Section 2 A Real data: Box 14: Initial data setup
# add column for outcome Y: length of stay
# Y = date of discharge - study admission date
# Y = date of death - study admission date if date of discharge not available
ObsData <- read.csv("https://hbiostat.org/data/repo/rhc.csv", header = TRUE)
# ObsData <- read.csv("rhc.csv", header = TRUE) # replace with your file path
ObsData$Y <- ObsData$dschdte - ObsData$sadmdte
ObsData$Y[is.na(ObsData$Y)] <- ObsData$dthdte[is.na(ObsData$Y)] -
ObsData$sadmdte[is.na(ObsData$Y)]
# remove outcomes we are not examining in this example
ObsData <- dplyr::select(ObsData,
!c(dthdte,lstctdte,dschdte,death,t3d30,dth30,surv2md1))
# remove unnecessary and problematic variables
ObsData <- dplyr::select(ObsData,
!c(sadmdte,ptid,X,adld3p,urin1,cat2))
# convert all categorical variables to factors
factors <- c("cat1", "ca", "cardiohx", "chfhx", "dementhx", "psychhx",
"chrpulhx", "renalhx", "liverhx", "gibledhx", "malighx",
"immunhx", "transhx", "amihx", "sex", "dnr1", "ninsclas",
"resp", "card", "neuro", "gastr", "renal", "meta", "hema",
"seps", "trauma", "ortho", "race", "income")
ObsData[factors] <- lapply(ObsData[factors], as.factor)
# convert our treatment A (RHC vs. No RHC) to a binary variable
ObsData$A <- ifelse(ObsData$swang1 == "RHC", 1, 0)
ObsData <- dplyr::select(ObsData, !swang1)
# categorize the variables to match with the original paper
ObsData$age <- cut(ObsData$age,breaks=c(-Inf, 50, 60, 70, 80, Inf),right=FALSE)
ObsData$race <- factor(ObsData$race, levels=c("white","black","other"))
ObsData$sex <- as.factor(ObsData$sex)
ObsData$sex <- relevel(ObsData$sex, ref = "Male")
ObsData$cat1 <- as.factor(ObsData$cat1)
levels(ObsData$cat1) <- c("ARF","CHF","Other","Other","Other",
"Other","Other","MOSF","MOSF")
ObsData$ca <- as.factor(ObsData$ca)
levels(ObsData$ca) <- c("Metastatic","None","Localized (Yes)")
ObsData$ca <- factor(ObsData$ca, levels=c("None", "Localized (Yes)", "Metastatic"))
# rename variables
names(ObsData) <- c("Disease.category", "Cancer", "Cardiovascular",
"Congestive.HF", "Dementia", "Psychiatric", "Pulmonary",
"Renal", "Hepatic", "GI.Bleed", "Tumor",
"Immunosuppression", "Transfer.hx", "MI", "age", "sex",
"edu", "DASIndex", "APACHE.score", "Glasgow.Coma.Score",
"blood.pressure", "WBC", "Heart.rate", "Respiratory.rate",
"Temperature", "PaO2vs.FIO2", "Albumin", "Hematocrit",
"Bilirubin", "Creatinine", "Sodium", "Potassium", "PaCo2",
"PH", "Weight", "DNR.status", "Medical.insurance",
"Respiratory.Diag", "Cardiovascular.Diag",
"Neurological.Diag", "Gastrointestinal.Diag", "Renal.Diag",
"Metabolic.Diag", "Hematologic.Diag", "Sepsis.Diag",
"Trauma.Diag", "Orthopedic.Diag", "race", "income",
"Y", "A")require(tableone)
CreateTableOne(data = ObsData, strata = "A")FALSE Stratified by A
FALSE 0 1 p test
FALSE n 3551 2184
FALSE Disease.category (%) <0.001
FALSE ARF 1581 (44.5) 909 (41.6)
FALSE CHF 247 ( 7.0) 209 ( 9.6)
FALSE Other 955 (26.9) 208 ( 9.5)
FALSE MOSF 768 (21.6) 858 (39.3)
FALSE Cancer (%) 0.001
FALSE None 2652 (74.7) 1727 (79.1)
FALSE Localized (Yes) 638 (18.0) 334 (15.3)
FALSE Metastatic 261 ( 7.4) 123 ( 5.6)
FALSE Cardiovascular = 1 (%) 567 (16.0) 446 (20.4) <0.001
FALSE Congestive.HF = 1 (%) 596 (16.8) 425 (19.5) 0.011
FALSE Dementia = 1 (%) 413 (11.6) 151 ( 6.9) <0.001
