Local Data Survival Analysis

library(gtsummary)
library(survival)
library(labelled)
library(tidyverse)

## ── Attaching packages ──────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.3     ✓ purrr   0.3.4
## ✓ tibble  3.0.3     ✓ dplyr   1.0.1
## ✓ tidyr   1.1.1     ✓ stringr 1.4.0
## ✓ readr   1.3.1     ✓ forcats 0.5.0

## ── 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

library(dplyr)
library(lubridate)

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

library(zoo)

## 
## Attaching package: 'zoo'

## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric

PanCancer2000 <- read.csv( ("PancreaticCancer2000.csv"))
PanCancer2001 <- read.csv( ("PancreaticCancer2001.csv"))
PanCancer2002 <- read.csv( ("PancreaticCancer2002.csv"))
PanCancer2003 <- read.csv( ("PancreaticCancer2003.csv"))
PanCancer2004 <- read.csv( ("PancreaticCancer2004.csv"))
PanCancer2005 <- read.csv( ("PancreaticCancer2005.csv"))
PanCancer2006 <- read.csv( ("PancreaticCancer2006.csv"))
PanCancer2007 <- read.csv( ("PancreaticCancer2007.csv"))
PanCancer2008 <- read.csv( ("PancreaticCancer2008.csv"))
PanCancer2009 <- read.csv( ("PancreaticCancer2009.csv"))
PanCancer2010 <- read.csv( ("PancreaticCancer2010.csv"))
PanCancer2011 <- read.csv( ("PancreaticCancer2011.csv"))
PanCancer2012 <- read.csv( ("PancreaticCancer2012.csv"))
PanCancer2013 <- read.csv( ("PancreaticCancer2013.csv"))
PanCancer2014 <- read.csv( ("PancreaticCancer2014.csv"))
PanCancer2015 <- read.csv( ("PancreaticCancer2015.csv"))
PanCancer2016 <- read.csv( ("PancreaticCancer2016.csv"))
PanCancer2017 <- read.csv( ("PancreaticCancer2017.csv"))
PanCancer2018 <- read.csv( ("PancreaticData2018.csv"))
PanCancer2019 <- read.csv( ("PancreaticData2019.csv"))
PanCancer2020 <- read.csv( ("PancreaticData2020.csv"))
MonthSurvival <- read.csv( ("MonthSurvival.csv"))

PanCancer2000$Medical.Record.Number <- as.character(PanCancer2000$Medical.Record.Number)
PanCancer2001$Medical.Record.Number <- as.character(PanCancer2001$Medical.Record.Number)
PanCancer2002$Medical.Record.Number <- as.character(PanCancer2002$Medical.Record.Number)
PanCancer2003$Medical.Record.Number <- as.character(PanCancer2003$Medical.Record.Number)
PanCancer2004$Medical.Record.Number <- as.character(PanCancer2004$Medical.Record.Number)
PanCancer2005$Medical.Record.Number <- as.character(PanCancer2005$Medical.Record.Number)
PanCancer2006$Medical.Record.Number <- as.character(PanCancer2006$Medical.Record.Number)
PanCancer2007$Medical.Record.Number <- as.character(PanCancer2007$Medical.Record.Number)
PanCancer2008$Medical.Record.Number <- as.character(PanCancer2008$Medical.Record.Number)
PanCancer2009$Medical.Record.Number <- as.character(PanCancer2009$Medical.Record.Number)
PanCancer2010$Medical.Record.Number <- as.character(PanCancer2010$Medical.Record.Number)
PanCancer2011$Medical.Record.Number <- as.character(PanCancer2011$Medical.Record.Number)
PanCancer2012$Medical.Record.Number <- as.character(PanCancer2012$Medical.Record.Number)
PanCancer2013$Medical.Record.Number <- as.character(PanCancer2013$Medical.Record.Number)
PanCancer2014$Medical.Record.Number <- as.character(PanCancer2014$Medical.Record.Number)
PanCancer2015$Medical.Record.Number <- as.character(PanCancer2015$Medical.Record.Number)
PanCancer2016$Medical.Record.Number <- as.character(PanCancer2016$Medical.Record.Number)
PanCancer2017$Medical.Record.Number <- as.character(PanCancer2017$Medical.Record.Number)
PanCancer2018$Medical.Record.Number <- as.character(PanCancer2018$Medical.Record.Number)
PanCancer2019$Medical.Record.Number <- as.character(PanCancer2019$Medical.Record.Number)
PanCancer2020$Medical.Record.Number <- as.character(PanCancer2020$Medical.Record.Number)
MonthSurvival$Medical.Record.Number <- as.character(MonthSurvival$Medical.Record.Number)

PanCancer2000$Postal.Code.at.Diagnosis <- as.character(PanCancer2000$Postal.Code.at.Diagnosis)
PanCancer2001$Postal.Code.at.Diagnosis <- as.character(PanCancer2001$Postal.Code.at.Diagnosis)
PanCancer2002$Postal.Code.at.Diagnosis <- as.character(PanCancer2002$Postal.Code.at.Diagnosis)
PanCancer2003$Postal.Code.at.Diagnosis <- as.character(PanCancer2003$Postal.Code.at.Diagnosis)
PanCancer2004$Postal.Code.at.Diagnosis <- as.character(PanCancer2004$Postal.Code.at.Diagnosis)
PanCancer2005$Postal.Code.at.Diagnosis <- as.character(PanCancer2005$Postal.Code.at.Diagnosis)
PanCancer2006$Postal.Code.at.Diagnosis <- as.character(PanCancer2006$Postal.Code.at.Diagnosis)
PanCancer2007$Postal.Code.at.Diagnosis <- as.character(PanCancer2007$Postal.Code.at.Diagnosis)
PanCancer2008$Postal.Code.at.Diagnosis <- as.character(PanCancer2008$Postal.Code.at.Diagnosis)
PanCancer2009$Postal.Code.at.Diagnosis <- as.character(PanCancer2009$Postal.Code.at.Diagnosis)
PanCancer2010$Postal.Code.at.Diagnosis <- as.character(PanCancer2010$Postal.Code.at.Diagnosis)
PanCancer2011$Postal.Code.at.Diagnosis <- as.character(PanCancer2011$Postal.Code.at.Diagnosis)
PanCancer2012$Postal.Code.at.Diagnosis <- as.character(PanCancer2012$Postal.Code.at.Diagnosis)
PanCancer2013$Postal.Code.at.Diagnosis <- as.character(PanCancer2013$Postal.Code.at.Diagnosis)
PanCancer2014$Postal.Code.at.Diagnosis <- as.character(PanCancer2014$Postal.Code.at.Diagnosis)
PanCancer2015$Postal.Code.at.Diagnosis <- as.character(PanCancer2015$Postal.Code.at.Diagnosis)
PanCancer2016$Postal.Code.at.Diagnosis <- as.character(PanCancer2016$Postal.Code.at.Diagnosis)
PanCancer2017$Postal.Code.at.Diagnosis <- as.character(PanCancer2017$Postal.Code.at.Diagnosis)
PanCancer2018$Postal.Code.at.Diagnosis <- as.character(PanCancer2018$Postal.Code.at.Diagnosis)
PanCancer2019$Postal.Code.at.Diagnosis <- as.character(PanCancer2019$Postal.Code.at.Diagnosis)
PanCancer2020$Postal.Code.at.Diagnosis <- as.character(PanCancer2020$Postal.Code.at.Diagnosis)

PanCancer2000$Tumor.Size.Summary <- as.character(PanCancer2000$Tumor.Size.Summary)
PanCancer2001$Tumor.Size.Summary <- as.character(PanCancer2001$Tumor.Size.Summary)
PanCancer2002$Tumor.Size.Summary <- as.character(PanCancer2002$Tumor.Size.Summary)
PanCancer2003$Tumor.Size.Summary <- as.character(PanCancer2003$Tumor.Size.Summary)
PanCancer2004$Tumor.Size.Summary <- as.character(PanCancer2004$Tumor.Size.Summary)
PanCancer2005$Tumor.Size.Summary <- as.character(PanCancer2005$Tumor.Size.Summary)
PanCancer2006$Tumor.Size.Summary <- as.character(PanCancer2006$Tumor.Size.Summary)
PanCancer2007$Tumor.Size.Summary <- as.character(PanCancer2007$Tumor.Size.Summary)
PanCancer2008$Tumor.Size.Summary <- as.character(PanCancer2008$Tumor.Size.Summary)
PanCancer2009$Tumor.Size.Summary <- as.character(PanCancer2009$Tumor.Size.Summary)
PanCancer2010$Tumor.Size.Summary <- as.character(PanCancer2010$Tumor.Size.Summary)
PanCancer2011$Tumor.Size.Summary <- as.character(PanCancer2011$Tumor.Size.Summary)
PanCancer2012$Tumor.Size.Summary <- as.character(PanCancer2012$Tumor.Size.Summary)
PanCancer2013$Tumor.Size.Summary <- as.character(PanCancer2013$Tumor.Size.Summary)
PanCancer2014$Tumor.Size.Summary <- as.character(PanCancer2014$Tumor.Size.Summary)
PanCancer2015$Tumor.Size.Summary <- as.character(PanCancer2015$Tumor.Size.Summary)
PanCancer2016$Tumor.Size.Summary <- as.character(PanCancer2016$Tumor.Size.Summary)
PanCancer2017$Tumor.Size.Summary <- as.character(PanCancer2017$Tumor.Size.Summary)
PanCancer2018$Tumor.Size.Summary <- as.character(PanCancer2018$Tumor.Size.Summary)
PanCancer2019$Tumor.Size.Summary <- as.character(PanCancer2019$Tumor.Size.Summary)
PanCancer2020$Tumor.Size.Summary <- as.character(PanCancer2020$Tumor.Size.Summary)

