# Important packages to load in
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(gtsummary)## #Uighurlibrary(survival)
library(labelled)
library(tidyverse)## ── Attaching packages ────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse 1.3.0 ──## ✓ ggplot2 3.3.3 ✓ purrr 0.3.4
## ✓ tibble 3.0.3 ✓ stringr 1.4.0
## ✓ tidyr 1.1.1 ✓ forcats 0.5.0
## ✓ readr 1.3.1## ── Conflicts ───────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(broom)
library(ggplot2)
library(survminer)## Loading required package: ggpubr###Intention to Treat MIS vs Open
## Importing data in to Rstudio below
NCDBOriginalData <- read.csv ("Mohamed_NCDB1.csv", header = TRUE, sep = "," )## Subsetting distal pancreatectomies
NCDBDistalPancreatectomy <-
subset(NCDBOriginalData, RX_SUMM_SURG_PRIM_SITE.2.2 == "Partial pancreatectomy, distal")### Recoding MIS vs MIS converted to open
NCDBDistalPancreatectomy$RX_HOSP_SURG_APPR_2010[NCDBDistalPancreatectomy$RX_HOSP_SURG_APPR_2010 =="Open or approach unspecified"] <- "Open"
NCDBDistalPancreatectomy$RX_HOSP_SURG_APPR_2010[NCDBDistalPancreatectomy$RX_HOSP_SURG_APPR_2010 =="Laparoscopic"] <- "MIS"
NCDBDistalPancreatectomy$RX_HOSP_SURG_APPR_2010[NCDBDistalPancreatectomy$RX_HOSP_SURG_APPR_2010 =="Laparoscopic converted to open"] <- "MIS Converted to open"
NCDBDistalPancreatectomy$RX_HOSP_SURG_APPR_2010[NCDBDistalPancreatectomy$RX_HOSP_SURG_APPR_2010 =="Robotic assisted"] <- "MIS"##Recoding Data within Columns Facility Location
NCDBDistalPancreatectomy$FACILITY_LOCATION_CD[NCDBDistalPancreatectomy$FACILITY_LOCATION_CD =="New England"] <- "NorthEast"
NCDBDistalPancreatectomy$FACILITY_LOCATION_CD[NCDBDistalPancreatectomy$FACILITY_LOCATION_CD =="New England"] <- "NorthEast"
NCDBDistalPancreatectomy$FACILITY_LOCATION_CD[NCDBDistalPancreatectomy$FACILITY_LOCATION_CD =="Middle Atlantic"] <- "NorthEast"
NCDBDistalPancreatectomy$FACILITY_LOCATION_CD[NCDBDistalPancreatectomy$FACILITY_LOCATION_CD =="New England"] <- "NorthEast"
NCDBDistalPancreatectomy$FACILITY_LOCATION_CD[NCDBDistalPancreatectomy$FACILITY_LOCATION_CD =="New England"] <- "NorthEast"
NCDBDistalPancreatectomy$FACILITY_LOCATION_CD[NCDBDistalPancreatectomy$FACILITY_LOCATION_CD =="East North Central"] <- "Midwest"
NCDBDistalPancreatectomy$FACILITY_LOCATION_CD[NCDBDistalPancreatectomy$FACILITY_LOCATION_CD =="East South Central"] <- "South"
NCDBDistalPancreatectomy$FACILITY_LOCATION_CD[NCDBDistalPancreatectomy$FACILITY_LOCATION_CD =="Mountain"] <- "West"
NCDBDistalPancreatectomy$FACILITY_LOCATION_CD[NCDBDistalPancreatectomy$FACILITY_LOCATION_CD =="South Atlantic"] <- "South"
NCDBDistalPancreatectomy$FACILITY_LOCATION_CD[NCDBDistalPancreatectomy$FACILITY_LOCATION_CD =="West South Central"] <- "South"
NCDBDistalPancreatectomy$FACILITY_LOCATION_CD[NCDBDistalPancreatectomy$FACILITY_LOCATION_CD =="West North Central"] <- "Midwest"
NCDBDistalPancreatectomy$FACILITY_LOCATION_CD[NCDBDistalPancreatectomy$FACILITY_LOCATION_CD =="Pacific"] <- "West"
NCDBDistalPancreatectomy$FACILITY_LOCATION_CD[NCDBDistalPancreatectomy$FACILITY_LOCATION_CD ==""] <- NA###Recoding Data within income
NCDBDistalPancreatectomy$MED_INC_QUAR_12[NCDBDistalPancreatectomy$MED_INC_QUAR_12 ==""] <- NA
###recoding data within no_hsd_quar_12
NCDBDistalPancreatectomy$NO_HSD_QUAR_12[NCDBDistalPancreatectomy$NO_HSD_QUAR_12 ==""] <- NA##Recoding Data within Columns Population Density
NCDBDistalPancreatectomy$UR_CD_13[NCDBDistalPancreatectomy$UR_CD_13 =="Urban population of 2,500 to 19,999, adjacent to a metro area"] <- "Urban"
NCDBDistalPancreatectomy$UR_CD_13[NCDBDistalPancreatectomy$UR_CD_13 =="Counties in metro areas of 250,000 to 1 million population"] <- "Metro"
NCDBDistalPancreatectomy$UR_CD_13[NCDBDistalPancreatectomy$UR_CD_13 =="Counties in metro areas of 1 million population or more"] <- "Metro"
NCDBDistalPancreatectomy$UR_CD_13[NCDBDistalPancreatectomy$UR_CD_13 =="Completely rural or less than 2,500 urban population, not adjacent to a metro area"] <- "Rural"
NCDBDistalPancreatectomy$UR_CD_13[NCDBDistalPancreatectomy$UR_CD_13 =="Counties in metro areas of fewer than 250,000 population"] <- "Metro"
NCDBDistalPancreatectomy$UR_CD_13[NCDBDistalPancreatectomy$UR_CD_13 =="Urban population of 2,500 to 19,999, not adjacent to a metro area"] <- "Urban"
NCDBDistalPancreatectomy$UR_CD_13[NCDBDistalPancreatectomy$UR_CD_13 =="Completely rural or less than 2,500 urban population, adjacent to a metro area"] <- "Rural"
NCDBDistalPancreatectomy$UR_CD_13[NCDBDistalPancreatectomy$UR_CD_13 =="Urban population of 20,000 or more not adjacent to a metro area"] <- "Urban"
NCDBDistalPancreatectomy$UR_CD_13[NCDBDistalPancreatectomy$UR_CD_13 =="Completely rural or less than 2,500 urban population, not adjacent to a metro area"] <- "Urban"
NCDBDistalPancreatectomy$UR_CD_13[NCDBDistalPancreatectomy$UR_CD_13 ==""] <- NA## recoding data within columns vital status
NCDBDistalPancreatectomy$PUF_VITAL_STATUS[NCDBDistalPancreatectomy$PUF_VITAL_STATUS ==""] <- NA##Recoding Analytical Stages removing Stage IV patients
NCDBDistalPancreatectomy$ANALYTIC_STAGE_GROUP[NCDBDistalPancreatectomy$ANALYTIC_STAGE_GROUP == "AJCC Stage Group unknown"] <- NA
NCDBDistalPancreatectomy$ANALYTIC_STAGE_GROUP[NCDBDistalPancreatectomy$ANALYTIC_STAGE_GROUP == "AJCC Staging not applicable"] <- NA
NCDBDistalPancreatectomy$ANALYTIC_STAGE_GROUP[NCDBDistalPancreatectomy$ANALYTIC_STAGE_GROUP == "Unknown"] <- NA
NCDBDistalPancreatectomy$ANALYTIC_STAGE_GROUP[NCDBDistalPancreatectomy$ANALYTIC_STAGE_GROUP == "Stage IV"] <- NA##Recoding Insurance removing Unknown patients
NCDBDistalPancreatectomy$INSURANCE_STATUS.2[NCDBDistalPancreatectomy$INSURANCE_STATUS.2 == "Unknown"] <- NA### Recoding data in Tumor Grade Column
NCDBDistalPancreatectomy$GRADE[NCDBDistalPancreatectomy$GRADE =="Cell type not determined, not stated or not applicable, unknown primaries, high grade dysplasia"] <- NA
NCDBDistalPancreatectomy$GRADE[NCDBDistalPancreatectomy$GRADE =="Unknown"] <- NA
NCDBDistalPancreatectomy$GRADE[NCDBDistalPancreatectomy$GRADE =="Undifferentiated, anaplastic"] <- "Undifferentiated"
NCDBDistalPancreatectomy$GRADE[NCDBDistalPancreatectomy$GRADE =="Moderately differentiated, moderately well differentiated, intermediate differentiation"] <- "Moderately differentiated"
NCDBDistalPancreatectomy$GRADE[NCDBDistalPancreatectomy$GRADE =="Well differentiated, differentiated, NOS"] <- "Well differentiated"###recode the surgical approach and make MIS converted to Open the same as MIS just before subsetting MIS and Open into new dataframe
NCDBDistalPancreatectomy$RX_HOSP_SURG_APPR_2010[NCDBDistalPancreatectomy$RX_HOSP_SURG_APPR_2010 =="MIS Converted to open"] <- "MIS"###Subsetting MIS vs Conversion to MIS vs Open into one Dataframe
ITTMISvsOpenNCDB <-
subset(NCDBDistalPancreatectomy, RX_HOSP_SURG_APPR_2010 == "MIS" | RX_HOSP_SURG_APPR_2010 == "Mis Converted to open" | RX_HOSP_SURG_APPR_2010 == "Open")##Subsetting MIS vs Conversion to MIS
MISvsConversionNCDB <-
subset(NCDBDistalPancreatectomy, RX_HOSP_SURG_APPR_2010 == "MIS" | RX_HOSP_SURG_APPR_2010 == "MIS Converted to open")#### Subsetting cleaned data from one dataframe to a new dataframe
MISvsConversionvsOpenNCDBDemoTable <-
ITTMISvsOpenNCDB %>%
select(RX_HOSP_SURG_APPR_2010, AGE, SEX, RACE.2, INSURANCE_STATUS.2, FACILITY_LOCATION_CD, MED_INC_QUAR_12, NO_HSD_QUAR_12, UR_CD_13, CDCC_TOTAL_BEST, ANALYTIC_STAGE_GROUP, GRADE, REGIONAL_NODES_POSITIVE, RX_SUMM_RADIATION, RX_SUMM_CHEMO, HISTOLOGY.2.2, DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS)### Recoding data in Radiationtherapy
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_RADIATION[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_RADIATION =="Beam radiation"] <- "Yes"
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_RADIATION[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_RADIATION =="None"] <- "None"
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_RADIATION[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_RADIATION =="Radiation therapy, NOS"] <- "Yes"
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_RADIATION[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_RADIATION =="Radioactive implants"] <- NA