FALSE Psychiatric = 1 (%) 286 ( 8.1) 100 ( 4.6) <0.001
FALSE Pulmonary = 1 (%) 774 (21.8) 315 (14.4) <0.001
FALSE Renal = 1 (%) 149 ( 4.2) 106 ( 4.9) 0.268
FALSE Hepatic = 1 (%) 265 ( 7.5) 136 ( 6.2) 0.084
FALSE GI.Bleed = 1 (%) 131 ( 3.7) 54 ( 2.5) 0.014
FALSE Tumor = 1 (%) 872 (24.6) 444 (20.3) <0.001
FALSE Immunosuppression = 1 (%) 907 (25.5) 636 (29.1) 0.003
FALSE Transfer.hx = 1 (%) 335 ( 9.4) 327 (15.0) <0.001
FALSE MI = 1 (%) 105 ( 3.0) 95 ( 4.3) 0.007
FALSE age (%) <0.001
FALSE [-Inf,50) 884 (24.9) 540 (24.7)
FALSE [50,60) 546 (15.4) 371 (17.0)
FALSE [60,70) 812 (22.9) 577 (26.4)
FALSE [70,80) 809 (22.8) 529 (24.2)
FALSE [80, Inf) 500 (14.1) 167 ( 7.6)
FALSE sex = Female (%) 1637 (46.1) 906 (41.5) 0.001
FALSE edu (mean (SD)) 11.57 (3.13) 11.86 (3.16) 0.001
FALSE DASIndex (mean (SD)) 20.37 (5.48) 20.70 (5.03) 0.023
FALSE APACHE.score (mean (SD)) 50.93 (18.81) 60.74 (20.27) <0.001
FALSE Glasgow.Coma.Score (mean (SD)) 22.25 (31.37) 18.97 (28.26) <0.001
FALSE blood.pressure (mean (SD)) 84.87 (38.87) 68.20 (34.24) <0.001
FALSE WBC (mean (SD)) 15.26 (11.41) 16.27 (12.55) 0.002
FALSE Heart.rate (mean (SD)) 112.87 (40.94) 118.93 (41.47) <0.001
FALSE Respiratory.rate (mean (SD)) 28.98 (13.95) 26.65 (14.17) <0.001
FALSE Temperature (mean (SD)) 37.63 (1.74) 37.59 (1.83) 0.429
FALSE PaO2vs.FIO2 (mean (SD)) 240.63 (116.66) 192.43 (105.54) <0.001
FALSE Albumin (mean (SD)) 3.16 (0.67) 2.98 (0.93) <0.001
FALSE Hematocrit (mean (SD)) 32.70 (8.79) 30.51 (7.42) <0.001
FALSE Bilirubin (mean (SD)) 2.00 (4.43) 2.71 (5.33) <0.001
FALSE Creatinine (mean (SD)) 1.92 (2.03) 2.47 (2.05) <0.001
FALSE Sodium (mean (SD)) 137.04 (7.68) 136.33 (7.60) 0.001
FALSE Potassium (mean (SD)) 4.08 (1.04) 4.05 (1.01) 0.321
FALSE PaCo2 (mean (SD)) 39.95 (14.24) 36.79 (10.97) <0.001
FALSE PH (mean (SD)) 7.39 (0.11) 7.38 (0.11) <0.001
FALSE Weight (mean (SD)) 65.04 (29.50) 72.36 (27.73) <0.001
FALSE DNR.status = Yes (%) 499 (14.1) 155 ( 7.1) <0.001
FALSE Medical.insurance (%) <0.001
FALSE Medicaid 454 (12.8) 193 ( 8.8)
FALSE Medicare 947 (26.7) 511 (23.4)
FALSE Medicare & Medicaid 251 ( 7.1) 123 ( 5.6)
FALSE No insurance 186 ( 5.2) 136 ( 6.2)
FALSE Private 967 (27.2) 731 (33.5)
FALSE Private & Medicare 746 (21.0) 490 (22.4)
FALSE Respiratory.Diag = Yes (%) 1481 (41.7) 632 (28.9) <0.001
FALSE Cardiovascular.Diag = Yes (%) 1007 (28.4) 924 (42.3) <0.001
FALSE Neurological.Diag = Yes (%) 575 (16.2) 118 ( 5.4) <0.001
FALSE Gastrointestinal.Diag = Yes (%) 522 (14.7) 420 (19.2) <0.001
FALSE Renal.Diag = Yes (%) 147 ( 4.1) 148 ( 6.8) <0.001
FALSE Metabolic.Diag = Yes (%) 172 ( 4.8) 93 ( 4.3) 0.337
FALSE Hematologic.Diag = Yes (%) 239 ( 6.7) 115 ( 5.3) 0.029
FALSE Sepsis.Diag = Yes (%) 515 (14.5) 516 (23.6) <0.001
FALSE Trauma.Diag = Yes (%) 18 ( 0.5) 34 ( 1.6) <0.001
FALSE Orthopedic.Diag = Yes (%) 3 ( 0.1) 4 ( 0.2) 0.516
FALSE race (%) 0.425
FALSE white 2753 (77.5) 1707 (78.2)
FALSE black 585 (16.5) 335 (15.3)
FALSE other 213 ( 6.0) 142 ( 6.5)
FALSE income (%) <0.001
FALSE $11-$25k 713 (20.1) 452 (20.7)
FALSE $25-$50k 500 (14.1) 393 (18.0)
FALSE > $50k 257 ( 7.2) 194 ( 8.9)
FALSE Under $11k 2081 (58.6) 1145 (52.4)
FALSE Y (mean (SD)) 19.53 (23.59) 24.86 (28.90) <0.001
FALSE A (mean (SD)) 0.00 (0.00) 1.00 (0.00) <0.001