PanCancer2000$AJCC.Post.Therapy.N <- as.character(PanCancer2000$AJCC.Post.Therapy.N)
PanCancer2001$AJCC.Post.Therapy.N <- as.character(PanCancer2001$AJCC.Post.Therapy.N)
PanCancer2002$AJCC.Post.Therapy.N <- as.character(PanCancer2002$AJCC.Post.Therapy.N)
PanCancer2003$AJCC.Post.Therapy.N <- as.character(PanCancer2003$AJCC.Post.Therapy.N)
PanCancer2004$AJCC.Post.Therapy.N <- as.character(PanCancer2004$AJCC.Post.Therapy.N)
PanCancer2005$AJCC.Post.Therapy.N <- as.character(PanCancer2005$AJCC.Post.Therapy.N)
PanCancer2006$AJCC.Post.Therapy.N <- as.character(PanCancer2006$AJCC.Post.Therapy.N)
PanCancer2007$AJCC.Post.Therapy.N <- as.character(PanCancer2007$AJCC.Post.Therapy.N)
PanCancer2008$AJCC.Post.Therapy.N <- as.character(PanCancer2008$AJCC.Post.Therapy.N)
PanCancer2009$AJCC.Post.Therapy.N <- as.character(PanCancer2009$AJCC.Post.Therapy.N)
PanCancer2010$AJCC.Post.Therapy.N <- as.character(PanCancer2010$AJCC.Post.Therapy.N)
PanCancer2011$AJCC.Post.Therapy.N <- as.character(PanCancer2011$AJCC.Post.Therapy.N)
PanCancer2012$AJCC.Post.Therapy.N <- as.character(PanCancer2012$AJCC.Post.Therapy.N)
PanCancer2013$AJCC.Post.Therapy.N <- as.character(PanCancer2013$AJCC.Post.Therapy.N)
PanCancer2014$AJCC.Post.Therapy.N <- as.character(PanCancer2014$AJCC.Post.Therapy.N)
PanCancer2015$AJCC.Post.Therapy.N <- as.character(PanCancer2015$AJCC.Post.Therapy.N)
PanCancer2016$AJCC.Post.Therapy.N <- as.character(PanCancer2016$AJCC.Post.Therapy.N)
PanCancer2017$AJCC.Post.Therapy.N <- as.character(PanCancer2017$AJCC.Post.Therapy.N)
PanCancer2018$AJCC.Post.Therapy.N <- as.character(PanCancer2018$AJCC.Post.Therapy.N)
PanCancer2019$AJCC.Post.Therapy.N <- as.character(PanCancer2019$AJCC.Post.Therapy.N)
PanCancer2020$AJCC.Post.Therapy.N <- as.character(PanCancer2020$AJCC.Post.Therapy.N)

PanCancer2000$AJCC.Post.Therapy.T <- as.character(PanCancer2000$AJCC.Post.Therapy.T)
PanCancer2001$AJCC.Post.Therapy.T <- as.character(PanCancer2001$AJCC.Post.Therapy.T)
PanCancer2002$AJCC.Post.Therapy.T <- as.character(PanCancer2002$AJCC.Post.Therapy.T)
PanCancer2003$AJCC.Post.Therapy.T <- as.character(PanCancer2003$AJCC.Post.Therapy.T)
PanCancer2004$AJCC.Post.Therapy.T <- as.character(PanCancer2004$AJCC.Post.Therapy.T)
PanCancer2005$AJCC.Post.Therapy.T <- as.character(PanCancer2005$AJCC.Post.Therapy.T)
PanCancer2006$AJCC.Post.Therapy.T <- as.character(PanCancer2006$AJCC.Post.Therapy.T)
PanCancer2007$AJCC.Post.Therapy.T <- as.character(PanCancer2007$AJCC.Post.Therapy.T)
PanCancer2008$AJCC.Post.Therapy.T <- as.character(PanCancer2008$AJCC.Post.Therapy.T)
PanCancer2009$AJCC.Post.Therapy.T <- as.character(PanCancer2009$AJCC.Post.Therapy.T)
PanCancer2010$AJCC.Post.Therapy.T <- as.character(PanCancer2010$AJCC.Post.Therapy.T)
PanCancer2011$AJCC.Post.Therapy.T <- as.character(PanCancer2011$AJCC.Post.Therapy.T)
PanCancer2012$AJCC.Post.Therapy.T <- as.character(PanCancer2012$AJCC.Post.Therapy.T)
PanCancer2013$AJCC.Post.Therapy.T <- as.character(PanCancer2013$AJCC.Post.Therapy.T)
PanCancer2014$AJCC.Post.Therapy.T <- as.character(PanCancer2014$AJCC.Post.Therapy.T)
PanCancer2015$AJCC.Post.Therapy.T <- as.character(PanCancer2015$AJCC.Post.Therapy.T)
PanCancer2016$AJCC.Post.Therapy.T <- as.character(PanCancer2016$AJCC.Post.Therapy.T)
PanCancer2017$AJCC.Post.Therapy.T <- as.character(PanCancer2017$AJCC.Post.Therapy.T)
PanCancer2018$AJCC.Post.Therapy.T <- as.character(PanCancer2018$AJCC.Post.Therapy.T)
PanCancer2019$AJCC.Post.Therapy.T <- as.character(PanCancer2019$AJCC.Post.Therapy.T)
PanCancer2020$AJCC.Post.Therapy.T <- as.character(PanCancer2020$AJCC.Post.Therapy.T)

PanCancer2000$AJCC.Post.Therapy.M <- as.character(PanCancer2000$AJCC.Post.Therapy.M)
PanCancer2001$AJCC.Post.Therapy.M <- as.character(PanCancer2001$AJCC.Post.Therapy.M)
PanCancer2002$AJCC.Post.Therapy.M <- as.character(PanCancer2002$AJCC.Post.Therapy.M)
PanCancer2003$AJCC.Post.Therapy.M <- as.character(PanCancer2003$AJCC.Post.Therapy.M)
PanCancer2004$AJCC.Post.Therapy.M <- as.character(PanCancer2004$AJCC.Post.Therapy.M)
PanCancer2005$AJCC.Post.Therapy.M <- as.character(PanCancer2005$AJCC.Post.Therapy.M)
PanCancer2006$AJCC.Post.Therapy.M <- as.character(PanCancer2006$AJCC.Post.Therapy.M)
PanCancer2007$AJCC.Post.Therapy.M <- as.character(PanCancer2007$AJCC.Post.Therapy.M)
PanCancer2008$AJCC.Post.Therapy.M <- as.character(PanCancer2008$AJCC.Post.Therapy.M)
PanCancer2009$AJCC.Post.Therapy.M <- as.character(PanCancer2009$AJCC.Post.Therapy.M)
PanCancer2010$AJCC.Post.Therapy.M <- as.character(PanCancer2010$AJCC.Post.Therapy.M)
PanCancer2011$AJCC.Post.Therapy.M <- as.character(PanCancer2011$AJCC.Post.Therapy.M)
PanCancer2012$AJCC.Post.Therapy.M <- as.character(PanCancer2012$AJCC.Post.Therapy.M)
PanCancer2013$AJCC.Post.Therapy.M <- as.character(PanCancer2013$AJCC.Post.Therapy.M)
PanCancer2014$AJCC.Post.Therapy.M <- as.character(PanCancer2014$AJCC.Post.Therapy.M)
PanCancer2015$AJCC.Post.Therapy.M <- as.character(PanCancer2015$AJCC.Post.Therapy.M)
PanCancer2016$AJCC.Post.Therapy.M <- as.character(PanCancer2016$AJCC.Post.Therapy.M)
PanCancer2017$AJCC.Post.Therapy.M <- as.character(PanCancer2017$AJCC.Post.Therapy.M)
PanCancer2018$AJCC.Post.Therapy.M <- as.character(PanCancer2018$AJCC.Post.Therapy.M)
PanCancer2019$AJCC.Post.Therapy.M <- as.character(PanCancer2019$AJCC.Post.Therapy.M)
PanCancer2020$AJCC.Post.Therapy.M <- as.character(PanCancer2020$AJCC.Post.Therapy.M)

PanCancer2000$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2000$AJCC.Post.Therapy.Stage.Group)
PanCancer2001$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2001$AJCC.Post.Therapy.Stage.Group)
PanCancer2002$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2002$AJCC.Post.Therapy.Stage.Group)
PanCancer2003$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2003$AJCC.Post.Therapy.Stage.Group)
PanCancer2004$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2004$AJCC.Post.Therapy.Stage.Group)
PanCancer2005$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2005$AJCC.Post.Therapy.Stage.Group)
PanCancer2006$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2006$AJCC.Post.Therapy.Stage.Group)
PanCancer2007$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2007$AJCC.Post.Therapy.Stage.Group)
PanCancer2008$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2008$AJCC.Post.Therapy.Stage.Group)
PanCancer2009$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2009$AJCC.Post.Therapy.Stage.Group)
PanCancer2010$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2010$AJCC.Post.Therapy.Stage.Group)
PanCancer2011$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2011$AJCC.Post.Therapy.Stage.Group)
PanCancer2012$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2012$AJCC.Post.Therapy.Stage.Group)
PanCancer2013$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2013$AJCC.Post.Therapy.Stage.Group)
PanCancer2014$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2014$AJCC.Post.Therapy.Stage.Group)
PanCancer2015$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2015$AJCC.Post.Therapy.Stage.Group)
PanCancer2016$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2016$AJCC.Post.Therapy.Stage.Group)
PanCancer2017$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2017$AJCC.Post.Therapy.Stage.Group)
PanCancer2018$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2018$AJCC.Post.Therapy.Stage.Group)
PanCancer2019$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2019$AJCC.Post.Therapy.Stage.Group)
PanCancer2020$AJCC.Post.Therapy.Stage.Group <- as.character(PanCancer2020$AJCC.Post.Therapy.Stage.Group)