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_RADIATION[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_RADIATION =="Radioisotopes"] <- NA
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_RADIATION[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_RADIATION =="Unknown"] <- NA### Recoding data in Chemotherapy
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO =="Chemotherapy administered, type and number of agents not documented"] <- "Yes"
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO =="Multiagent chemotherapy"] <- "Yes"
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO =="Single-agent chemotherapy"] <- "Yes"
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO =="None"] <- "No"
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO =="Chemotherapy not administered, was recommended, not administered Reason unknown"] <- "No"
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO =="Chemotherapy not administered, recommended, but refused by patient, patient's family member or guardian"] <- "No"
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO =="Chemotherapy not administered, patient died prior to planned or recommended therapy"] <- "No"
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO =="Chemotherapy not recommended/administered, contraindicated due to patient risk factors"] <- "No"
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO =="Chemotherapy recommended, unknown if administered"] <- NA
MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO[MISvsConversionvsOpenNCDBDemoTable$RX_SUMM_CHEMO =="Unknown if recommended or administered"] <- NA### Recoding data Lymph Nodes
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE <- as.character(MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE)MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="1"] <- "<5"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="2"] <- "<5"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="3"] <- "<5"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="4"] <- "<5"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="5"] <- "<5"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="6"] <- "5-10"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="7"] <- "5-10"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="8"] <- "5-10"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="9"] <- "5-10"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="10"] <- "5-10"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="11"] <- "11-15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="12"] <- "11-15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="13"] <- "11-15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="14"] <- "11-15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="15"] <- "11-15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="16"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="17"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="18"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="19"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="20"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="21"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="22"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="23"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="24"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="25"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="26"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="27"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="28"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="29"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="30"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="31"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="32"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="33"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="34"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="35"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="36"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="37"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="38"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="39"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="40"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="64"] <- ">15"
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="All nodes examined are negative"] <- NA
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="No nodes were examined"] <- NA
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="Positive aspiration of lymph node(s) was performed"] <- NA
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="Positive nodes are documented, but the number is unspecified"] <- NA
MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE[MISvsConversionvsOpenNCDBDemoTable$REGIONAL_NODES_POSITIVE =="Unknown whether nodes are positive, not applicable, not stated in patient record"] <- NA###Labeling Columns for MISvsCOnversionVsopenNCDBDemotable
var_label(MISvsConversionvsOpenNCDBDemoTable$AGE) <- "Age"
var_label(MISvsConversionvsOpenNCDBDemoTable$SEX) <- "Sex"
var_label(MISvsConversionvsOpenNCDBDemoTable$RACE.2) <- "Race"
var_label(MISvsConversionvsOpenNCDBDemoTable$INSURANCE_STATUS.2) <- "Insurance Status"
var_label(MISvsConversionvsOpenNCDBDemoTable$FACILITY_LOCATION_CD) <- "Region"
var_label(MISvsConversionvsOpenNCDBDemoTable$MED_INC_QUAR_12) <- "Income"
var_label(MISvsConversionvsOpenNCDBDemoTable$NO_HSD_QUAR_12) <- "No High School Degree"
var_label(MISvsConversionvsOpenNCDBDemoTable$CDCC_TOTAL_BEST) <- "Charlson-Deyo Disability Score"
var_label(MISvsConversionvsOpenNCDBDemoTable$UR_CD_13) <- "Population"
var_label(MISvsConversionvsOpenNCDBDemoTable$RX_HOSP_SURG_APPR_2010) <- "Surgery"
var_label(MISvsConversionvsOpenNCDBDemoTable$ANALYTIC_STAGE_GROUP) <- "Staging"
var_label(MISvsConversionvsOpenNCDBDemoTable$GRADE) <- "Tumor Grade"
var_label(MISvsConversionvsOpenNCDBDemoTable$DX_LASTCONTACT_DEATH_MONTHS) <- "Median Survival"
var_label(MISvsConversionvsOpenNCDBDemoTable$PUF_VITAL_STATUS) <- "Vital Status"MISvsOpenCarcinoma <-
subset(MISvsConversionvsOpenNCDBDemoTable, HISTOLOGY.2.2 == "Carcinoma")MISvsOpenCarcinoma\(ANALYTIC_STAGE_GROUP[MISvsOpenCarcinoma\)ANALYTIC_STAGE_GROUP ==“Stage 0”] <- NA
#Final Step to create demographic table
MISvsOpenCarcinoma %>%
tbl_summary(
by = RX_HOSP_SURG_APPR_2010,
digits = all_continuous() ~ 2,) %>%
add_p(pvalue_fun = ~style_pvalue(.x, digits = 2))%>%
bold_p() %>%
add_overall() %>%
modify_header(label ~ "**Variables**") %>%
modify_spanning_header(c("stat_0", "stat_1") ~ "**NCDB Long Term Outcomes**") %>%
bold_labels() ## There was an error in 'add_p()' for variable 'HISTOLOGY.2.2', p-value omitted:
## Error in stats::chisq.test(data[[variable]], as.factor(data[[by]])): 'x' and 'y' must have at least 2 levels| Variables | NCDB Long Term Outcomes | Open, N = 3,4981 | p-value2 | |
|---|---|---|---|---|
| Overall, N = 5,4441 | MIS, N = 1,9461 | |||
| AGE | 67.00 (60.00, 75.00) | 68.00 (60.00, 76.00) | 67.00 (59.00, 75.00) | <0.001 |
| SEX | 0.94 | |||
| Female | 2,870 (53%) | 1,024 (53%) | 1,846 (53%) | |
| Male | 2,574 (47%) | 922 (47%) | 1,652 (47%) | |
| RACE.2 | 0.35 | |||
| Black | 636 (12%) | 211 (11%) | 425 (12%) | |
| Other | 261 (4.8%) | 93 (4.8%) | 168 (4.8%) | |
| White | 4,547 (84%) | 1,642 (84%) | 2,905 (83%) | |
| INSURANCE_STATUS.2 | 0.029 | |||
| Medicaid | 268 (5.0%) | 89 (4.6%) | 179 (5.2%) | |
| Medicare | 3,055 (57%) | 1,137 (59%) | 1,918 (55%) | |
| Not Insured | 115 (2.1%) | 31 (1.6%) | 84 (2.4%) | |
| Private Insurance/Managed Care/Goverment | 1,950 (36%) | 671 (35%) | 1,279 (37%) | |
| Unknown | 56 | 18 | 38 | |
| FACILITY_LOCATION_CD | <0.001 | |||
| Midwest | 1,409 (26%) | 482 (25%) | 927 (27%) | |
| NorthEast | 1,326 (25%) | 542 (28%) | 784 (23%) | |
| South | 1,971 (37%) | 672 (35%) | 1,299 (38%) | |
| West | 659 (12%) | 226 (12%) | 433 (13%) | |
| Unknown | 79 | 24 | 55 | |
| MED_INC_QUAR_12 | 0.41 | |||
| < $38,000 | 853 (16%) | 293 (15%) | 560 (16%) | |
| >=$63,000 | 1,981 (36%) | 731 (38%) | 1,250 (36%) | |
| $38,000-$47,999 | 1,185 (22%) | 408 (21%) | 777 (22%) | |
| $48,000-$62,999 | 1,417 (26%) | 512 (26%) | 905 (26%) | |
| Unknown | 8 | 2 | 6 | |
