## Number of Fisher Scoring iterations: 4
| Characteristic |
OR |
95% CI |
p-value |
| age |
1.85 |
1.83, 1.87 |
<0.001 |
| ALBUMIN |
0.57 |
0.56, 0.57 |
<0.001 |
| COMO_CHFY |
1.51 |
1.49, 1.54 |
<0.001 |
| IRON_SAT_PERCENT |
0.83 |
0.82, 0.84 |
<0.001 |
| HGB |
0.83 |
0.82, 0.83 |
<0.001 |
| CLM_FROM_3year_cat |
1.32 |
1.31, 1.33 |
<0.001 |