PanCancer2000$Primary.Surgeon.NPI <- as.character(PanCancer2000$Primary.Surgeon.NPI)
PanCancer2001$Primary.Surgeon.NPI <- as.character(PanCancer2001$Primary.Surgeon.NPI)
PanCancer2002$Primary.Surgeon.NPI <- as.character(PanCancer2002$Primary.Surgeon.NPI)
PanCancer2003$Primary.Surgeon.NPI <- as.character(PanCancer2003$Primary.Surgeon.NPI)
PanCancer2004$Primary.Surgeon.NPI <- as.character(PanCancer2004$Primary.Surgeon.NPI)
PanCancer2005$Primary.Surgeon.NPI <- as.character(PanCancer2005$Primary.Surgeon.NPI)
PanCancer2006$Primary.Surgeon.NPI <- as.character(PanCancer2006$Primary.Surgeon.NPI)
PanCancer2007$Primary.Surgeon.NPI <- as.character(PanCancer2007$Primary.Surgeon.NPI)
PanCancer2008$Primary.Surgeon.NPI <- as.character(PanCancer2008$Primary.Surgeon.NPI)
PanCancer2009$Primary.Surgeon.NPI <- as.character(PanCancer2009$Primary.Surgeon.NPI)
PanCancer2010$Primary.Surgeon.NPI <- as.character(PanCancer2010$Primary.Surgeon.NPI)
PanCancer2011$Primary.Surgeon.NPI <- as.character(PanCancer2011$Primary.Surgeon.NPI)
PanCancer2012$Primary.Surgeon.NPI <- as.character(PanCancer2012$Primary.Surgeon.NPI)
PanCancer2013$Primary.Surgeon.NPI <- as.character(PanCancer2013$Primary.Surgeon.NPI)
PanCancer2014$Primary.Surgeon.NPI <- as.character(PanCancer2014$Primary.Surgeon.NPI)
PanCancer2015$Primary.Surgeon.NPI <- as.character(PanCancer2015$Primary.Surgeon.NPI)
PanCancer2016$Primary.Surgeon.NPI <- as.character(PanCancer2016$Primary.Surgeon.NPI)
PanCancer2017$Primary.Surgeon.NPI <- as.character(PanCancer2017$Primary.Surgeon.NPI)
PanCancer2018$Primary.Surgeon.NPI <- as.character(PanCancer2018$Primary.Surgeon.NPI)
PanCancer2019$Primary.Surgeon.NPI <- as.character(PanCancer2019$Primary.Surgeon.NPI)
PanCancer2020$Primary.Surgeon.NPI <- as.character(PanCancer2020$Primary.Surgeon.NPI)

PanCancer2000$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2000$Radiation.Oncology.Physician.NPI)
PanCancer2001$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2001$Radiation.Oncology.Physician.NPI)
PanCancer2002$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2002$Radiation.Oncology.Physician.NPI)
PanCancer2003$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2003$Radiation.Oncology.Physician.NPI)
PanCancer2004$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2004$Radiation.Oncology.Physician.NPI)
PanCancer2005$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2005$Radiation.Oncology.Physician.NPI)
PanCancer2006$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2006$Radiation.Oncology.Physician.NPI)
PanCancer2007$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2007$Radiation.Oncology.Physician.NPI)
PanCancer2008$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2008$Radiation.Oncology.Physician.NPI)
PanCancer2009$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2009$Radiation.Oncology.Physician.NPI)
PanCancer2010$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2010$Radiation.Oncology.Physician.NPI)
PanCancer2011$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2011$Radiation.Oncology.Physician.NPI)
PanCancer2012$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2012$Radiation.Oncology.Physician.NPI)
PanCancer2013$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2013$Radiation.Oncology.Physician.NPI)
PanCancer2014$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2014$Radiation.Oncology.Physician.NPI)
PanCancer2015$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2015$Radiation.Oncology.Physician.NPI)
PanCancer2016$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2016$Radiation.Oncology.Physician.NPI)
PanCancer2017$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2017$Radiation.Oncology.Physician.NPI)
PanCancer2018$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2018$Radiation.Oncology.Physician.NPI)
PanCancer2019$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2019$Radiation.Oncology.Physician.NPI)
PanCancer2020$Radiation.Oncology.Physician.NPI <- as.character(PanCancer2020$Radiation.Oncology.Physician.NPI)

PanCancerAllYears <- bind_rows(PanCancer2000, PanCancer2001, PanCancer2002, PanCancer2003, PanCancer2004, PanCancer2005, PanCancer2005, PanCancer2006, PanCancer2007, PanCancer2008, PanCancer2009, PanCancer2010, PanCancer2011, PanCancer2012, PanCancer2013, PanCancer2014, PanCancer2015, PanCancer2016, PanCancer2017, PanCancer2018, PanCancer2019, PanCancer2020)

MonthSurvival <-
  MonthSurvival %>%
  select(Medical.Record.Number, Date.of.Last.Contact, Date.of.Initial.Diagnosis)

AllFinal <-
merge(MonthSurvival, PanCancerAllYears, by.x = "Medical.Record.Number", by.y = "Medical.Record.Number", all.x=F, all.y=FALSE)

AllFinal$Date.of.Initial.Diagnosis.y <- mdy(AllFinal$Date.of.Initial.Diagnosis.y)
AllFinal$Date.of.Last.Contact <- mdy(AllFinal$Date.of.Last.Contact)

## Warning: 8 failed to parse.

AllFinal$Date.of.First.Surgery <- mdy(AllFinal$Date.of.First.Surgery)

## Warning: 1129 failed to parse.

AllFinal$MonthDate <- (as.yearmon(AllFinal$Date.of.Last.Contact, format = "%m/%Y")-
               as.yearmon(AllFinal$Date.of.Initial.Diagnosis.y, format = "%m/%Y"))*12

###removing duplicates
AllFinalUnique <- 
  AllFinal %>% 
  distinct()

LocalDataSet <- AllFinalUnique[!duplicated(AllFinalUnique[c("Medical.Record.Number")]),]

rm(PanCancer2000,PanCancer2001,PanCancer2002,PanCancer2003,PanCancer2004,PanCancer2005,PanCancer2006,PanCancer2007,PanCancer2008,PanCancer2009,PanCancer2010,PanCancer2011,PanCancer2012,PanCancer2013,PanCancer2014,PanCancer2015,PanCancer2016,PanCancer2017,PanCancer2018,PanCancer2019,PanCancer2020,PanCancerAllYears)

LocalDataSet4 <- 
  LocalDataSet %>%
  mutate(LocalDataSet, Era = ifelse(Date.of.Initial.Diagnosis.y > "2011-01-01", "Era2", 
                                               ifelse(Date.of.Initial.Diagnosis.y > "2000-01-01", "Era1", NA)))

LocalDataSet4$Date.of.First.Surgery <- as.Date(LocalDataSet4$Date.of.First.Surgery)


LocalDataSet4 <-
  LocalDataSet4 %>%
  mutate(LocalDataSet4, Surgery = ifelse(Date.of.First.Surgery > "2000-01-01", "Yes",
                                         ifelse(Date.of.First.Surgery == "No", "No","No")))


LocalDataSet4$Surgery[is.na(LocalDataSet4$Surgery)] <- "No"
table(LocalDataSet4$Surgery)

## 
##   No  Yes 
## 1061  515

LocalDataSet4$X1st.Course.Date.Radiation.Started <- mdy(LocalDataSet4$X1st.Course.Date.Radiation.Started)

## Warning: 1134 failed to parse.

LocalDataSet4 <-
  LocalDataSet4 %>%
  mutate(LocalDataSet4, Radiation = ifelse(X1st.Course.Date.Radiation.Started > "2000-01-01", "Yes",
                                         ifelse(X1st.Course.Date.Radiation.Started == "No", "No","No")))


LocalDataSet4$Radiation[is.na(LocalDataSet4$Radiation)] <- "No"
table(LocalDataSet4$Radiation)

## 
##   No  Yes 
## 1134  442

LocalDataSet2 <- LocalDataSet1 %>% mutate(LocalDataSet1, StagingBest = ifelse(Best.Summary.Stage == “0”, “In situ”, NA))

LocalDataSet3 <- LocalDataSet2 %>% mutate(LocalDataSet2, StagingSummary = ifelse(Summary.Stage.2018 == “0 In situ”, “In Situ”, NA))

LocalDataSet4 <- LocalDataSet3 %>% unite(Staging, c(“Best.Summary.Stage”, “Summary.Stage.2018”))

LocalDataSet4\(Staging[LocalDataSet4\)Staging == “NA_0 In situ”] <- “In Situ” LocalDataSet4\(Staging[LocalDataSet4\)Staging == “0_NA”] <- “In Situ”

LocalDataSet4\(Staging[LocalDataSet4\)Staging == “NA_1 Localized”] <- “Localized” LocalDataSet4\(Staging[LocalDataSet4\)Staging == “1_NA”] <- “Localized”

LocalDataSet4\(Staging[LocalDataSet4\)Staging == “NA_2 Regional by direct extension only”] <- “Regional by direct extension only” LocalDataSet4\(Staging[LocalDataSet4\)Staging == “2_NA”] <- “Regional by direct extension only”

LocalDataSet4\(Staging[LocalDataSet4\)Staging == “NA_3 Regional lymph nodes only”] <- “Regional lymph nodes only” LocalDataSet4\(Staging[LocalDataSet4\)Staging == “3_NA”] <- “Regional lymph nodes only”

LocalDataSet4\(Staging[LocalDataSet4\)Staging == “NA_4 Regional by BOTH direct extension AND lymph node involvement”] <- “Regional by BOTH direct extension AND lymph node involvement” LocalDataSet4\(Staging[LocalDataSet4\)Staging == “4_NA”] <- “Regional by BOTH direct extension AND lymph node involvement”

LocalDataSet4\(Staging[LocalDataSet4\)Staging == “5_NA”] <- NA

LocalDataSet4\(Staging[LocalDataSet4\)Staging == “NA_7 Distant site(s)/node(s) involved”] <- “Distant Site(s)/node(s) involved” LocalDataSet4\(Staging[LocalDataSet4\)Staging == “7_NA”] <- “Distant Site(s)/node(s) involved”

LocalDataSet4\(Staging[LocalDataSet4\)Staging == “NA_9 Unknown if extension or metastasis (unstaged, unknown, or unspecified); Death Certificate Only Case”] <- NA LocalDataSet4\(Staging[LocalDataSet4\)Staging == “9_NA”] <- NA

LocalDataSet4\(Staging[LocalDataSet4\)Staging == “NA_NA”] <- NA LocalDataSet4\(Staging[LocalDataSet4\)Staging == “NA_”] <- NA

table(LocalDataSet4\(Staging) table(LocalDataSet4\)Race.1)

LocalDataSet4$Race.1[LocalDataSet4$Race.1 == "98  Other"] <- "Non-White"
LocalDataSet4$Race.1[LocalDataSet4$Race.1 == "02  Black"] <- "Non-White"
LocalDataSet4$Race.1[LocalDataSet4$Race.1 == "03  American Indian, Aleutian, or Eskimo"] <- "Non-White"
LocalDataSet4$Race.1[LocalDataSet4$Race.1 == "05  Japanese"] <- "Non-White"
LocalDataSet4$Race.1[LocalDataSet4$Race.1 == "04  Chinese"] <- "Non-White"

LocalDataSet4$Race.1[LocalDataSet4$Race.1 == "06  Filipino"] <- "Non-White"
LocalDataSet4$Race.1[LocalDataSet4$Race.1 == "10  Vietnamese"] <- "Non-White"
LocalDataSet4$Race.1[LocalDataSet4$Race.1 == "98  Other"] <- "Non-White"