| NO_HSD_QUAR_12 | 0.008 | |||
| <7.0% | 1,549 (28%) | 573 (29%) | 976 (28%) | |
| >=21.0% | 766 (14%) | 270 (14%) | 496 (14%) | |
| 13.0-20.9% | 1,364 (25%) | 438 (23%) | 926 (26%) | |
| 7.0-12.9% | 1,760 (32%) | 663 (34%) | 1,097 (31%) | |
| Unknown | 5 | 2 | 3 | |
| UR_CD_13 | 0.92 | |||
| Metro | 4,529 (85%) | 1,624 (86%) | 2,905 (85%) | |
| Rural | 92 (1.7%) | 31 (1.6%) | 61 (1.8%) | |
| Urban | 467 (8.8%) | 162 (8.6%) | 305 (8.9%) | |
| Urban population of 20,000 or more adjacent to a metro area | 210 (4.0%) | 73 (3.9%) | 137 (4.0%) | |
| Unknown | 146 | 56 | 90 | |
| CDCC_TOTAL_BEST | 0.37 | |||
| >=3 | 220 (4.0%) | 84 (4.3%) | 136 (3.9%) | |
| 0 | 3,253 (60%) | 1,133 (58%) | 2,120 (61%) | |
| 1 | 1,570 (29%) | 579 (30%) | 991 (28%) | |
| 2 | 401 (7.4%) | 150 (7.7%) | 251 (7.2%) | |
| ANALYTIC_STAGE_GROUP | 0.001 | |||
| Stage 0 | 148 (2.9%) | 56 (3.0%) | 92 (2.9%) | |
| Stage I | 1,064 (21%) | 373 (20%) | 691 (21%) | |
| Stage II | 3,691 (73%) | 1,379 (75%) | 2,312 (72%) | |
| Stage III | 161 (3.2%) | 36 (2.0%) | 125 (3.9%) | |
| Unknown | 380 | 102 | 278 | |
| GRADE | 0.97 | |||
| Moderately differentiated | 2,577 (54%) | 935 (55%) | 1,642 (54%) | |
| Poorly differentiated | 1,460 (31%) | 529 (31%) | 931 (31%) | |
| Undifferentiated | 82 (1.7%) | 30 (1.8%) | 52 (1.7%) | |
| Well differentiated | 612 (13%) | 216 (13%) | 396 (13%) | |
| Unknown | 713 | 236 | 477 | |
| REGIONAL_NODES_POSITIVE | 0.87 | |||
| <5 | 2,250 (88%) | 824 (88%) | 1,426 (87%) | |
| >15 | 12 (0.5%) | 3 (0.3%) | 9 (0.6%) | |
| 11-15 | 49 (1.9%) | 17 (1.8%) | 32 (2.0%) | |
| 5-10 | 256 (10.0%) | 91 (9.7%) | 165 (10%) | |
| Unknown | 2,877 | 1,011 | 1,866 | |
| RX_SUMM_RADIATION | 0.001 | |||
| None | 4,063 (75%) | 1,499 (78%) | 2,564 (74%) | |
| Yes | 1,343 (25%) | 429 (22%) | 914 (26%) | |
| Unknown | 38 | 18 | 20 | |
| RX_SUMM_CHEMO | 3,550 (69%) | 1,268 (69%) | 2,282 (68%) | 0.80 |
| Unknown | 266 | 103 | 163 | |
| HISTOLOGY.2.2 | ||||
| Carcinoma | 5,444 (100%) | 1,946 (100%) | 3,498 (100%) | |
| DX_LASTCONTACT_DEATH_MONTHS | 20.37 (10.81, 35.22) | 21.13 (11.76, 34.27) | 19.73 (10.28, 35.82) | 0.051 |
| Unknown | 863 | 387 | 476 | |
| PUF_VITAL_STATUS | <0.001 | |||
| Alive | 1,689 (37%) | 657 (42%) | 1,032 (34%) | |
| Dead | 2,892 (63%) | 902 (58%) | 1,990 (66%) | |
| Unknown | 863 | 387 | 476 | |
|
1
Statistics presented: Median (IQR); n (%)
2
Statistical tests performed: Wilcoxon rank-sum test; chi-square test of independence; Fisher's exact test
|
||||
###No high school degree blanks to NA's
MISvsOpenCarcinoma$NO_HSD_QUAR_12[MISvsOpenCarcinoma$NO_HSD_QUAR_12 ==""] <- NA#####Survival Analysis Ensure that vital status is labeled as 1= Alive and 2=Death
MISvsOpenCarcinoma$PUF_VITAL_STATUS[MISvsOpenCarcinoma$PUF_VITAL_STATUS == "Dead"] <- 2
MISvsOpenCarcinoma$PUF_VITAL_STATUS[MISvsOpenCarcinoma$PUF_VITAL_STATUS == "Alive"] <- 1###pufvitalstatus should be numeric
MISvsOpenCarcinoma$PUF_VITAL_STATUS <- as.numeric(MISvsOpenCarcinoma$PUF_VITAL_STATUS)
###RX_HOSP_SURG_APPR_2010 should be numeric
MISvsOpenCarcinoma$DX_LASTCONTACT_DEATH_MONTHS <- as.numeric(MISvsOpenCarcinoma$DX_LASTCONTACT_DEATH_MONTHS)MISvsOpenCarcinoma$ANALYTIC_STAGE_GROUP <- as.factor(MISvsOpenCarcinoma$ANALYTIC_STAGE_GROUP)
MISvsOpenCarcinoma$ANALYTIC_STAGE_GROUP = relevel(MISvsOpenCarcinoma$ANALYTIC_STAGE_GROUP, ref="Stage 0")### Univariant Survival Neoadj
UVSurv <-
MISvsOpenCarcinoma %>%
select(RX_HOSP_SURG_APPR_2010, RACE.2, INSURANCE_STATUS.2, FACILITY_LOCATION_CD, MED_INC_QUAR_12, NO_HSD_QUAR_12, ANALYTIC_STAGE_GROUP, GRADE, RX_SUMM_CHEMO, RX_SUMM_RADIATION, DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) %>%
tbl_uvregression(
method = coxph,
y = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS),
exponentiate = TRUE) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()
###Multivariant survival Neoadj
MVSurv <-
coxph(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ RX_HOSP_SURG_APPR_2010 + RACE.2 + INSURANCE_STATUS.2 + FACILITY_LOCATION_CD + MED_INC_QUAR_12 + NO_HSD_QUAR_12 + ANALYTIC_STAGE_GROUP + GRADE + RX_SUMM_CHEMO + RX_SUMM_RADIATION,
data = MISvsOpenCarcinoma
) %>%
tbl_regression(exponentiate = T
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()###Merged Neo Univariant and Multivariant
tbl_merge(
list(UVSurv, MVSurv),
tab_spanner = c("**Univariable**", "**Multivariable**")
) %>%
bold_labels() %>%
italicize_levels()| Characteristic | Univariable | Multivariable | |||||
|---|---|---|---|---|---|---|---|
| N | HR1 | 95% CI1 | p-value | HR1 | 95% CI1 | p-value | |
| RX_HOSP_SURG_APPR_2010 | 4,581 | ||||||
| MIS | — | — | — | — | |||
| Open | 1.16 | 1.07, 1.26 | <0.001 | 1.19 | 1.08, 1.30 | <0.001 | |
| RACE.2 | 4,581 | ||||||
| Black | — | — | — | — | |||
| Other | 0.68 | 0.55, 0.84 | <0.001 | 0.82 | 0.63, 1.07 | 0.14 | |
| White | 0.97 | 0.86, 1.08 | 0.5 | 0.98 | 0.86, 1.11 | 0.7 | |
| INSURANCE_STATUS.2 | 4,535 | ||||||
| Medicaid | — | — | — | — | |||
| Medicare | 1.07 | 0.90, 1.27 | 0.5 | 1.01 | 0.82, 1.24 | >0.9 | |
| Not Insured | 0.95 | 0.70, 1.28 | 0.7 | 0.95 | 0.67, 1.34 | 0.8 | |
| Private Insurance/Managed Care/Goverment | 0.76 | 0.64, 0.91 | 0.003 | 0.78 | 0.63, 0.96 | 0.019 | |
| FACILITY_LOCATION_CD | 4,514 | ||||||
| Midwest | — | — | — | — | |||
| NorthEast | 0.82 | 0.74, 0.91 | <0.001 | 0.86 | 0.76, 0.97 | 0.011 | |
| South | 1.06 | 0.97, 1.17 | 0.2 | 1.08 | 0.97, 1.20 | 0.2 | |
| West | 0.92 | 0.81, 1.05 | 0.2 | 1.03 | 0.89, 1.19 | 0.7 | |
| MED_INC_QUAR_12 | 4,574 | ||||||
| < $38,000 | — | — | — | — | |||
| >=$63,000 | 0.76 | 0.69, 0.85 | <0.001 | 0.75 | 0.64, 0.89 | <0.001 | |
| $38,000-$47,999 | 0.93 | 0.82, 1.04 | 0.2 | 0.90 | 0.78, 1.04 | 0.2 | |
| $48,000-$62,999 | 0.84 | 0.74, 0.94 | 0.002 | 0.84 | 0.72, 0.97 | 0.019 | |
| NO_HSD_QUAR_12 | 4,576 | ||||||
| <7.0% | — | — | — | — | |||
| >=21.0% | 1.26 | 1.12, 1.41 | <0.001 | 0.97 | 0.81, 1.16 | 0.8 | |
| 13.0-20.9% | 1.17 | 1.06, 1.30 | 0.002 | 0.98 | 0.85, 1.13 | 0.8 | |
| 7.0-12.9% | 1.12 | 1.02, 1.23 | 0.023 | 1.08 | 0.96, 1.22 | 0.2 | |
| ANALYTIC_STAGE_GROUP | 4,256 | ||||||
| Stage 0 | — | — | — | — | |||
| Stage I | 4.04 | 2.41, 6.76 | <0.001 | 5.09 | 1.27, 20.5 | 0.022 | |
| Stage II | 8.32 | 5.01, 13.8 | <0.001 | 10.3 | 2.55, 41.2 | 0.001 | |
| Stage III | 10.2 | 5.92, 17.5 | <0.001 | 14.2 | 3.48, 58.1 | <0.001 | |
| GRADE | 4,006 | ||||||
| Moderately differentiated | — | — | — | — | |||
| Poorly differentiated | 1.36 | 1.25, 1.48 | <0.001 | 1.37 | 1.25, 1.50 | <0.001 | |
| Undifferentiated | 1.31 | 0.97, 1.77 | 0.082 | 1.16 | 0.81, 1.67 | 0.4 | |
| Well differentiated | 0.59 | 0.51, 0.67 | <0.001 | 0.65 | 0.56, 0.75 | <0.001 | |
| RX_SUMM_CHEMO | 4,351 | ||||||
| No | — | — | — | — | |||
| Yes | 0.91 | 0.84, 0.99 | 0.020 | 0.67 | 0.61, 0.74 | <0.001 | |
| RX_SUMM_RADIATION | 4,546 | ||||||
| None | — | — | — | — | |||
| Yes | 0.93 | 0.85, 1.01 | 0.076 | 1.01 | 0.91, 1.11 | >0.9 | |
|
1
HR = Hazard Ratio, CI = Confidence Interval
|
|||||||
survfit(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ RX_HOSP_SURG_APPR_2010, data = MISvsOpenCarcinoma)## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~