LocalDataSet4$Race.1[LocalDataSet4$Race.1 == "99  Unknown"] <- "Non-White"

LocalDataSet4$Race.1[LocalDataSet4$Race.1 == "01  White"] <- "White"


table(LocalDataSet4$Race.1)

## 
## Non-White     White 
##        24      1552

LocalDataSet4$AJCC.Clinical.Stage.Group[LocalDataSet4$AJCC.Clinical.Stage.Group == "0"] <- "EminentlyResectable"
LocalDataSet4$AJCC.Clinical.Stage.Group[LocalDataSet4$AJCC.Clinical.Stage.Group == "1"] <- "EminentlyResectable"
LocalDataSet4$AJCC.Clinical.Stage.Group[LocalDataSet4$AJCC.Clinical.Stage.Group == "1A"] <- "EminentlyResectable"
LocalDataSet4$AJCC.Clinical.Stage.Group[LocalDataSet4$AJCC.Clinical.Stage.Group == "1B"] <- "EminentlyResectable"
LocalDataSet4$AJCC.Clinical.Stage.Group[LocalDataSet4$AJCC.Clinical.Stage.Group == "2"] <- "LocallyAdvanced"
LocalDataSet4$AJCC.Clinical.Stage.Group[LocalDataSet4$AJCC.Clinical.Stage.Group == "2A"] <- "LocallyAdvanced"
LocalDataSet4$AJCC.Clinical.Stage.Group[LocalDataSet4$AJCC.Clinical.Stage.Group == "2B"] <- "LocallyAdvanced"
LocalDataSet4$AJCC.Clinical.Stage.Group[LocalDataSet4$AJCC.Clinical.Stage.Group == "3"] <- "LocallyAdvanced"
LocalDataSet4$AJCC.Clinical.Stage.Group[LocalDataSet4$AJCC.Clinical.Stage.Group == "4"] <- "Stage4"
LocalDataSet4$AJCC.Clinical.Stage.Group[LocalDataSet4$AJCC.Clinical.Stage.Group == "4B"] <- "Stage4"
LocalDataSet4$AJCC.Clinical.Stage.Group[LocalDataSet4$AJCC.Clinical.Stage.Group == "88"] <- NA
LocalDataSet4$AJCC.Clinical.Stage.Group[LocalDataSet4$AJCC.Clinical.Stage.Group == "99"] <- NA
LocalDataSet4$AJCC.Clinical.Stage.Group[LocalDataSet4$AJCC.Clinical.Stage.Group == ""] <- NA







table(LocalDataSet4$AJCC.Clinical.Stage.Group )

## 
## EminentlyResectable     LocallyAdvanced              Stage4 
##                 309                 559                 482

LocalDataSet4$X1st.Course.Chemotherapy.Summ[LocalDataSet4$X1st.Course.Chemotherapy.Summ == "00  None; chemotherapy not part of planned first course; autopsy only"] <- "No"
LocalDataSet4$X1st.Course.Chemotherapy.Summ[LocalDataSet4$X1st.Course.Chemotherapy.Summ == "87  Pt/pt`s guardian refused chemotherapy; refusal noted"] <- "No"
LocalDataSet4$X1st.Course.Chemotherapy.Summ[LocalDataSet4$X1st.Course.Chemotherapy.Summ == "86  Reason unknown for no chemo; recommended but not admin"] <- "No"
LocalDataSet4$X1st.Course.Chemotherapy.Summ[LocalDataSet4$X1st.Course.Chemotherapy.Summ == "82  Chemotherapy contraindicated due to pt risk factors"] <- "No"
LocalDataSet4$X1st.Course.Chemotherapy.Summ[LocalDataSet4$X1st.Course.Chemotherapy.Summ == "85  Chemo not admin; Pt died prior to planned/recommended therapy"] <- "No"
LocalDataSet4$X1st.Course.Chemotherapy.Summ[LocalDataSet4$X1st.Course.Chemotherapy.Summ == "01  Chemotherapy, NOS"] <- "Yes"
LocalDataSet4$X1st.Course.Chemotherapy.Summ[LocalDataSet4$X1st.Course.Chemotherapy.Summ == "02  Chemotherapy, single agent"] <- "Yes"
LocalDataSet4$X1st.Course.Chemotherapy.Summ[LocalDataSet4$X1st.Course.Chemotherapy.Summ == "03  Chemotherapy, multiple agents (combination regimen)"] <- "Yes"
LocalDataSet4$X1st.Course.Chemotherapy.Summ[LocalDataSet4$X1st.Course.Chemotherapy.Summ == "88  Chemotherapy recommended, unk if administered"] <- NA
LocalDataSet4$X1st.Course.Chemotherapy.Summ[LocalDataSet4$X1st.Course.Chemotherapy.Summ == "99  Unk if chemotherapy recommended/administered; death cert only"] <- NA

table(LocalDataSet4$X1st.Course.Chemotherapy.Summ)

## 
##   No  Yes 
##  529 1018

table(LocalDataSet4$Marital.Status.at.DX)

## 
##                                                                                               1  Single (never married) 
##                                                                                                                     146 
##                                                                                       2  Married (including common law) 
##                                                                                                                     910 
##                                                                                                            3  Separated 
##                                                                                                                       8 
##                                                                                                             4  Divorced 
##                                                                                                                     161 
##                                                                                                              5  Widowed 
##                                                                                                                     234 
## 6  Unmarried or Domestic Partner (same sex or opposite sex, registered or unregistered, other than common law marriage) 
##                                                                                                                      35 
##                                                                                                              9  Unknown 
##                                                                                                                      82

LocalDataSet4$Marital.Status.at.DX[LocalDataSet4$Marital.Status.at.DX == "1  Single (never married)"] <- "Single"
LocalDataSet4$Marital.Status.at.DX[LocalDataSet4$Marital.Status.at.DX == "2  Married (including common law)"] <- "Married"
LocalDataSet4$Marital.Status.at.DX[LocalDataSet4$Marital.Status.at.DX == "3  Separated"] <- "Divorced/Separated"
LocalDataSet4$Marital.Status.at.DX[LocalDataSet4$Marital.Status.at.DX == "4  Divorced"] <- "Divorced/Separated"
LocalDataSet4$Marital.Status.at.DX[LocalDataSet4$Marital.Status.at.DX == "5  Widowed"] <- "Widowed"
LocalDataSet4$Marital.Status.at.DX[LocalDataSet4$Marital.Status.at.DX == "6  Unmarried or Domestic Partner (same sex or opposite sex, registered or unregistered, other than common law marriage)"] <- "Single"
LocalDataSet4$Marital.Status.at.DX[LocalDataSet4$Marital.Status.at.DX == "9  Unknown"] <- NA

LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "01  Not Insured"] <- "Uninsured"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "02  Not Insured, self pay"] <- "Uninsured"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "20  Private Ins: Managed care, HMO, PPO"] <- "Insured"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "31  Medicaid"] <- "Medicaid"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "35  Medicaid - Admin through Managed Care Plan"] <- "Medicaid"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "60  Medicare w/o supplement, Medicare, NOS"] <- "Insured"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "61  Medicare with supplement, NOS"] <- "Insured"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "62  Medicare - Admin through Managed Care Plan"] <- "Insured"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "63  Medicare with private supplement"] <- "Insured"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "64  Medicare with Medicaid eligibility"] <- "Insured"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "64  Medicare with Medicaid eligibility"] <- "Insured"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "65  TRICARE"] <- "Insured"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "66  Military"] <- "Insured"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "67  Veterans Affairs"] <- "Insured"
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "99  Insurance status unknown"] <- NA
LocalDataSet4$Primary.Payer.at.DX[LocalDataSet4$Primary.Payer.at.DX == "10  Insurance, NOS"] <- NA

table(LocalDataSet4$Primary.Payer.at.DX)

## 
##   Insured  Medicaid Uninsured 
##      1308        77        26

LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "80133  Large cell neuroendocrine carcinoma"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "81503  Pancreatic endocrine tumor, malignant (C25._)"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "80313  Giant cell carcinoma"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "80703  Squamous cell carcinoma, NOS"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "81513  Insulinoma, malignant"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "81533  Gastrinoma, malignant"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "81503  Islet cell carcinoma (C25._)"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "81581  Endocrine tumor, functioning, NOS"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "82403  Carcinoid tumor, NOS (except of appendix)"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "82403  Carcinoid, NOS  (except of appendix)"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "82403  Neuroendocrine carcinoma, low grade"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "82403  Neuroendocrine carcinoma, well-differentiated"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "82403  Neuroendocrine tumor, grade 1"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "82493  Neuroendocrine tumor, grade 2"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "82463  Neuroendocrine tumor, well differentiated (C50._)"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "82463  Neuroendocrine carcinoma, NOS"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "84532  Intraductal papillary mucinous neoplasm with high-grade dysplasia (C25._)"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "84532  Intraductal papillary-mucinous carcinoma, non-invasive"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "84533  Intraductal papillary mucinous neoplasm (IPMN) with an associated invasive  carcinoma (C25._)"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "84533  Intraductal papillary-mucinous carcinoma, invasive"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "88903  Leiomyosarcoma, NOS"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "89363  GIST, malignant"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "92603  Ewing sarcoma"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "95913  Non-Hodgkin lymphoma, NOS"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "96803  Lymphoma, diffuse large B-cell, NOS"] <- NA
LocalDataSet4$Histo.Behavior.ICD.O.3[LocalDataSet4$Histo.Behavior.ICD.O.3 == "96803  Lymphoma, malig, large B-cell, diffuse, (DLBCL), NOS"] <- NA


table(LocalDataSet4$Histo.Behavior.ICD.O.3)

## 
##                                                     
##                                                   3 
##                                       80003  Cancer 
##                                                   4 
##                                   80003  Malignancy 
##                                                   1 
##                          80003  Neoplasm, malignant 
##                                                   8 
##                        80003  Tumor, malignant, NOS 
##                                                   1 
##                       80102  Carcinoma in situ, NOS 
##                                                   1 
##                               80103  Carcinoma, NOS 
##                                                  29 
##                   80213  Carcinoma, anaplastic, NOS 
##                                                   1 
##                        80333  Sarcomatoid carcinoma 
##                                                   1 
##                    80413  Small cell carcinoma, NOS 
##                                                   1 
##                     80463  Non-small cell carcinoma 
##                                                   8 
##                          81403  Adenocarcinoma, NOS 
##                                                1204 
##              81443  Adenocarcinoma, intestinal type 
##                                                   2 
## 81543  Mixed islet cell and exocrine adenocarcinoma 
##                                                   1 
##       82443  Carcinoid and adenocarcinoma, combined 
##                                                   1 
##          82443  Mixed adenoneuroendocrine carcinoma 
##                                                   1 
##           82553  Adenocarcinoma with mixed subtypes 
##                                                   4 
##                    83233  Mixed cell adenocarcinoma 
##                                                   1 
##                      84403  Cystadenocarcinoma, NOS 
##                                                   1 
##              84523  Solid pseudopapillary carcinoma 
##                                                   4 
##                            84803  Colloid carcinoma 
##                                                   1 
##                      84803  Mucinous adenocarcinoma 
##                                                  22 
##                           84803  Mucinous carcinoma 
##                                                   2 
##                        84803  Mucous adenocarcinoma 
##                                                   1 
##               84813  Mucin-producing adenocarcinoma 
##                                                   2 
##              84903  Signet ring cell adenocarcinoma 
##                                                   1 
##                   84903  Signet ring cell carcinoma 
##                                                   2 
##                     85003  Duct adenocarcinoma, NOS 
##                                                  40 
##                          85003  Duct carcinoma, NOS 
##                                                   1 
##                        85003  Ductal carcinoma, NOS 
##                                                  55 
##             85003  Infiltrating duct adenocarcinoma 
##                                                  16 
##             85003  Infiltrating duct carcinoma, NOS 
##                                                  28 
##              85213  Infiltrating ductular carcinoma 
##                                                   7 
##                        85503  Acinar cell carcinoma 
##                                                   1 
##                   85503  Acinic cell adenocarcinoma 
##                                                   1 
##                      85603  Adenosquamous carcinoma 
##                                                   6 
##                   85753  Metaplastic carcinoma, NOS 
##                                                   1

LocalDataSetDT <-
  LocalDataSet4 %>%
  select(Age.at.Diagnosis, Sex, Race.1, Primary.Payer.at.DX, Marital.Status.at.DX, Histo.Behavior.ICD.O.3, Era, AJCC.Clinical.Stage.Group, Vital.Status, MonthDate, Surgery, X1st.Course.Chemotherapy.Summ, Radiation)

DTLocalDataStage4 <- 
  subset(LocalDataSetDT, AJCC.Clinical.Stage.Group == "Stage4")

DTLocalized <- 
  subset(LocalDataSetDT, AJCC.Clinical.Stage.Group == "LocallyAdvanced" | AJCC.Clinical.Stage.Group == "EminentlyResectable")

DTLocallyAdvanced <- 
  subset(LocalDataSetDT, AJCC.Clinical.Stage.Group == "LocallyAdvanced")

DTEminentlyResectable <- 
  subset(LocalDataSetDT, AJCC.Clinical.Stage.Group == "EminentlyResectable")

DTSurgery <- 
  subset(LocalDataSetDT, Surgery == "Yes")

DTSurgery$AJCC.Clinical.Stage.Group[DTSurgery$AJCC.Clinical.Stage.Group == "Stage4"] <- NA


table(DTLocalized$AJCC.Clinical.Stage.Group)

## 
## EminentlyResectable     LocallyAdvanced 
##                 309                 559

DTSurgery <-
  DTSurgery %>%
  select(Age.at.Diagnosis, Sex, Race.1, Primary.Payer.at.DX, Marital.Status.at.DX, Histo.Behavior.ICD.O.3, Era, AJCC.Clinical.Stage.Group, Vital.Status, MonthDate, X1st.Course.Chemotherapy.Summ, Radiation)

LocalDataSetDT %>%
  tbl_summary(
    by = Era,
    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") ~ "**Demographic Table Everyone Era1 vs Era2*") %>%
  bold_labels()

## 4 observations missing `Era` have been removed. To include these observations, use `forcats::fct_explicit_na()` on `Era` column before passing to `tbl_summary()`.

## There was an error in 'add_p()' for variable 'Histo.Behavior.ICD.O.3', p-value omitted:
## Error in stats::fisher.test(data[[variable]], as.factor(data[[by]])): FEXACT error 7(location). LDSTP=18180 is too small for this problem,
##   (pastp=6.29157, ipn_0:=ipoin[itp=298]=6073, stp[ipn_0]=5.63479).
## Increase workspace or consider using 'simulate.p.value=TRUE'

Variable	Overall, N = 1,572¹	*Demographic Table Everyone Era1 vs Era2		p-value²
Variable	Overall, N = 1,572¹	Era1, N = 562¹	Era2, N = 1,010¹	p-value²
Age.at.Diagnosis	69.00 (61.00, 77.00)	69.00 (60.00, 77.00)	69.00 (62.00, 77.00)	0.70
Sex				0.99
1 Male	813 (52%)	290 (52%)	523 (52%)
2 Female	759 (48%)	272 (48%)	487 (48%)
Race.1				0.64
Non-White	21 (1.3%)	6 (1.1%)	15 (1.5%)
White	1,551 (99%)	556 (99%)	995 (99%)
Primary.Payer.at.DX				0.038
Insured	1,308 (93%)	445 (94%)	863 (92%)
Medicaid	77 (5.5%)	17 (3.6%)	60 (6.4%)
Uninsured	26 (1.8%)	12 (2.5%)	14 (1.5%)
Unknown	161	88	73
Marital.Status.at.DX				0.004
Divorced/Separated	169 (11%)	54 (10%)	115 (12%)
Married	910 (61%)	342 (65%)	568 (59%)
Single	181 (12%)	44 (8.3%)	137 (14%)
Widowed	234 (16%)	90 (17%)	144 (15%)
Unknown	78	32	46
Histo.Behavior.ICD.O.3
80003 Cancer	3 (0.2%)	0 (0%)	3 (0.3%)
80003 Malignancy	1 (<0.1%)	0 (0%)	1 (0.1%)
80003 Neoplasm, malignant	8 (0.5%)	5 (0.9%)	3 (0.3%)
80003 Tumor, malignant, NOS	1 (<0.1%)	1 (0.2%)	0 (0%)
80102 Carcinoma in situ, NOS	1 (<0.1%)	1 (0.2%)	0 (0%)
80103 Carcinoma, NOS	29 (2.0%)	20 (3.7%)	9 (1.0%)
80213 Carcinoma, anaplastic, NOS	1 (<0.1%)	1 (0.2%)	0 (0%)
80333 Sarcomatoid carcinoma	1 (<0.1%)	0 (0%)	1 (0.1%)
80413 Small cell carcinoma, NOS	1 (<0.1%)	1 (0.2%)	0 (0%)
80463 Non-small cell carcinoma	8 (0.5%)	8 (1.5%)	0 (0%)
81403 Adenocarcinoma, NOS	1,204 (82%)	470 (87%)	734 (80%)
81443 Adenocarcinoma, intestinal type	2 (0.1%)	0 (0%)	2 (0.2%)
81543 Mixed islet cell and exocrine adenocarcinoma	1 (<0.1%)	1 (0.2%)	0 (0%)
82443 Carcinoid and adenocarcinoma, combined	1 (<0.1%)	0 (0%)	1 (0.1%)
82443 Mixed adenoneuroendocrine carcinoma	1 (<0.1%)	0 (0%)	1 (0.1%)
82553 Adenocarcinoma with mixed subtypes	4 (0.3%)	1 (0.2%)	3 (0.3%)
83233 Mixed cell adenocarcinoma	1 (<0.1%)	0 (0%)	1 (0.1%)
84403 Cystadenocarcinoma, NOS	1 (<0.1%)	1 (0.2%)	0 (0%)
84523 Solid pseudopapillary carcinoma	4 (0.3%)	0 (0%)	4 (0.4%)
84803 Colloid carcinoma	1 (<0.1%)	0 (0%)	1 (0.1%)
84803 Mucinous adenocarcinoma	22 (1.5%)	9 (1.7%)	13 (1.4%)
84803 Mucinous carcinoma	2 (0.1%)	0 (0%)	2 (0.2%)
84803 Mucous adenocarcinoma	1 (<0.1%)	0 (0%)	1 (0.1%)
84813 Mucin-producing adenocarcinoma	2 (0.1%)	2 (0.4%)	0 (0%)
84903 Signet ring cell adenocarcinoma	1 (<0.1%)	0 (0%)	1 (0.1%)
84903 Signet ring cell carcinoma	2 (0.1%)	2 (0.4%)	0 (0%)
85003 Duct adenocarcinoma, NOS	40 (2.7%)	8 (1.5%)	32 (3.5%)
85003 Duct carcinoma, NOS	1 (<0.1%)	0 (0%)	1 (0.1%)
85003 Ductal carcinoma, NOS	55 (3.8%)	0 (0%)	55 (6.0%)
85003 Infiltrating duct adenocarcinoma	16 (1.1%)	2 (0.4%)	14 (1.5%)
85003 Infiltrating duct carcinoma, NOS	28 (1.9%)	6 (1.1%)	22 (2.4%)
85213 Infiltrating ductular carcinoma	7 (0.5%)	0 (0%)	7 (0.8%)
85503 Acinar cell carcinoma	1 (<0.1%)	0 (0%)	1 (0.1%)
85503 Acinic cell adenocarcinoma	1 (<0.1%)	0 (0%)	1 (0.1%)
85603 Adenosquamous carcinoma	6 (0.4%)	2 (0.4%)	4 (0.4%)
85753 Metaplastic carcinoma, NOS	1 (<0.1%)	0 (0%)	1 (0.1%)
Unknown	112	21	91
AJCC.Clinical.Stage.Group				<0.001
EminentlyResectable	309 (23%)	57 (13%)	252 (27%)
LocallyAdvanced	559 (41%)	202 (47%)	357 (39%)
Stage4	482 (36%)	170 (40%)	312 (34%)
Unknown	222	133	89
Vital.Status				<0.001
0 Dead	1,284 (82%)	536 (95%)	748 (74%)
1 Alive	288 (18%)	26 (4.6%)	262 (26%)
MonthDate	8.00 (3.00, 17.00)	8.00 (3.00, 14.00)	8.00 (3.00, 18.00)	0.59
Unknown	4	0	4
Surgery	515 (33%)	131 (23%)	384 (38%)	<0.001
X1st.Course.Chemotherapy.Summ	1,018 (66%)	372 (67%)	646 (65%)	0.46
Unknown	29	9	20
Radiation	442 (28%)	197 (35%)	245 (24%)	<0.001
¹ Statistics presented: Median (IQR); n (%) ² Statistical tests performed: Wilcoxon rank-sum test; chi-square test of independence