## RX_HOSP_SURG_APPR_2010, data = MISvsOpenCarcinoma)
##
## 863 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## RX_HOSP_SURG_APPR_2010=MIS 1559 902 27.6 25.7 29.7
## RX_HOSP_SURG_APPR_2010=Open 3022 1990 23.2 22.3 24.6survfit(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ RACE.2, data = MISvsOpenCarcinoma)## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~
## RACE.2, data = MISvsOpenCarcinoma)
##
## 863 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## RACE.2=Black 553 357 23.3 21.1 28.2
## RACE.2=Other 222 111 34.2 28.2 45.3
## RACE.2=White 3806 2424 24.5 23.4 25.5survfit(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ INSURANCE_STATUS.2, data = MISvsOpenCarcinoma)## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~
## INSURANCE_STATUS.2, data = MISvsOpenCarcinoma)
##
## 909 observations deleted due to missingness
## n events median
## INSURANCE_STATUS.2=Medicaid 221 140 23.8
## INSURANCE_STATUS.2=Medicare 2553 1728 22.1
## INSURANCE_STATUS.2=Not Insured 97 61 23.4
## INSURANCE_STATUS.2=Private Insurance/Managed Care/Goverment 1664 938 30.0
## 0.95LCL 0.95UCL
## INSURANCE_STATUS.2=Medicaid 20.1 28.0
## INSURANCE_STATUS.2=Medicare 21.1 23.3
## INSURANCE_STATUS.2=Not Insured 19.4 35.3
## INSURANCE_STATUS.2=Private Insurance/Managed Care/Goverment 27.9 32.8survfit(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ FACILITY_LOCATION_CD, data = MISvsOpenCarcinoma)## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~
## FACILITY_LOCATION_CD, data = MISvsOpenCarcinoma)
##
## 930 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## FACILITY_LOCATION_CD=Midwest 1201 788 23.3 22.0 25.0
## FACILITY_LOCATION_CD=NorthEast 1128 674 29.4 26.7 33.0
## FACILITY_LOCATION_CD=South 1633 1074 21.9 20.7 23.5
## FACILITY_LOCATION_CD=West 552 342 25.2 23.2 29.0survfit(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ MED_INC_QUAR_12, data = MISvsOpenCarcinoma)## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~
## MED_INC_QUAR_12, data = MISvsOpenCarcinoma)
##
## 870 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## MED_INC_QUAR_12=< $38,000 720 484 21.6 19.6 23.5
## MED_INC_QUAR_12=>=$63,000 1677 1004 28.1 25.9 30.1
## MED_INC_QUAR_12=$38,000-$47,999 1003 663 22.0 20.6 25.1
## MED_INC_QUAR_12=$48,000-$62,999 1174 737 24.6 23.1 27.7survfit(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ NO_HSD_QUAR_12, data = MISvsOpenCarcinoma)## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~
## NO_HSD_QUAR_12, data = MISvsOpenCarcinoma)
##
## 868 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## NO_HSD_QUAR_12=<7.0% 1304 781 28.4 26.1 31.0
## NO_HSD_QUAR_12=>=21.0% 659 430 22.8 20.8 24.9
## NO_HSD_QUAR_12=13.0-20.9% 1146 744 23.1 20.8 25.7
## NO_HSD_QUAR_12=7.0-12.9% 1467 934 24.1 22.8 25.7survfit(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ ANALYTIC_STAGE_GROUP, data = MISvsOpenCarcinoma)## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~
## ANALYTIC_STAGE_GROUP, data = MISvsOpenCarcinoma)
##
## 1188 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## ANALYTIC_STAGE_GROUP=Stage 0 118 15 NA NA NA
## ANALYTIC_STAGE_GROUP=Stage I 921 414 48.5 42.2 59.0
## ANALYTIC_STAGE_GROUP=Stage II 3083 2113 22.4 21.6 23.3
## ANALYTIC_STAGE_GROUP=Stage III 134 100 19.8 18.2 24.5survfit(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ GRADE, data = MISvsOpenCarcinoma)## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~
## GRADE, data = MISvsOpenCarcinoma)
##
## 1438 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## GRADE=Moderately differentiated 2176 1414 25.2 23.9 26.9
## GRADE=Poorly differentiated 1244 935 18.1 16.7 19.1
## GRADE=Undifferentiated 68 43 14.4 12.0 26.0
## GRADE=Well differentiated 518 247 47.6 43.4 55.5survfit(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ REGIONAL_NODES_POSITIVE, data = MISvsOpenCarcinoma)## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~
## REGIONAL_NODES_POSITIVE, data = MISvsOpenCarcinoma)
##
## 3293 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## REGIONAL_NODES_POSITIVE=<5 1896 1385 20.40 19.32 21.4
## REGIONAL_NODES_POSITIVE=>15 11 10 9.66 4.86 NA
## REGIONAL_NODES_POSITIVE=11-15 33 22 18.63 9.79 NA
## REGIONAL_NODES_POSITIVE=5-10 211 174 16.59 15.01 20.2survfit(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ RX_SUMM_CHEMO, data = MISvsOpenCarcinoma)## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~
## RX_SUMM_CHEMO, data = MISvsOpenCarcinoma)
##
## 1093 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## RX_SUMM_CHEMO=No 1390 859 21.0 19.2 23.8
## RX_SUMM_CHEMO=Yes 2961 1884 25.7 24.7 26.9survfit(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ RX_SUMM_RADIATION, data = MISvsOpenCarcinoma)## Call: survfit(formula = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~
## RX_SUMM_RADIATION, data = MISvsOpenCarcinoma)
##
## 898 observations deleted due to missingness
## n events median 0.95LCL 0.95UCL
## RX_SUMM_RADIATION=None 3371 2096 23.7 22.7 25.1
## RX_SUMM_RADIATION=Yes 1175 772 26.4 25.1 28.9MISvsOpenCarcinomaStage1<-
subset(MISvsOpenCarcinoma, ANALYTIC_STAGE_GROUP == "Stage I")
MISvsOpenCarcinomaStage2<-
subset(MISvsOpenCarcinoma, ANALYTIC_STAGE_GROUP == "Stage II")
MISvsOpenCarcinomaStage3<-
subset(MISvsOpenCarcinoma, ANALYTIC_STAGE_GROUP == "Stage III")### Univariant Survival Neoadj Stage I
UVSurvstage1 <-
MISvsOpenCarcinomaStage1 %>%
select(RX_HOSP_SURG_APPR_2010, RACE.2, INSURANCE_STATUS.2, FACILITY_LOCATION_CD, MED_INC_QUAR_12, NO_HSD_QUAR_12, ANALYTIC_STAGE_GROUP, GRADE, RX_SUMM_CHEMO, RX_SUMM_RADIATION, DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) %>%
tbl_uvregression(
method = coxph,
y = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS),
exponentiate = TRUE) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()
###Multivariant survival Neoadj
MVSurvStage1 <-
coxph(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ RX_HOSP_SURG_APPR_2010 + RACE.2 + INSURANCE_STATUS.2 + FACILITY_LOCATION_CD + MED_INC_QUAR_12 + NO_HSD_QUAR_12 + GRADE + RX_SUMM_CHEMO + RX_SUMM_RADIATION,
data = MISvsOpenCarcinomaStage1
) %>%
tbl_regression(exponentiate = T
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()###Merged Neo Univariant and Multivariant
tbl_merge(
list(UVSurvstage1, MVSurvStage1),
tab_spanner = c("**Univariable**", "**Multivariable**")
) %>%
bold_labels() %>%
italicize_levels()| Characteristic | Univariable | Multivariable | |||||
|---|---|---|---|---|---|---|---|
| N | HR1 | 95% CI1 | p-value | HR1 | 95% CI1 | p-value | |
| RX_HOSP_SURG_APPR_2010 | 921 | ||||||
| MIS | — | — | — | — | |||
| Open | 1.22 | 0.99, 1.51 | 0.066 | 1.30 | 1.02, 1.65 | 0.035 | |
| RACE.2 | 921 | ||||||
| Black | — | — | — | — | |||
| Other | 0.47 | 0.25, 0.87 | 0.016 | 0.56 | 0.28, 1.11 | 0.10 | |
| White | 1.11 | 0.82, 1.51 | 0.5 | 1.17 | 0.83, 1.67 | 0.4 | |
| INSURANCE_STATUS.2 | 911 | ||||||
| Medicaid | — | — | — | — | |||
| Medicare | 1.47 | 0.91, 2.37 | 0.11 | 1.26 | 0.73, 2.18 | 0.4 | |
| Not Insured | 1.10 | 0.49, 2.44 | 0.8 | 0.93 | 0.35, 2.45 | 0.9 | |
| Private Insurance/Managed Care/Goverment | 0.68 | 0.41, 1.12 | 0.13 | 0.60 | 0.34, 1.06 | 0.076 | |
| FACILITY_LOCATION_CD | 889 | ||||||
| Midwest | — | — | — | — | |||
| NorthEast | 0.93 | 0.70, 1.24 | 0.6 | 1.04 | 0.75, 1.44 | 0.8 | |
| South | 1.15 | 0.89, 1.47 | 0.3 | 1.11 | 0.83, 1.47 | 0.5 | |
| West | 1.18 | 0.86, 1.60 | 0.3 | 1.21 | 0.85, 1.72 | 0.3 | |
| MED_INC_QUAR_12 | 919 | ||||||
| < $38,000 | — | — | — | — | |||
| >=$63,000 | 0.76 | 0.57, 1.00 | 0.052 | 0.87 | 0.57, 1.34 | 0.5 | |
| $38,000-$47,999 | 0.95 | 0.69, 1.29 | 0.7 | 0.95 | 0.65, 1.39 | 0.8 | |
| $48,000-$62,999 | 0.94 | 0.70, 1.26 | 0.7 | 1.12 | 0.76, 1.65 | 0.6 | |
| NO_HSD_QUAR_12 | 919 | ||||||
| <7.0% | — | — | — | — | |||
| >=21.0% | 1.44 | 1.06, 1.95 | 0.019 | 1.18 | 0.76, 1.85 | 0.5 | |
| 13.0-20.9% | 1.33 | 1.02, 1.73 | 0.035 | 1.24 | 0.85, 1.79 | 0.3 | |
| 7.0-12.9% | 1.21 | 0.94, 1.58 | 0.14 | 1.12 | 0.82, 1.55 | 0.5 | |
| ANALYTIC_STAGE_GROUP | 921 | ||||||
| Stage I | — | — | |||||
| GRADE | 780 | ||||||
| Moderately differentiated | — | — | — | — | |||
| Poorly differentiated | 1.50 | 1.18, 1.89 | <0.001 | 1.47 | 1.14, 1.89 | 0.003 | |
| Undifferentiated | 1.82 | 0.90, 3.70 | 0.10 | 2.08 | 0.96, 4.50 | 0.063 | |
| Well differentiated | 0.53 | 0.40, 0.71 | <0.001 | 0.55 | 0.40, 0.76 | <0.001 | |
| RX_SUMM_CHEMO | 883 | ||||||
| No | — | — | — | — | |||
| Yes | 1.08 | 0.88, 1.32 | 0.5 | 0.83 | 0.65, 1.07 | 0.15 | |
| RX_SUMM_RADIATION | 919 | ||||||
| None | — | — | — | — | |||
| Yes | 1.16 | 0.92, 1.45 | 0.2 | 1.26 | 0.95, 1.67 | 0.11 | |
|
1
HR = Hazard Ratio, CI = Confidence Interval
|
|||||||
### Univariant Survival Neoadj Stage II
UVSurvstage2 <-
MISvsOpenCarcinomaStage2 %>%
select(RX_HOSP_SURG_APPR_2010, RACE.2, INSURANCE_STATUS.2, FACILITY_LOCATION_CD, MED_INC_QUAR_12, NO_HSD_QUAR_12, GRADE, RX_SUMM_CHEMO, RX_SUMM_RADIATION, DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) %>%
tbl_uvregression(
method = coxph,
y = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS),
exponentiate = TRUE) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()
###Multivariant survival Neoadj
MVSurvStage2 <-