DTSurgery %>%
  tbl_summary(
    by = Era,
    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") ~ "**Demographic Table Surgical Patients Era1 vs Era2*") %>%
  bold_labels()

## There was an error in 'add_p()' for variable 'Histo.Behavior.ICD.O.3', p-value omitted:
## Error in stats::fisher.test(data[[variable]], as.factor(data[[by]])): FEXACT error 7(location). LDSTP=18540 is too small for this problem,
##   (pastp=13.5846, ipn_0:=ipoin[itp=208]=1370, stp[ipn_0]=14.0366).
## Increase workspace or consider using 'simulate.p.value=TRUE'

Variable	Overall, N = 515¹	*Demographic Table Surgical Patients Era1 vs Era2		p-value²
Variable	Overall, N = 515¹	Era1, N = 131¹	Era2, N = 384¹	p-value²
Age.at.Diagnosis	66.00 (58.00, 73.00)	65.00 (57.50, 72.00)	67.00 (58.75, 73.00)	0.34
Sex				0.21
1 Male	270 (52%)	62 (47%)	208 (54%)
2 Female	245 (48%)	69 (53%)	176 (46%)
Race.1				>0.99
Non-White	11 (2.1%)	3 (2.3%)	8 (2.1%)
White	504 (98%)	128 (98%)	376 (98%)
Primary.Payer.at.DX				0.18
Insured	430 (92%)	99 (90%)	331 (92%)
Medicaid	34 (7.2%)	8 (7.3%)	26 (7.2%)
Uninsured	5 (1.1%)	3 (2.7%)	2 (0.6%)
Unknown	46	21	25
Marital.Status.at.DX				0.16
Divorced/Separated	58 (12%)	14 (11%)	44 (12%)
Married	310 (63%)	87 (71%)	223 (61%)
Single	74 (15%)	12 (9.8%)	62 (17%)
Widowed	49 (10.0%)	10 (8.1%)	39 (11%)
Unknown	24	8	16
Histo.Behavior.ICD.O.3
80003 Neoplasm, malignant	1 (0.2%)	1 (0.8%)	0 (0%)
80102 Carcinoma in situ, NOS	1 (0.2%)	1 (0.8%)	0 (0%)
81403 Adenocarcinoma, NOS	278 (62%)	92 (78%)	186 (57%)
81443 Adenocarcinoma, intestinal type	2 (0.4%)	0 (0%)	2 (0.6%)
81543 Mixed islet cell and exocrine adenocarcinoma	1 (0.2%)	1 (0.8%)	0 (0%)
82443 Carcinoid and adenocarcinoma, combined	1 (0.2%)	0 (0%)	1 (0.3%)
82443 Mixed adenoneuroendocrine carcinoma	1 (0.2%)	0 (0%)	1 (0.3%)
82553 Adenocarcinoma with mixed subtypes	3 (0.7%)	0 (0%)	3 (0.9%)
83233 Mixed cell adenocarcinoma	1 (0.2%)	0 (0%)	1 (0.3%)
84523 Solid pseudopapillary carcinoma	3 (0.7%)	0 (0%)	3 (0.9%)
84803 Colloid carcinoma	1 (0.2%)	0 (0%)	1 (0.3%)
84803 Mucinous adenocarcinoma	11 (2.5%)	5 (4.2%)	6 (1.8%)
84803 Mucinous carcinoma	2 (0.4%)	0 (0%)	2 (0.6%)
84803 Mucous adenocarcinoma	1 (0.2%)	0 (0%)	1 (0.3%)
85003 Duct adenocarcinoma, NOS	37 (8.3%)	8 (6.8%)	29 (8.8%)
85003 Duct carcinoma, NOS	1 (0.2%)	0 (0%)	1 (0.3%)
85003 Ductal carcinoma, NOS	47 (11%)	0 (0%)	47 (14%)
85003 Infiltrating duct adenocarcinoma	15 (3.4%)	2 (1.7%)	13 (4.0%)
85003 Infiltrating duct carcinoma, NOS	26 (5.8%)	6 (5.1%)	20 (6.1%)
85213 Infiltrating ductular carcinoma	7 (1.6%)	0 (0%)	7 (2.1%)
85603 Adenosquamous carcinoma	5 (1.1%)	2 (1.7%)	3 (0.9%)
85753 Metaplastic carcinoma, NOS	1 (0.2%)	0 (0%)	1 (0.3%)
Unknown	69	13	56
AJCC.Clinical.Stage.Group				0.13
EminentlyResectable	176 (48%)	26 (39%)	150 (50%)
LocallyAdvanced	191 (52%)	41 (61%)	150 (50%)
Unknown	148	64	84
Vital.Status				<0.001
0 Dead	343 (67%)	114 (87%)	229 (60%)
1 Alive	172 (33%)	17 (13%)	155 (40%)
MonthDate	19.00 (10.00, 36.00)	20.00 (11.00, 39.00)	18.00 (9.00, 34.50)	0.12
Unknown	1	0	1
X1st.Course.Chemotherapy.Summ	380 (75%)	98 (76%)	282 (75%)	0.85
Unknown	8	2	6
Radiation	207 (40%)	68 (52%)	139 (36%)	0.002
¹ Statistics presented: Median (IQR); n (%) ² Statistical tests performed: Wilcoxon rank-sum test; chi-square test of independence; Fisher's exact test

DTEminentlyResectable %>%
  tbl_summary(
    by = Era,
    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") ~ "**Demographic Table EminentlyResectable Era1 vs Era2*") %>%
  bold_labels()

## There was an error in 'add_p()' for variable 'AJCC.Clinical.Stage.Group', p-value omitted:
## Error in stats::chisq.test(data[[variable]], as.factor(data[[by]])): 'x' and 'y' must have at least 2 levels

Variable	Overall, N = 309¹	*Demographic Table EminentlyResectable Era1 vs Era2		p-value²
Variable	Overall, N = 309¹	Era1, N = 57¹	Era2, N = 252¹	p-value²
Age.at.Diagnosis	69.00 (61.00, 77.00)	68.00 (63.00, 78.00)	69.00 (61.00, 77.00)	0.39
Sex				0.91
1 Male	147 (48%)	28 (49%)	119 (47%)
2 Female	162 (52%)	29 (51%)	133 (53%)
Race.1				0.56
Non-White	4 (1.3%)	1 (1.8%)	3 (1.2%)
White	305 (99%)	56 (98%)	249 (99%)
Primary.Payer.at.DX				>0.99
Insured	266 (94%)	41 (95%)	225 (94%)
Medicaid	16 (5.7%)	2 (4.7%)	14 (5.8%)
Uninsured	1 (0.4%)	0 (0%)	1 (0.4%)
Unknown	26	14	12
Marital.Status.at.DX				0.083
Divorced/Separated	30 (10%)	2 (3.8%)	28 (11%)
Married	174 (59%)	37 (70%)	137 (56%)
Single	38 (13%)	3 (5.7%)	35 (14%)
Widowed	55 (19%)	11 (21%)	44 (18%)
Unknown	12	4	8
Histo.Behavior.ICD.O.3				0.20
80003 Malignancy	1 (0.4%)	0 (0%)	1 (0.5%)
80003 Neoplasm, malignant	2 (0.8%)	1 (1.9%)	1 (0.5%)
81403 Adenocarcinoma, NOS	199 (75%)	47 (89%)	152 (71%)
82553 Adenocarcinoma with mixed subtypes	1 (0.4%)	0 (0%)	1 (0.5%)
84523 Solid pseudopapillary carcinoma	3 (1.1%)	0 (0%)	3 (1.4%)
84803 Mucinous adenocarcinoma	2 (0.8%)	1 (1.9%)	1 (0.5%)
85003 Duct adenocarcinoma, NOS	13 (4.9%)	2 (3.8%)	11 (5.2%)
85003 Duct carcinoma, NOS	1 (0.4%)	0 (0%)	1 (0.5%)
85003 Ductal carcinoma, NOS	24 (9.0%)	0 (0%)	24 (11%)
85003 Infiltrating duct adenocarcinoma	6 (2.3%)	1 (1.9%)	5 (2.3%)
85003 Infiltrating duct carcinoma, NOS	10 (3.8%)	1 (1.9%)	9 (4.2%)
85213 Infiltrating ductular carcinoma	1 (0.4%)	0 (0%)	1 (0.5%)
85603 Adenosquamous carcinoma	2 (0.8%)	0 (0%)	2 (0.9%)
85753 Metaplastic carcinoma, NOS	1 (0.4%)	0 (0%)	1 (0.5%)
Unknown	43	4	39
AJCC.Clinical.Stage.Group
EminentlyResectable	309 (100%)	57 (100%)	252 (100%)
Vital.Status				<0.001
0 Dead	202 (65%)	52 (91%)	150 (60%)
1 Alive	107 (35%)	5 (8.8%)	102 (40%)
MonthDate	13.00 (6.00, 27.50)	14.00 (7.00, 31.00)	12.00 (6.00, 27.00)	0.56
Unknown	2	0	2
Surgery	176 (57%)	26 (46%)	150 (60%)	0.077
X1st.Course.Chemotherapy.Summ	203 (66%)	35 (61%)	168 (67%)	0.50
Unknown	2	0	2
Radiation	109 (35%)	26 (46%)	83 (33%)	0.10
¹ Statistics presented: Median (IQR); n (%) ² Statistical tests performed: Wilcoxon rank-sum test; chi-square test of independence; Fisher's exact test

DTLocalDataStage4  %>%
  tbl_summary(
    by = Era,
    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") ~ "**Demographic Table Stage 4 Era1 vs Era2*") %>%
  bold_labels()

## Warning in 'add_p()' for variable 'Primary.Payer.at.DX':
##  simpleWarning in stats::chisq.test(data[[variable]], as.factor(data[[by]])): Chi-squared approximation may be incorrect

## There was an error in 'add_p()' for variable 'AJCC.Clinical.Stage.Group', p-value omitted:
## Error in stats::chisq.test(data[[variable]], as.factor(data[[by]])): 'x' and 'y' must have at least 2 levels