coxph(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ RX_HOSP_SURG_APPR_2010 + RACE.2 + INSURANCE_STATUS.2 + FACILITY_LOCATION_CD + MED_INC_QUAR_12 + NO_HSD_QUAR_12 + GRADE + RX_SUMM_CHEMO + RX_SUMM_RADIATION,
data = MISvsOpenCarcinomaStage2
) %>%
tbl_regression(exponentiate = T
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()###Merged Neo Univariant and Multivariant
tbl_merge(
list(UVSurvstage2, MVSurvStage2),
tab_spanner = c("**Univariable**", "**Multivariable**")
) %>%
bold_labels() %>%
italicize_levels()| Characteristic | Univariable | Multivariable | |||||
|---|---|---|---|---|---|---|---|
| N | HR1 | 95% CI1 | p-value | HR1 | 95% CI1 | p-value | |
| RX_HOSP_SURG_APPR_2010 | 3,083 | ||||||
| MIS | — | — | — | — | |||
| Open | 1.16 | 1.06, 1.27 | 0.001 | 1.17 | 1.06, 1.29 | 0.002 | |
| RACE.2 | 3,083 | ||||||
| Black | — | — | — | — | |||
| Other | 0.76 | 0.59, 0.99 | 0.039 | 0.94 | 0.70, 1.25 | 0.7 | |
| White | 0.99 | 0.87, 1.13 | 0.9 | 0.99 | 0.85, 1.14 | 0.8 | |
| INSURANCE_STATUS.2 | 3,052 | ||||||
| Medicaid | — | — | — | — | |||
| Medicare | 1.04 | 0.85, 1.29 | 0.7 | 1.02 | 0.81, 1.28 | 0.9 | |
| Not Insured | 1.06 | 0.74, 1.52 | 0.7 | 1.02 | 0.70, 1.51 | >0.9 | |
| Private Insurance/Managed Care/Goverment | 0.83 | 0.67, 1.03 | 0.084 | 0.85 | 0.67, 1.07 | 0.2 | |
| FACILITY_LOCATION_CD | 3,063 | ||||||
| Midwest | — | — | — | — | |||
| NorthEast | 0.80 | 0.71, 0.90 | <0.001 | 0.83 | 0.73, 0.95 | 0.005 | |
| South | 1.11 | 1.00, 1.24 | 0.052 | 1.06 | 0.94, 1.20 | 0.3 | |
| West | 0.98 | 0.85, 1.15 | 0.8 | 0.98 | 0.83, 1.16 | 0.9 | |
| MED_INC_QUAR_12 | 3,081 | ||||||
| < $38,000 | — | — | — | — | |||
| >=$63,000 | 0.75 | 0.66, 0.85 | <0.001 | 0.71 | 0.59, 0.86 | <0.001 | |
| $38,000-$47,999 | 0.90 | 0.79, 1.03 | 0.14 | 0.86 | 0.73, 1.00 | 0.053 | |
| $48,000-$62,999 | 0.84 | 0.73, 0.96 | 0.009 | 0.76 | 0.64, 0.89 | 0.001 | |
| NO_HSD_QUAR_12 | 3,082 | ||||||
| <7.0% | — | — | — | — | |||
| >=21.0% | 1.21 | 1.05, 1.39 | 0.007 | 0.91 | 0.74, 1.11 | 0.3 | |
| 13.0-20.9% | 1.12 | 0.99, 1.26 | 0.064 | 0.93 | 0.79, 1.09 | 0.4 | |
| 7.0-12.9% | 1.09 | 0.97, 1.21 | 0.14 | 1.06 | 0.92, 1.21 | 0.4 | |
| GRADE | 2,835 | ||||||
| Moderately differentiated | — | — | — | — | |||
| Poorly differentiated | 1.31 | 1.19, 1.44 | <0.001 | 1.35 | 1.22, 1.49 | <0.001 | |
| Undifferentiated | 1.06 | 0.71, 1.59 | 0.8 | 0.96 | 0.62, 1.50 | 0.9 | |
| Well differentiated | 0.73 | 0.62, 0.87 | <0.001 | 0.69 | 0.58, 0.83 | <0.001 | |
| RX_SUMM_CHEMO | 2,907 | ||||||
| No | — | — | — | — | |||
| Yes | 0.63 | 0.57, 0.70 | <0.001 | 0.63 | 0.56, 0.70 | <0.001 | |
| RX_SUMM_RADIATION | 3,059 | ||||||
| None | — | — | — | — | |||
| Yes | 0.82 | 0.75, 0.91 | <0.001 | 0.99 | 0.89, 1.11 | 0.9 | |
|
1
HR = Hazard Ratio, CI = Confidence Interval
|
|||||||
### Univariant Survival Neoadj Stage III
UVSurvstage3 <-
MISvsOpenCarcinomaStage3 %>%
select(RX_HOSP_SURG_APPR_2010, RACE.2, INSURANCE_STATUS.2, FACILITY_LOCATION_CD, MED_INC_QUAR_12, NO_HSD_QUAR_12, GRADE, RX_SUMM_CHEMO, RX_SUMM_RADIATION, DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) %>%
tbl_uvregression(
method = coxph,
y = Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS),
exponentiate = TRUE) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()
###Multivariant survival Neoadj
MVSurvStage3 <-
coxph(Surv(DX_LASTCONTACT_DEATH_MONTHS, PUF_VITAL_STATUS) ~ RX_HOSP_SURG_APPR_2010 + RACE.2 + INSURANCE_STATUS.2 + FACILITY_LOCATION_CD + MED_INC_QUAR_12 + NO_HSD_QUAR_12 + GRADE + RX_SUMM_CHEMO + RX_SUMM_RADIATION,
data = MISvsOpenCarcinomaStage3
) %>%
tbl_regression(exponentiate = T
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()###Merged Neo Univariant and Multivariant
tbl_merge(
list(UVSurvstage3, MVSurvStage3),
tab_spanner = c("**Univariable**", "**Multivariable**")
) %>%
bold_labels() %>%
italicize_levels()| Characteristic | Univariable | Multivariable | |||||
|---|---|---|---|---|---|---|---|
| N | HR1 | 95% CI1 | p-value | HR1 | 95% CI1 | p-value | |
| RX_HOSP_SURG_APPR_2010 | 134 | ||||||
| MIS | — | — | — | — | |||
| Open | 1.05 | 0.64, 1.72 | 0.8 | 1.06 | 0.53, 2.11 | 0.9 | |
| RACE.2 | 134 | ||||||
| Black | — | — | — | — | |||
| Other | 0.47 | 0.14, 1.61 | 0.2 | 1.18 | 0.19, 7.42 | 0.9 | |
| White | 0.47 | 0.28, 0.81 | 0.007 | 0.30 | 0.13, 0.69 | 0.005 | |
| INSURANCE_STATUS.2 | 133 | ||||||
| Medicaid | — | — | — | — | |||
| Medicare | 0.73 | 0.31, 1.72 | 0.5 | 0.19 | 0.05, 0.72 | 0.014 | |
| Not Insured | 0.58 | 0.12, 2.92 | 0.5 | 0.13 | 0.02, 1.07 | 0.058 | |
| Private Insurance/Managed Care/Goverment | 0.62 | 0.26, 1.46 | 0.3 | 0.22 | 0.05, 0.91 | 0.036 | |
| FACILITY_LOCATION_CD | 134 | ||||||
| Midwest | — | — | — | — | |||
| NorthEast | 1.07 | 0.60, 1.92 | 0.8 | 0.95 | 0.38, 2.40 | >0.9 | |
| South | 1.16 | 0.68, 1.99 | 0.6 | 0.94 | 0.42, 2.09 | 0.9 | |
| West | 0.70 | 0.35, 1.39 | 0.3 | 0.56 | 0.20, 1.60 | 0.3 | |
| MED_INC_QUAR_12 | 133 | ||||||
| < $38,000 | — | — | — | — | |||
| >=$63,000 | 1.21 | 0.59, 2.49 | 0.6 | 1.16 | 0.33, 4.11 | 0.8 | |
| $38,000-$47,999 | 1.76 | 0.81, 3.82 | 0.2 | 2.54 | 0.77, 8.34 | 0.13 | |
| $48,000-$62,999 | 1.89 | 0.87, 4.09 | 0.11 | 2.14 | 0.63, 7.24 | 0.2 | |
| NO_HSD_QUAR_12 | 133 | ||||||
| <7.0% | — | — | — | — | |||
| >=21.0% | 1.62 | 0.89, 2.95 | 0.11 | 0.68 | 0.23, 2.05 | 0.5 | |
| 13.0-20.9% | 1.32 | 0.74, 2.34 | 0.3 | 0.86 | 0.31, 2.36 | 0.8 | |
| 7.0-12.9% | 1.40 | 0.84, 2.33 | 0.2 | 1.66 | 0.81, 3.39 | 0.2 | |
| GRADE | 99 | ||||||
| Moderately differentiated | — | — | — | — | |||
| Poorly differentiated | 1.24 | 0.77, 1.99 | 0.4 | 1.42 | 0.77, 2.62 | 0.3 | |
| Undifferentiated | 1.47 | 0.35, 6.12 | 0.6 | 0.95 | 0.18, 5.11 | >0.9 | |
| Well differentiated | 0.61 | 0.30, 1.27 | 0.2 | 0.45 | 0.17, 1.16 | 0.10 | |
| RX_SUMM_CHEMO | 129 | ||||||
| No | — | — | — | — | |||
| Yes | 0.39 | 0.25, 0.63 | <0.001 | 0.43 | 0.19, 0.94 | 0.035 | |
| RX_SUMM_RADIATION | 132 | ||||||
| None | — | — | — | — | |||
| Yes | 0.50 | 0.33, 0.74 | <0.001 | 0.78 | 0.39, 1.55 | 0.5 | |
|
1
HR = Hazard Ratio, CI = Confidence Interval
|
|||||||
# Important packages to load in
library(dplyr)
library(gtsummary)
library(survival)
library(labelled)
library(tidyverse)
library(broom)
library(ggplot2)
library(survminer)NSQIPShortTermOutcomes <- read.csv ("PANFINAL.csv", header = TRUE, sep = "," )
unique(NSQIPShortTermOutcomes$PAN_MALIG_HISTOLOGIC)## [1] "Other type" "Pancreatic adenocarcinoma"
## [3] "Duodenal carcinoma" "N/A"
## [5] "Neuroendocrine-nonfunctioning" "Neuroendocrine-functioning"
## [7] "Ampullary carcinoma" "Distal cholangiocarcinoma"
## [9] "IPMN-invasive" "Unknown"
## [11] "Cystadenocarcinoma"##Creating BMI column from heigh, weight
NSQIPShortTermOutcomes$BMI <- (NSQIPShortTermOutcomes$WEIGHT * 703) / (NSQIPShortTermOutcomes$HEIGHT * NSQIPShortTermOutcomes$HEIGHT)NSQIPShortTermOutcomes <-
subset(NSQIPShortTermOutcomes, CPT == "48140" | CPT == "48145")NSQIPShortTermOutcomes <-
subset(NSQIPShortTermOutcomes, PAN_MALIG_HISTOLOGIC == "Pancreatic adenocarcinoma")NSQIPShortTermOutcomes$PAN_APPROACH[NSQIPShortTermOutcomes$PAN_APPROACH =="Open (planned)"] <- "Open"
NSQIPShortTermOutcomes$PAN_APPROACH[NSQIPShortTermOutcomes$PAN_APPROACH =="NOTES w/ unplanned conversion to open"] <- "MIS"
NSQIPShortTermOutcomes$PAN_APPROACH[NSQIPShortTermOutcomes$PAN_APPROACH =="Laparoscopic"] <- "MIS"
NSQIPShortTermOutcomes$PAN_APPROACH[NSQIPShortTermOutcomes$PAN_APPROACH =="Laparoscopic w/ open assist"] <- "MIS Converted to Open"
NSQIPShortTermOutcomes$PAN_APPROACH[NSQIPShortTermOutcomes$PAN_APPROACH =="Laparoscopic w/ unplanned conversion to open"] <- "MIS"
NSQIPShortTermOutcomes$PAN_APPROACH[NSQIPShortTermOutcomes$PAN_APPROACH =="Robotic"] <- "MIS"
NSQIPShortTermOutcomes$PAN_APPROACH[NSQIPShortTermOutcomes$PAN_APPROACH =="Robotic w/ unplanned conversion to open"] <- "MIS"
NSQIPShortTermOutcomes$PAN_APPROACH[NSQIPShortTermOutcomes$PAN_APPROACH =="Robotic w/ open assist"] <- "MIS Converted to Open"
NSQIPShortTermOutcomes$PAN_APPROACH[NSQIPShortTermOutcomes$PAN_APPROACH =="Other"] <- NA
NSQIPShortTermOutcomes$PAN_APPROACH[NSQIPShortTermOutcomes$PAN_APPROACH =="Other MIS approach"] <- "MIS"
NSQIPShortTermOutcomes$PAN_APPROACH[NSQIPShortTermOutcomes$PAN_APPROACH =="Other MIS approach w/ open assist"] <- "MIS Converted to Open"