Variable	Overall, N = 482¹	*Demographic Table Stage 4 Era1 vs Era2		p-value²
Variable	Overall, N = 482¹	Era1, N = 170¹	Era2, N = 312¹	p-value²
Age.at.Diagnosis	69.00 (61.00, 76.00)	69.00 (60.00, 75.75)	69.00 (61.00, 76.00)	0.56
Sex				0.13
1 Male	271 (56%)	104 (61%)	167 (54%)
2 Female	211 (44%)	66 (39%)	145 (46%)
Race.1				>0.99
Non-White	6 (1.2%)	2 (1.2%)	4 (1.3%)
White	476 (99%)	168 (99%)	308 (99%)
Primary.Payer.at.DX				0.18
Insured	392 (92%)	133 (94%)	259 (91%)
Medicaid	20 (4.7%)	3 (2.1%)	17 (6.0%)
Uninsured	15 (3.5%)	6 (4.2%)	9 (3.2%)
Unknown	55	28	27
Marital.Status.at.DX				0.52
Divorced/Separated	65 (14%)	23 (14%)	42 (14%)
Married	275 (61%)	103 (64%)	172 (59%)
Single	51 (11%)	14 (8.8%)	37 (13%)
Widowed	63 (14%)	20 (12%)	43 (15%)
Unknown	28	10	18
Histo.Behavior.ICD.O.3				0.014
80003 Cancer	2 (0.4%)	0 (0%)	2 (0.7%)
80003 Neoplasm, malignant	1 (0.2%)	0 (0%)	1 (0.3%)
80003 Tumor, malignant, NOS	1 (0.2%)	1 (0.6%)	0 (0%)
80103 Carcinoma, NOS	13 (2.8%)	7 (4.1%)	6 (2.0%)
80333 Sarcomatoid carcinoma	1 (0.2%)	0 (0%)	1 (0.3%)
80413 Small cell carcinoma, NOS	1 (0.2%)	1 (0.6%)	0 (0%)
80463 Non-small cell carcinoma	5 (1.1%)	5 (3.0%)	0 (0%)
81403 Adenocarcinoma, NOS	409 (88%)	148 (88%)	261 (89%)
82553 Adenocarcinoma with mixed subtypes	2 (0.4%)	1 (0.6%)	1 (0.3%)
84803 Mucinous adenocarcinoma	12 (2.6%)	3 (1.8%)	9 (3.1%)
84813 Mucin-producing adenocarcinoma	2 (0.4%)	2 (1.2%)	0 (0%)
84903 Signet ring cell adenocarcinoma	1 (0.2%)	0 (0%)	1 (0.3%)
84903 Signet ring cell carcinoma	1 (0.2%)	1 (0.6%)	0 (0%)
85003 Duct adenocarcinoma, NOS	3 (0.6%)	0 (0%)	3 (1.0%)
85003 Ductal carcinoma, NOS	4 (0.9%)	0 (0%)	4 (1.4%)
85003 Infiltrating duct adenocarcinoma	1 (0.2%)	0 (0%)	1 (0.3%)
85003 Infiltrating duct carcinoma, NOS	1 (0.2%)	0 (0%)	1 (0.3%)
85503 Acinar cell carcinoma	1 (0.2%)	0 (0%)	1 (0.3%)
85503 Acinic cell adenocarcinoma	1 (0.2%)	0 (0%)	1 (0.3%)
85603 Adenosquamous carcinoma	1 (0.2%)	0 (0%)	1 (0.3%)
Unknown	19	1	18
AJCC.Clinical.Stage.Group
Stage4	482 (100%)	170 (100%)	312 (100%)
Vital.Status				<0.001
0 Dead	440 (91%)	168 (99%)	272 (87%)
1 Alive	42 (8.7%)	2 (1.2%)	40 (13%)
MonthDate	4.00 (2.00, 9.00)	4.00 (2.00, 8.00)	4.00 (1.75, 9.00)	0.59
Surgery	45 (9.3%)	9 (5.3%)	36 (12%)	0.037
X1st.Course.Chemotherapy.Summ	299 (63%)	108 (64%)	191 (62%)	0.73
Unknown	7	2	5
Radiation	38 (7.9%)	21 (12%)	17 (5.4%)	0.012
¹ Statistics presented: Median (IQR); n (%) ² Statistical tests performed: Wilcoxon rank-sum test; chi-square test of independence; Fisher's exact test

DTLocalized %>%
  tbl_summary(
    by = Era,
    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") ~ "**Demographic Table Localized Era1 vs Era2*") %>%
  bold_labels()

## There was an error in 'add_p()' for variable 'Histo.Behavior.ICD.O.3', p-value omitted:
## Error in stats::fisher.test(data[[variable]], as.factor(data[[by]])): FEXACT error 7(location). LDSTP=18480 is too small for this problem,
##   (pastp=14.9639, ipn_0:=ipoin[itp=152]=14651, stp[ipn_0]=6.85118).
## Increase workspace or consider using 'simulate.p.value=TRUE'

Variable	Overall, N = 868¹	*Demographic Table Localized Era1 vs Era2		p-value²
Variable	Overall, N = 868¹	Era1, N = 259¹	Era2, N = 609¹	p-value²
Age.at.Diagnosis	70.00 (61.00, 77.00)	70.00 (61.00, 78.00)	70.00 (62.00, 77.00)	0.53
Sex				0.67
1 Male	427 (49%)	124 (48%)	303 (50%)
2 Female	441 (51%)	135 (52%)	306 (50%)
Race.1				>0.99
Non-White	11 (1.3%)	3 (1.2%)	8 (1.3%)
White	857 (99%)	256 (99%)	601 (99%)
Primary.Payer.at.DX				0.022
Insured	742 (94%)	211 (96%)	531 (93%)
Medicaid	41 (5.2%)	5 (2.3%)	36 (6.3%)
Uninsured	8 (1.0%)	4 (1.8%)	4 (0.7%)
Unknown	77	39	38
Marital.Status.at.DX				0.006
Divorced/Separated	84 (10%)	18 (7.3%)	66 (11%)
Married	509 (61%)	164 (67%)	345 (59%)
Single	103 (12%)	18 (7.3%)	85 (14%)
Widowed	138 (17%)	46 (19%)	92 (16%)
Unknown	34	13	21
Histo.Behavior.ICD.O.3
80003 Malignancy	1 (0.1%)	0 (0%)	1 (0.2%)
80003 Neoplasm, malignant	3 (0.4%)	2 (0.8%)	1 (0.2%)
80103 Carcinoma, NOS	9 (1.1%)	7 (2.8%)	2 (0.4%)
80213 Carcinoma, anaplastic, NOS	1 (0.1%)	1 (0.4%)	0 (0%)
80463 Non-small cell carcinoma	3 (0.4%)	3 (1.2%)	0 (0%)
81403 Adenocarcinoma, NOS	650 (81%)	222 (88%)	428 (78%)
81443 Adenocarcinoma, intestinal type	1 (0.1%)	0 (0%)	1 (0.2%)
82443 Carcinoid and adenocarcinoma, combined	1 (0.1%)	0 (0%)	1 (0.2%)
82553 Adenocarcinoma with mixed subtypes	2 (0.2%)	0 (0%)	2 (0.4%)
84523 Solid pseudopapillary carcinoma	3 (0.4%)	0 (0%)	3 (0.5%)
84803 Mucinous adenocarcinoma	8 (1.0%)	5 (2.0%)	3 (0.5%)
84803 Mucinous carcinoma	2 (0.2%)	0 (0%)	2 (0.4%)
84803 Mucous adenocarcinoma	1 (0.1%)	0 (0%)	1 (0.2%)
85003 Duct adenocarcinoma, NOS	30 (3.7%)	6 (2.4%)	24 (4.4%)
85003 Duct carcinoma, NOS	1 (0.1%)	0 (0%)	1 (0.2%)
85003 Ductal carcinoma, NOS	38 (4.7%)	0 (0%)	38 (6.9%)
85003 Infiltrating duct adenocarcinoma	15 (1.9%)	2 (0.8%)	13 (2.4%)
85003 Infiltrating duct carcinoma, NOS	21 (2.6%)	3 (1.2%)	18 (3.3%)
85213 Infiltrating ductular carcinoma	7 (0.9%)	0 (0%)	7 (1.3%)
85603 Adenosquamous carcinoma	3 (0.4%)	1 (0.4%)	2 (0.4%)
85753 Metaplastic carcinoma, NOS	1 (0.1%)	0 (0%)	1 (0.2%)
Unknown	67	7	60
AJCC.Clinical.Stage.Group				<0.001
EminentlyResectable	309 (36%)	57 (22%)	252 (41%)
LocallyAdvanced	559 (64%)	202 (78%)	357 (59%)
Vital.Status				<0.001
0 Dead	670 (77%)	249 (96%)	421 (69%)
1 Alive	198 (23%)	10 (3.9%)	188 (31%)
MonthDate	10.00 (5.00, 22.00)	10.00 (6.00, 18.50)	11.00 (5.00, 24.00)	0.31
Unknown	2	0	2
Surgery	367 (42%)	67 (26%)	300 (49%)	<0.001
X1st.Course.Chemotherapy.Summ	615 (72%)	197 (77%)	418 (70%)	0.034
Unknown	11	3	8
Radiation	364 (42%)	146 (56%)	218 (36%)	<0.001
¹ Statistics presented: Median (IQR); n (%) ² Statistical tests performed: Wilcoxon rank-sum test; chi-square test of independence; Fisher's exact test

DTLocallyAdvanced %>%
  tbl_summary(
    by = Era,
    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") ~ "**Demographic Table Locally Advanced Era1 vs Era2*") %>%
  bold_labels()

## There was an error in 'add_p()' for variable 'Histo.Behavior.ICD.O.3', p-value omitted:
## Error in stats::fisher.test(data[[variable]], as.factor(data[[by]])): FEXACT error 7(location). LDSTP=18540 is too small for this problem,
##   (pastp=17.9441, ipn_0:=ipoin[itp=89]=5918, stp[ipn_0]=17.9929).
## Increase workspace or consider using 'simulate.p.value=TRUE'

## There was an error in 'add_p()' for variable 'AJCC.Clinical.Stage.Group', p-value omitted:
## Error in stats::chisq.test(data[[variable]], as.factor(data[[by]])): 'x' and 'y' must have at least 2 levels