NSQIPShortTermOutcomes$PAN_APPROACH[NSQIPShortTermOutcomes$PAN_APPROACH =="Hybrid"] <- "MIS"
NSQIPShortTermOutcomes$PAN_APPROACH[NSQIPShortTermOutcomes$PAN_APPROACH =="Hybrid w/ open assist"] <- "MIS Converted to Open"NSQIPShortTermOutcomes$PRSEPIS[NSQIPShortTermOutcomes$PRSEPIS == "SIRS"] <- "Yes"
NSQIPShortTermOutcomes$PRSEPIS[NSQIPShortTermOutcomes$PRSEPIS == "Septic Shock"] <- "Yes"
NSQIPShortTermOutcomes$PRSEPIS[NSQIPShortTermOutcomes$PRSEPIS == "Sepsis"] <- "Yes"
NSQIPShortTermOutcomes$ASACLAS[NSQIPShortTermOutcomes$ASACLAS =="None assigned"] <- "Unknown"NSQIPShortTermOutcomes$RACE_NEW[NSQIPShortTermOutcomes$RACE_NEW == "American Indian or Alaska Native"] <- "Other"
NSQIPShortTermOutcomes$RACE_NEW[NSQIPShortTermOutcomes$RACE_NEW == "Asian"] <- "Other"
NSQIPShortTermOutcomes$RACE_NEW[NSQIPShortTermOutcomes$RACE_NEW == "Native Hawaiian or Pacific Islander"] <- "Other"
NSQIPShortTermOutcomes$RACE_NEW[NSQIPShortTermOutcomes$RACE_NEW == "Black or African American"] <- "Black"
NSQIPShortTermOutcomes$RACE_NEW[NSQIPShortTermOutcomes$RACE_NEW == "Unknown/Not Reported"] <- NANSQIPShortTermOutcomes$Age <- as.numeric(NSQIPShortTermOutcomes$Age)## Warning: NAs introduced by coercionNSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == -99] <- "No"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 0] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 1] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 2] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 3] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 4] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 5] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 6] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 7] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 8] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 9] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 10] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 11] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 12] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 13] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 14] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 15] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 16] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 17] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 18] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 19] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 20] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 21] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 22] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 23] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 24] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 25] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 26] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 27] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 28] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 29] <- "Yes"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == 30] <- "Yes"###Recoding Variables in DopertoD numbers > yes and any NA's to No
NSQIPShortTermOutcomes[NSQIPShortTermOutcomes$DOpertoD =="NA"]$DOpertoD <- "No"
NSQIPShortTermOutcomes$DOpertoD[NSQIPShortTermOutcomes$DOpertoD == NA] <- "No"
NSQIPShortTermOutcomes$DOpertoD <- as.character(NSQIPShortTermOutcomes$DOpertoD)
NSQIPShortTermOutcomes$DOpertoD[is.na(NSQIPShortTermOutcomes$DOpertoD)] <- "No"#Ifelse function to create new column for serious complication and any complication
MISITTDemoTable <-
mutate(NSQIPShortTermOutcomes, SeriousComplication = ifelse(CDARREST == "Cardiac Arrest Requiring CPR", "Yes",
ifelse(CDMI == "Myocardial Infarction", "Yes",
ifelse(OUPNEUMO == "Pneumonia", "Yes",
ifelse(RENAINSF == "Progressive Renal Insufficiency", "Yes",
ifelse(OPRENAFL == "Acute Renal Failure", "Yes",
ifelse(PULEMBOL == "Pulmonary Embolism", "Yes",
ifelse(OTHDVT == "DVT Requiring Therapy", "Yes",
ifelse(RETURNOR == "Yes", "Yes",
ifelse(ORGSPCSSI == "Organ/Space SSI", "Yes",
ifelse(PRSEPIS == "Yes", "Yes",
ifelse(REINTUB == "Unplanned Intubation", "Yes",
ifelse(URNINFEC == "Urinary Tract Infection", "Yes",
ifelse(DEHIS == "Wound Disruption", "Yes", "No"))))))))))))))### Ifelse function to create new column for any complication
MISITTDemoTable1 <- MISITTDemoTable %>%
mutate(MISITTDemoTable, AnyComplication = ifelse(CDARREST == "Cardiac Arrest Requiring CPR", "Yes",
ifelse(CDMI == "Myocardial Infarction", "Yes",
ifelse(OUPNEUMO == "Pneumonia", "Yes",
ifelse(RENAINSF == "Progressive Renal Insufficiency", "Yes",
ifelse(OPRENAFL == "Acute Renal Failure", "Yes",
ifelse(PULEMBOL == "Pulmonary Embolism", "Yes",
ifelse(OTHDVT == "DVT Requiring Therapy", "Yes",
ifelse(RETURNOR == "Yes", "Yes",
ifelse(ORGSPCSSI == "Organ/Space SSI", "Yes",
ifelse(PRSEPIS == "Yes", "Yes",
ifelse(REINTUB == "Unplanned Intubation", "Yes",
ifelse(URNINFEC == "Urinary Tract Infection", "Yes",
ifelse(SUPINFEC == "Superficial Incisional SSI", "Yes",
ifelse(FAILWEAN == "On Ventilator greater than 48 Hours", "Yes",
ifelse(CNSCVA == "Stroke/CVA", "Yes",
ifelse(DEHIS == "Wound Disruption", "Yes", "No")))))))))))))))))MISITTDemoTable1$PAN_APPROACH[MISITTDemoTable1$PAN_APPROACH =="MIS"] <- "MIS"
MISITTDemoTable1$PAN_APPROACH[MISITTDemoTable1$PAN_APPROACH =="MIS Converted to Open"] <- "MIS"#### Subsetting cleaned data from one dataframe to a new dataframe
IntentiontotreatFinal <-
MISITTDemoTable1 %>%
select(PAN_APPROACH, Age, SEX, BMI, RACE_NEW, ASACLAS, DOpertoD, Fistula.Grade, OPTIME, TOTHLOS, CDARREST, CDMI, NRENAINSF, OPRENAFL, OTHDVT, OUPNEUMO, PULEMBOL, WNDINFD, URNINFEC, DEHIS, STILLINHOSP, REOPERATION1, RETURNOR, REINTUB, ORGSPCSSI, OTHSYSEP, PRSEPIS, FAILWEAN, CNSCVA, SeriousComplication, AnyComplication)## Changing any Unknowns/none assigned to NA
IntentiontotreatFinal[IntentiontotreatFinal =="None assigned"] <- NA
IntentiontotreatFinal[IntentiontotreatFinal =="Unknown"] <- NA#### Labeling columns
var_label(IntentiontotreatFinal$SEX) <- "Sex"
var_label(IntentiontotreatFinal$RACE_NEW) <- "Race"
var_label(IntentiontotreatFinal$ASACLAS) <- "ASA Classification"
var_label(IntentiontotreatFinal$Fistula.Grade) <- "Fistula"
var_label(IntentiontotreatFinal$OPTIME) <- "Total operation time"
var_label(IntentiontotreatFinal$OUPNEUMO) <- "Number of Pneumonia Occurrences"
var_label(IntentiontotreatFinal$DOpertoD) <- "Mortality"
var_label(IntentiontotreatFinal$TOTHLOS) <- "Length of total hospital stay"
var_label(IntentiontotreatFinal$OUPNEUMO) <- "Occurrences Pneumonia"
var_label(IntentiontotreatFinal$PULEMBOL) <- "Occurrences Pulmonary Embolism"
var_label(IntentiontotreatFinal$WNDINFD) <- " Occurrences Deep Incisional SSI"
var_label(IntentiontotreatFinal$STILLINHOSP) <- "Still in Hospital > 30 Days"
var_label(IntentiontotreatFinal$REOPERATION1) <- "Unplanned Reoperation 1"
var_label(IntentiontotreatFinal$OTHSYSEP) <- "Occurrences Sepsis"
var_label(IntentiontotreatFinal$SeriousComplication) <- "Serious Complication"
var_label(IntentiontotreatFinal$AnyComplication) <- "Any Complication"#Final Step to create demographic table
IntentiontotreatFinal %>%
tbl_summary(
by = PAN_APPROACH,
digits = all_continuous() ~ 2,) %>%
add_p(pvalue_fun = ~style_pvalue(.x, digits = 2))%>%
bold_p() %>%
add_overall() %>%
modify_header(label ~ "**Variable**") %>%
modify_spanning_header(c("stat_1", "stat_2") ~ "**NSQIP Short Term Outcomes**") %>%
bold_labels() ## 2 observations missing `PAN_APPROACH` have been removed. To include these observations, use `forcats::fct_explicit_na()` on `PAN_APPROACH` column before passing to `tbl_summary()`.| Variable | Overall, N = 2,4061 | NSQIP Short Term Outcomes | p-value2 | |
|---|---|---|---|---|
| MIS, N = 9291 | Open, N = 1,4771 | |||
| Age | 68.00 (60.00, 74.00) | 69.00 (61.00, 76.00) | 67.00 (60.00, 74.00) | <0.001 |
| Unknown | 8 | 3 | 5 | |
| Sex | 0.94 | |||
| female | 1,200 (50%) | 462 (50%) | 738 (50%) | |
| male | 1,206 (50%) | 467 (50%) | 739 (50%) | |
| BMI | 26.58 (23.41, 30.50) | 26.79 (23.71, 30.89) | 26.44 (23.22, 30.22) | 0.011 |
| Race | 0.81 | |||
| Black | 241 (11%) | 90 (11%) | 151 (12%) | |
| Other | 90 (4.2%) | 37 (4.4%) | 53 (4.0%) | |
| White | 1,812 (85%) | 706 (85%) | 1,106 (84%) | |
| Unknown | 263 | 96 | 167 | |
| ASA Classification | 0.23 | |||
| 1-No Disturb | 11 (0.5%) | 6 (0.6%) | 5 (0.3%) | |
| 2-Mild Disturb | 497 (21%) | 208 (22%) | 289 (20%) | |
| 3-Severe Disturb | 1,732 (72%) | 650 (70%) | 1,082 (73%) | |
| 4-Life Threat | 163 (6.8%) | 63 (6.8%) | 100 (6.8%) | |
| Unknown | 3 | 2 | 1 | |
| Mortality | 27 (1.1%) | 8 (0.9%) | 19 (1.3%) | 0.44 |
| Fistula | 0.003 | |||
| Grade A | 32 (1.3%) | 8 (0.9%) | 24 (1.6%) | |
| Grade B | 357 (15%) | 164 (18%) | 193 (13%) | |
| Grade C | 8 (0.3%) | 1 (0.1%) | 7 (0.5%) | |
| No Fistula | 1,976 (83%) | 741 (81%) | 1,235 (85%) | |
| Unknown | 33 | 15 | 18 | |
| Total operation time | 232.00 (171.00, 312.00) | 232.00 (178.00, 296.00) | 232.00 (165.00, 324.00) | 0.98 |
| Length of total hospital stay | 6.00 (5.00, 8.00) | 5.00 (4.00, 7.00) | 6.00 (5.00, 9.00) | <0.001 |
| CDARREST | 0.57 | |||
| Cardiac Arrest Requiring CPR | 20 (0.8%) | 6 (0.6%) | 14 (0.9%) | |
| No Complication | 2,386 (99%) | 923 (99%) | 1,463 (99%) | |
| CDMI | >0.99 | |||
| Myocardial Infarction | 26 (1.1%) | 10 (1.1%) | 16 (1.1%) | |
| No Complication | 2,380 (99%) | 919 (99%) | 1,461 (99%) | |
| NRENAINSF | 6 (0.2%) | 2 (0.2%) | 4 (0.3%) | >0.99 |
| OPRENAFL | 0.74 | |||
| Acute Renal Failure | 9 (0.4%) | 4 (0.4%) | 5 (0.3%) | |
| No Complication | 2,397 (100%) | 925 (100%) | 1,472 (100%) | |
| OTHDVT | 0.85 | |||
| DVT Requiring Therapy | 59 (2.5%) | 24 (2.6%) | 35 (2.4%) | |
| No Complication | 2,347 (98%) | 905 (97%) | 1,442 (98%) | |
| Occurrences Pneumonia | 0.78 | |||
| No Complication | 2,330 (97%) | 898 (97%) | 1,432 (97%) | |
| Pneumonia | 76 (3.2%) | 31 (3.3%) | 45 (3.0%) | |
| Occurrences Pulmonary Embolism | 0.48 | |||
| No Complication | 2,371 (99%) | 918 (99%) | 1,453 (98%) | |
| Pulmonary Embolism | 35 (1.5%) | 11 (1.2%) | 24 (1.6%) | |
| Occurrences Deep Incisional SSI | 0.33 | |||
| Deep Incisional SSI | 10 (0.4%) | 2 (0.2%) | 8 (0.5%) | |
| No Complication | 2,396 (100%) | 927 (100%) | 1,469 (99%) | |
| URNINFEC | >0.99 | |||
| No Complication | 2,349 (98%) | 907 (98%) | 1,442 (98%) | |
| Urinary Tract Infection | 57 (2.4%) | 22 (2.4%) | 35 (2.4%) | |
| DEHIS | 0.26 | |||
| No Complication | 2,399 (100%) | 928 (100%) | 1,471 (100%) | |
| Wound Disruption | 7 (0.3%) | 1 (0.1%) | 6 (0.4%) | |
| Still in Hospital > 30 Days | 21 (0.9%) | 8 (0.9%) | 13 (0.9%) | >0.99 |
| Unplanned Reoperation 1 | 93 (3.9%) | 32 (3.4%) | 61 (4.1%) | 0.46 |
| RETURNOR | 93 (3.9%) | 32 (3.4%) | 61 (4.1%) | 0.46 |
| REINTUB | 0.58 | |||
| No Complication | 2,353 (98%) | 911 (98%) | 1,442 (98%) | |
| Unplanned Intubation | 53 (2.2%) | 18 (1.9%) | 35 (2.4%) | |
| ORGSPCSSI | 0.99 | |||
| No Complication | 2,148 (89%) | 830 (89%) | 1,318 (89%) | |
| Organ/Space SSI | 258 (11%) | 99 (11%) | 159 (11%) | |
| Occurrences Sepsis | 0.85 | |||
| No Complication | 2,324 (97%) | 896 (96%) | 1,428 (97%) | |
| Sepsis | 82 (3.4%) | 33 (3.6%) | 49 (3.3%) | |
| PRSEPIS | 0.021 | |||
| None | 2,383 (99%) | 926 (100%) | 1,457 (99%) | |
| Yes | 23 (1.0%) | 3 (0.3%) | 20 (1.4%) | |
| FAILWEAN | 0.67 | |||
| No Complication | 2,357 (98%) | 912 (98%) | 1,445 (98%) | |
| On Ventilator greater than 48 Hours | 49 (2.0%) | 17 (1.8%) | 32 (2.2%) | |
| CNSCVA | 0.50 | |||
| No Complication | 2,397 (100%) | 927 (100%) | 1,470 (100%) | |
| Stroke/CVA | 9 (0.4%) | 2 (0.2%) | 7 (0.5%) | |
| Serious Complication | 508 (21%) | 189 (20%) | 319 (22%) | 0.50 |
| Any Complication | 544 (23%) | 198 (21%) | 346 (23%) | 0.25 |
|
1
Statistics presented: Median (IQR); n (%)
2
Statistical tests performed: Wilcoxon rank-sum test; chi-square test of independence; Fisher's exact test
|
||||
##Creating New Column for Age breakdown
IntentiontotreatFinal <-
IntentiontotreatFinal %>%
mutate(IntentiontotreatFinal, BMIB = ifelse(BMI >= 30, "Obese",
ifelse(BMI <= 30, "Non-Obese", "NA")))###Try removing 5-moribound from the odds ratio
IntentiontotreatFinal$ASACLAS[IntentiontotreatFinal$ASACLAS =="5-Moribund"] <- NA###Creating table for logistic regression pan_approach
MISOR <-
IntentiontotreatFinal %>%
mutate(IntentiontotreatFinal, Laparoscopic = ifelse(PAN_APPROACH =="MIS", "1",
ifelse(PAN_APPROACH =="Open", "0", "NA")))### pan_approach --> numeric in the ITTMORTOR column before running logistic regression
MISOR$Laparoscopic <- as.numeric(MISOR$Laparoscopic)##Univariant Model MISvsITT laparoscopic
UVMISOR <- MISOR %>%
select(Laparoscopic, SEX, BMIB, RACE_NEW, ASACLAS) %>%
tbl_uvregression(
method = glm,
y = Laparoscopic,
method.args = list(family = binomial),
exponentiate = TRUE,
pvalue_fun = ~style_pvalue(.x, digits = 2)
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()####Multivariant analysis Laparoscopic
MISMVOR <-
glm(Laparoscopic ~ RACE_NEW + SEX + BMIB + ASACLAS,
data = MISOR,
family = binomial("logit"),
na.action =na.omit
)TBLMVORMIS <-
tbl_regression(MISMVOR, exponentiate = T,
pvalue_fun = ~style_pvalue(.x, digits = 2),
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()tbl_merge(
list(UVMISOR, TBLMVORMIS),
tab_spanner = c("**Univariable**", "**Multivariable**")
) %>%
bold_labels() %>%
italicize_levels()| Characteristic | Univariable | Multivariable | |||||
|---|---|---|---|---|---|---|---|
| N | OR1 | 95% CI1 | p-value | OR1 | 95% CI1 | p-value | |
| Sex | 2,406 | ||||||
| female | — | — | — | — | |||
| male | 1.01 | 0.86, 1.19 | 0.91 | 1.00 | 0.84, 1.19 | >0.99 | |
| BMIB | 2,406 | ||||||
| Non-Obese | — | — | — | — | |||
| Obese | 1.16 | 0.97, 1.39 | 0.11 | 1.21 | 1.00, 1.47 | 0.054 | |
| Race | 2,143 | ||||||
| Black | — | — | — | — | |||
| Other | 1.17 | 0.71, 1.92 | 0.53 | 1.22 | 0.74, 2.01 | 0.43 | |
| White | 1.07 | 0.81, 1.42 | 0.63 | 1.09 | 0.83, 1.45 | 0.54 | |
| ASA Classification | 2,403 | ||||||
| 1-No Disturb | — | — | — | — | |||
| 2-Mild Disturb | 0.60 | 0.17, 2.02 | 0.40 | 0.91 | 0.24, 3.72 | 0.89 | |
| 3-Severe Disturb | 0.50 | 0.14, 1.67 | 0.25 | 0.73 | 0.19, 2.98 | 0.64 | |
| 4-Life Threat | 0.52 | 0.15, 1.81 | 0.30 | 1.07 | 0.27, 4.51 | 0.93 | |
|
1
OR = Odds Ratio, CI = Confidence Interval
|
|||||||
###Creating table for logistic regression Anycomplication
MISAnycomplication <-
IntentiontotreatFinal %>%
mutate(IntentiontotreatFinal, Anycomplication1 = ifelse(AnyComplication =="Yes", "1",
ifelse(AnyComplication =="No", "0", "NA")))### AnyComplication --> numeric in the AnyComplication column before running logistic regression
MISAnycomplication$Anycomplication1 <- as.numeric(MISAnycomplication$Anycomplication1)##Univariant Model AnyComplication
UVMISAnycomplicationOR <- MISAnycomplication %>%
select(Anycomplication1, PAN_APPROACH, SEX, BMIB, RACE_NEW, ASACLAS) %>%
tbl_uvregression(
method = glm,
y = Anycomplication1,
method.args = list(family = binomial),
exponentiate = TRUE,
pvalue_fun = ~style_pvalue(.x, digits = 2)
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()####Multivariant analysis AnyComplication
MISMVORAnycomplication <-
glm(Anycomplication1 ~ PAN_APPROACH + RACE_NEW + SEX + BMIB + ASACLAS,
data = MISAnycomplication,
family = binomial("logit"),
na.action =na.omit
)TBLAnycomplication <-
tbl_regression(MISMVORAnycomplication, exponentiate = T,
pvalue_fun = ~style_pvalue(.x, digits = 2),
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()tbl_merge(
list(UVMISAnycomplicationOR, TBLAnycomplication),
tab_spanner = c("**Univariable**", "**Multivariable**")
) %>%
bold_labels() %>%
italicize_levels()| Characteristic | Univariable | Multivariable | |||||
|---|---|---|---|---|---|---|---|
| N | OR1 | 95% CI1 | p-value | OR1 | 95% CI1 | p-value | |
| PAN_APPROACH | 2,406 | ||||||
| MIS | — | — | — | — | |||
| Open | 1.13 | 0.93, 1.38 | 0.23 | 1.07 | 0.86, 1.32 | 0.56 | |
| Sex | 2,408 | ||||||
| female | — | — | — | — | |||
| male | 1.11 | 0.92, 1.35 | 0.28 | 1.12 | 0.91, 1.38 | 0.28 | |
| BMIB | 2,408 | ||||||
| Non-Obese | — | — | — | — | |||
| Obese | 1.05 | 0.85, 1.29 | 0.66 | 1.02 | 0.81, 1.28 | 0.86 | |
| Race | 2,145 | ||||||
| Black | — | — | — | — | |||
| Other | 0.65 | 0.33, 1.19 | 0.17 | 0.67 | 0.35, 1.24 | 0.22 | |
| White | 0.92 | 0.67, 1.27 | 0.60 | 0.92 | 0.67, 1.27 | 0.61 | |
| ASA Classification | 2,405 | ||||||
| 1-No Disturb | — | — | — | — | |||
| 2-Mild Disturb | 2.65 | 0.50, 48.8 | 0.36 | 1.95 | 0.35, 36.4 | 0.53 | |
| 3-Severe Disturb | 2.89 | 0.55, 53.2 | 0.31 | 2.05 | 0.37, 38.2 | 0.50 | |
| 4-Life Threat | 4.14 | 0.76, 77.0 | 0.18 | 2.82 | 0.49, 53.4 | 0.34 | |
|
1
OR = Odds Ratio, CI = Confidence Interval
|
|||||||
###Creating table for logistic regression serious complication
MISSeriouscomplication <-
IntentiontotreatFinal %>%
mutate(IntentiontotreatFinal, SeriousComplication1 = ifelse(SeriousComplication =="Yes", "1",
ifelse(SeriousComplication =="No", "0", "NA")))### SeriousComplication --> numeric in the serious complication column before running logistic regression
MISSeriouscomplication$SeriousComplication1 <- as.numeric(MISSeriouscomplication$SeriousComplication1)##Univariant Model serious complication
UVMISSeriouscomplicationOR <- MISSeriouscomplication %>%
select(SeriousComplication1, PAN_APPROACH, SEX, BMIB, RACE_NEW, ASACLAS) %>%
tbl_uvregression(
method = glm,
y = SeriousComplication1,
method.args = list(family = binomial),
exponentiate = TRUE,
pvalue_fun = ~style_pvalue(.x, digits = 2)
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()####Multivariant analysis serious complication
MISMVORSeriouscomplication <-
glm(SeriousComplication1 ~ PAN_APPROACH + RACE_NEW + SEX + BMIB + ASACLAS,
data = MISSeriouscomplication,
family = binomial("logit"),
na.action =na.omit
)TBLSeriouscomplication <-
tbl_regression(MISMVORSeriouscomplication, exponentiate = T,
pvalue_fun = ~style_pvalue(.x, digits = 2),
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()tbl_merge(
list(UVMISSeriouscomplicationOR, TBLSeriouscomplication),
tab_spanner = c("**Univariable**", "**Multivariable**")
) %>%
bold_labels() %>%
italicize_levels()| Characteristic | Univariable | Multivariable | |||||
|---|---|---|---|---|---|---|---|
| N | OR1 | 95% CI1 | p-value | OR1 | 95% CI1 | p-value | |
| PAN_APPROACH | 2,406 | ||||||
| MIS | — | — | — | — | |||
| Open | 1.08 | 0.88, 1.32 | 0.46 | 1.03 | 0.83, 1.28 | 0.79 | |
| Sex | 2,408 | ||||||
| female | — | — | — | — | |||
| male | 1.11 | 0.91, 1.35 | 0.31 | 1.11 | 0.90, 1.37 | 0.34 | |
| BMIB | 2,408 | ||||||
| Non-Obese | — | — | — | — | |||
| Obese | 1.09 | 0.88, 1.35 | 0.44 | 1.06 | 0.84, 1.34 | 0.63 | |
| Race | 2,145 | ||||||
| Black | — | — | — | — | |||
| Other | 0.69 | 0.35, 1.28 | 0.26 | 0.72 | 0.36, 1.35 | 0.32 | |
| White | 0.98 | 0.71, 1.37 | 0.91 | 0.98 | 0.71, 1.38 | 0.91 | |
| ASA Classification | 2,405 | ||||||
| 1-No Disturb | — | — | — | — | |||
| 2-Mild Disturb | 2.39 | 0.45, 44.2 | 0.41 | 1.76 | 0.32, 33.0 | 0.60 | |
| 3-Severe Disturb | 2.67 | 0.51, 49.0 | 0.35 | 1.90 | 0.34, 35.4 | 0.55 | |
| 4-Life Threat | 3.67 | 0.67, 68.3 | 0.22 | 2.37 | 0.41, 45.0 | 0.43 | |
|
1
OR = Odds Ratio, CI = Confidence Interval
|
|||||||
###Creating table for logistic regression Mortality
MISMortality <-
IntentiontotreatFinal %>%
mutate(IntentiontotreatFinal, DOpertoD1 = ifelse(DOpertoD =="Yes", "1",
ifelse(DOpertoD =="No", "0", "NA")))### Mortality --> numeric in the Mortality column before running logistic regression
MISMortality$DOpertoD1 <- as.numeric(MISMortality$DOpertoD1)##Univariant Model Mortality
UVMISMortality <- MISMortality %>%
select(DOpertoD1, PAN_APPROACH, SEX, BMIB, RACE_NEW, ASACLAS) %>%
tbl_uvregression(
method = glm,
y = DOpertoD1,
method.args = list(family = binomial),
exponentiate = TRUE,
pvalue_fun = ~style_pvalue(.x, digits = 2)
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x collapsing to unique 'x' values
## ℹ Input `tbl` is `map2(...)`.## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values####Multivariant analysis Mortality
MISMVORMortality <-
glm(DOpertoD1 ~ PAN_APPROACH + RACE_NEW + SEX + BMIB + ASACLAS,
data = MISMortality,
family = binomial("logit"),
na.action =na.omit
)TBLMortality <-
tbl_regression(MISMVORMortality, exponentiate = T,
pvalue_fun = ~style_pvalue(.x, digits = 2),
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values
## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' valuestbl_merge(
list(UVMISMortality, TBLMortality),
tab_spanner = c("**Univariable**", "**Multivariable**")
) %>%
bold_labels() %>%
italicize_levels()| Characteristic | Univariable | Multivariable | |||||
|---|---|---|---|---|---|---|---|
| N | OR1 | 95% CI1 | p-value | OR1 | 95% CI1 | p-value | |
| PAN_APPROACH | 2,406 | ||||||
| MIS | — | — | — | — | |||
| Open | 1.50 | 0.68, 3.65 | 0.34 | 1.24 | 0.51, 3.30 | 0.64 | |
| Sex | 2,408 | ||||||
| female | — | — | — | — | |||
| male | 1.07 | 0.50, 2.32 | 0.86 | 1.22 | 0.51, 3.02 | 0.65 | |
| BMIB | 2,408 | ||||||
| Non-Obese | — | — | — | — | |||
| Obese | 1.32 | 0.56, 2.88 | 0.50 | 0.76 | 0.25, 1.97 | 0.59 | |
| Race | 2,145 | ||||||
| Black | — | — | — | — | |||
| Other | 0.89 | 0.04, 7.06 | 0.92 | 1.05 | 0.05, 8.53 | 0.97 | |
| White | 0.75 | 0.25, 3.23 | 0.65 | 0.79 | 0.26, 3.42 | 0.71 | |
| ASA Classification | 2,405 | ||||||
| 1-No Disturb | — | — | — | — | |||
| 2-Mild Disturb | 95,049 | 0.00, NA | 0.99 | 35,677 | 0.00, NA | 0.99 | |
| 3-Severe Disturb | 164,271 | 0.00, NA | 0.99 | 177,045 | 0.00, NA | 0.99 | |
| 4-Life Threat | 594,355 | 0.00, NA | 0.99 | 409,313 | 0.00, NA | 0.99 | |
|
1
OR = Odds Ratio, CI = Confidence Interval
|
|||||||
###Creating table for logistic regression serious complication
MISReturnOR <-
IntentiontotreatFinal %>%
mutate(IntentiontotreatFinal, RETURNOR1 = ifelse(RETURNOR =="Yes", "1",
ifelse(RETURNOR =="No", "0", "NA")))### AnyComplication --> numeric in the serious complication column before running logistic regression
MISReturnOR$RETURNOR1 <- as.numeric(MISReturnOR$RETURNOR1)##Univariant Model serious complication
UVMISReturnOR <- MISReturnOR %>%
select(RETURNOR1, PAN_APPROACH, SEX, BMIB, RACE_NEW, ASACLAS) %>%
tbl_uvregression(
method = glm,
y = RETURNOR1,
method.args = list(family = binomial),
exponentiate = TRUE,
pvalue_fun = ~style_pvalue(.x, digits = 2)
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x glm.fit: fitted probabilities numerically 0 or 1 occurred
## ℹ Input `tbl` is `map2(...)`.## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred## Warning: Problem with `mutate()` input `tbl`.
## x collapsing to unique 'x' values
## ℹ Input `tbl` is `map2(...)`.## Warning in regularize.values(x, y, ties, missing(ties), na.rm = na.rm):
## collapsing to unique 'x' values####Multivariant analysis serious complication
MISMVORReturnOR <-
glm(RETURNOR1 ~ PAN_APPROACH + RACE_NEW + SEX + BMIB + ASACLAS,
data = MISReturnOR,
family = binomial("logit"),
na.action =na.omit
)TBLReturnOR <-
tbl_regression(MISMVORReturnOR, exponentiate = T,
pvalue_fun = ~style_pvalue(.x, digits = 2),
) %>%
bold_p(t = 0.10) %>%
bold_labels() %>%
italicize_levels()## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredtbl_merge(
list(UVMISReturnOR, TBLReturnOR),
tab_spanner = c("**Univariable**", "**Multivariable**")
) %>%
bold_labels() %>%
italicize_levels()| Characteristic | Univariable | Multivariable | |||||
|---|---|---|---|---|---|---|---|
| N | OR1 | 95% CI1 | p-value | OR1 | 95% CI1 | p-value | |
| PAN_APPROACH | 2,406 | ||||||
| MIS | — | — | — | — | |||
| Open | 1.21 | 0.79, 1.89 | 0.40 | 1.09 | 0.69, 1.75 | 0.73 | |
| Sex | 2,408 | ||||||
| female | — | — | — | — | |||
| male | 1.22 | 0.80, 1.85 | 0.36 | 1.13 | 0.72, 1.78 | 0.58 | |
| BMIB | 2,408 | ||||||
| Non-Obese | — | — | — | — | |||
| Obese | 0.81 | 0.49, 1.29 | 0.39 | 0.61 | 0.34, 1.04 | 0.081 | |
| Race | 2,145 | ||||||
| Black | — | — | — | — | |||
| Other | 0.17 | 0.01, 0.85 | 0.088 | 0.17 | 0.01, 0.85 | 0.086 | |
| White | 0.57 | 0.33, 1.05 | 0.056 | 0.55 | 0.31, 1.02 | 0.043 | |
| ASA Classification | 2,405 | ||||||
| 1-No Disturb | — | — | — | — | |||
| 2-Mild Disturb | 118,230 | 0.02, 6,026,453,222,427,280,373,204,702,613,959,489,815,126,414,113,393,895,722,886,685,804,935,365,263,360 | 0.98 | 91,107 | 0.00, NA | 0.98 | |
| 3-Severe Disturb | 256,828 | 0.00, NA | 0.98 | 232,146 | 0.00, NA | 0.98 | |
| 4-Life Threat | 295,272 | 0.06, 15,050,867,399,493,342,165,163,603,763,121,182,966,376,093,892,550,861,607,661,198,350,299,930,034,176 | 0.98 | 206,389 | 0.01, 334,840,329,407,747,723,578,845,935,567,899,486,870,654,799,029,570,408,296,079,931,929,020,384,713,637,888 | 0.98 | |
|
1
OR = Odds Ratio, CI = Confidence Interval
|
|||||||