Variable	Overall, N = 559¹	*Demographic Table Locally Advanced Era1 vs Era2		p-value²
Variable	Overall, N = 559¹	Era1, N = 202¹	Era2, N = 357¹	p-value²
Age.at.Diagnosis	70.00 (61.50, 77.00)	70.00 (61.00, 78.00)	70.00 (62.00, 77.00)	0.93
Sex				0.41
1 Male	280 (50%)	96 (48%)	184 (52%)
2 Female	279 (50%)	106 (52%)	173 (48%)
Race.1				>0.99
Non-White	7 (1.3%)	2 (1.0%)	5 (1.4%)
White	552 (99%)	200 (99%)	352 (99%)
Primary.Payer.at.DX				0.015
Insured	476 (94%)	170 (96%)	306 (92%)
Medicaid	25 (4.9%)	3 (1.7%)	22 (6.6%)
Uninsured	7 (1.4%)	4 (2.3%)	3 (0.9%)
Unknown	51	25	26
Marital.Status.at.DX				0.056
Divorced/Separated	54 (10%)	16 (8.3%)	38 (11%)
Married	335 (62%)	127 (66%)	208 (60%)
Single	65 (12%)	15 (7.8%)	50 (15%)
Widowed	83 (15%)	35 (18%)	48 (14%)
Unknown	22	9	13
Histo.Behavior.ICD.O.3
80003 Neoplasm, malignant	1 (0.2%)	1 (0.5%)	0 (0%)
80103 Carcinoma, NOS	9 (1.7%)	7 (3.5%)	2 (0.6%)
80213 Carcinoma, anaplastic, NOS	1 (0.2%)	1 (0.5%)	0 (0%)
80463 Non-small cell carcinoma	3 (0.6%)	3 (1.5%)	0 (0%)
81403 Adenocarcinoma, NOS	451 (84%)	175 (88%)	276 (82%)
81443 Adenocarcinoma, intestinal type	1 (0.2%)	0 (0%)	1 (0.3%)
82443 Carcinoid and adenocarcinoma, combined	1 (0.2%)	0 (0%)	1 (0.3%)
82553 Adenocarcinoma with mixed subtypes	1 (0.2%)	0 (0%)	1 (0.3%)
84803 Mucinous adenocarcinoma	6 (1.1%)	4 (2.0%)	2 (0.6%)
84803 Mucinous carcinoma	2 (0.4%)	0 (0%)	2 (0.6%)
84803 Mucous adenocarcinoma	1 (0.2%)	0 (0%)	1 (0.3%)
85003 Duct adenocarcinoma, NOS	17 (3.2%)	4 (2.0%)	13 (3.9%)
85003 Ductal carcinoma, NOS	14 (2.6%)	0 (0%)	14 (4.2%)
85003 Infiltrating duct adenocarcinoma	9 (1.7%)	1 (0.5%)	8 (2.4%)
85003 Infiltrating duct carcinoma, NOS	11 (2.1%)	2 (1.0%)	9 (2.7%)
85213 Infiltrating ductular carcinoma	6 (1.1%)	0 (0%)	6 (1.8%)
85603 Adenosquamous carcinoma	1 (0.2%)	1 (0.5%)	0 (0%)
Unknown	24	3	21
AJCC.Clinical.Stage.Group
LocallyAdvanced	559 (100%)	202 (100%)	357 (100%)
Vital.Status				<0.001
0 Dead	468 (84%)	197 (98%)	271 (76%)
1 Alive	91 (16%)	5 (2.5%)	86 (24%)
MonthDate	10.00 (5.00, 19.00)	9.00 (5.00, 15.00)	10.00 (4.00, 21.00)	0.62
Surgery	191 (34%)	41 (20%)	150 (42%)	<0.001
X1st.Course.Chemotherapy.Summ	412 (75%)	162 (81%)	250 (71%)	0.011
Unknown	9	3	6
Radiation	255 (46%)	120 (59%)	135 (38%)	<0.001
¹ Statistics presented: Median (IQR); n (%) ² Statistical tests performed: Wilcoxon rank-sum test; chi-square test of independence; Fisher's exact test

SurvivalLocalData <-
  LocalDataSetDT %>%
  select(Age.at.Diagnosis, Sex, Race.1, Era, AJCC.Clinical.Stage.Group, Marital.Status.at.DX, Primary.Payer.at.DX, Vital.Status, MonthDate, Surgery, X1st.Course.Chemotherapy.Summ, Radiation)

SurvivalLocalData <- 
  SurvivalLocalData %>%
  mutate(SurvivalLocalData, Age = ifelse(Age.at.Diagnosis >= 85, "85+", 
                                               ifelse(Age.at.Diagnosis >= 75, "75-84", 
                                                      ifelse(Age.at.Diagnosis >= 65, "65-74", 
                                                             ifelse(Age.at.Diagnosis >=0, "0-65", NA)))))

ORLocalData <-
  SurvivalLocalData %>%
  select(Age, Sex, Race.1, Era, AJCC.Clinical.Stage.Group, Marital.Status.at.DX, Primary.Payer.at.DX, Vital.Status, MonthDate, Surgery, X1st.Course.Chemotherapy.Summ, Radiation)

#####Logistic Regression Ensure that Era is labeled as 1= Era2 and 0=Era1
ORLocalData$Era[ORLocalData$Era == "Era2"] <- 1


ORLocalData$Era[ORLocalData$Era == "Era1"] <- 0

table(ORLocalData$Era)

## 
##    0    1 
##  562 1010

#####Survival Analysis Ensure that vital status is labeled as 1= Alive and 2=Death
SurvivalLocalData$Vital.Status[SurvivalLocalData$Vital.Status == "0  Dead"] <- 2


SurvivalLocalData$Vital.Status[SurvivalLocalData$Vital.Status == "1  Alive"] <- 1

SurvivalLocalData$Vital.Status <- as.numeric(SurvivalLocalData$Vital.Status)
SurvivalLocalData$MonthDate <- as.numeric(SurvivalLocalData$MonthDate)

ORLocalData$Era <- as.numeric(ORLocalData$Era)

ORLocalDataStage4 <- 
  subset(ORLocalData, AJCC.Clinical.Stage.Group  == "Stage4")


ORLocalized <- 
  subset(ORLocalData, AJCC.Clinical.Stage.Group  == "LocallyAdvanced" | AJCC.Clinical.Stage.Group    == "EminentlyResectable")

ORLocallyAdvanced <- 
  subset(ORLocalData, AJCC.Clinical.Stage.Group  == "LocallyAdvanced")

OREminentlyResectable <- 
  subset(ORLocalData, AJCC.Clinical.Stage.Group  == "EminentlyResectable")

ORSurgery <- 
  subset(ORLocalData, Surgery    == "Yes")

ORSurgery$AJCC.Clinical.Stage.Group[ORSurgery$AJCC.Clinical.Stage.Group == "Stage4"] <- NA

SurvivalLocalDataStage4 <- 
  subset(SurvivalLocalData, AJCC.Clinical.Stage.Group    == "Stage4")


SurvivalLocalized <- 
  subset(SurvivalLocalData, AJCC.Clinical.Stage.Group    == "LocallyAdvanced" | AJCC.Clinical.Stage.Group    == "EminentlyResectable")

SurvivalLocallyAdvanced <- 
  subset(SurvivalLocalData, AJCC.Clinical.Stage.Group    == "LocallyAdvanced")

SurvivalEminentlyResectable <- 
  subset(SurvivalLocalData, AJCC.Clinical.Stage.Group    == "EminentlyResectable")

SurvivalSurgery <- 
  subset(SurvivalLocalData, Surgery  == "Yes")

SurvivalSurgery$AJCC.Clinical.Stage.Group[SurvivalSurgery$AJCC.Clinical.Stage.Group == "Stage4"] <- NA

UVEveryoneOR <- ORLocalData %>%
  select(Primary.Payer.at.DX, Marital.Status.at.DX, AJCC.Clinical.Stage.Group, Surgery, Radiation, Era) %>%
  tbl_uvregression(
    method = glm,
    y = Era,
    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 Everyone
MVOREveryoneOR <- 
  glm(Era ~ Primary.Payer.at.DX + AJCC.Clinical.Stage.Group + Surgery + Radiation, 
      data = ORLocalData,
      family = binomial("logit"), 
      na.action =na.omit)

###continue on to merge the table sets
MVORTableEveryoneOR <-
  tbl_regression(MVOREveryoneOR, exponentiate = T,
                 pvalue_fun = ~style_pvalue(.x, digits = 2),
  ) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

tbl_merge(
  list(UVEveryoneOR, MVORTableEveryoneOR),
  tab_spanner = c("All Patients, **Univariable**", "**Multivariable**")
) %>%
  bold_labels() %>%
  italicize_levels()

Characteristic	All Patients, Univariable				Multivariable
Characteristic	N	OR¹	95% CI¹	p-value	OR¹	95% CI¹	p-value
Primary.Payer.at.DX	1,411
Insured		—	—		—	—
Medicaid		1.82	1.07, 3.25	0.033	2.70	1.31, 6.30	0.012
Uninsured		0.60	0.28, 1.33	0.20	0.70	0.29, 1.70	0.41
Marital.Status.at.DX	1,494
Divorced/Separated		—	—
Married		0.78	0.55, 1.10	0.16
Single		1.46	0.92, 2.34	0.11
Widowed		0.75	0.49, 1.14	0.18
AJCC.Clinical.Stage.Group	1,350
EminentlyResectable		—	—		—	—
LocallyAdvanced		0.40	0.28, 0.56	<0.001	0.43	0.29, 0.63	<0.001
Stage4		0.42	0.29, 0.58	<0.001	0.41	0.26, 0.61	<0.001
Surgery	1,572
No		—	—		—	—
Yes		2.02	1.60, 2.55	<0.001	2.78	2.00, 3.92	<0.001
Radiation	1,572
No		—	—		—	—
Yes		0.59	0.47, 0.74	<0.001	0.38	0.28, 0.51	<0.001
¹ OR = Odds Ratio, CI = Confidence Interval

UVLocalizedOR <- ORLocalized %>%
  select(Primary.Payer.at.DX, Marital.Status.at.DX, AJCC.Clinical.Stage.Group, Surgery, Radiation, X1st.Course.Chemotherapy.Summ, Era) %>%
  tbl_uvregression(
    method = glm,
    y = Era,
    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 Localized
MVORLocalizedOR <- 
  glm(Era ~ Primary.Payer.at.DX + Marital.Status.at.DX + AJCC.Clinical.Stage.Group + X1st.Course.Chemotherapy.Summ + Surgery + Radiation, 
      data = ORLocalized,
      family = binomial("logit"), 
      na.action =na.omit)

###continue on to merge the table sets
MVORTableLocalizedOR <-
  tbl_regression(MVORLocalizedOR, exponentiate = T,
                 pvalue_fun = ~style_pvalue(.x, digits = 2),
  ) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

tbl_merge(
  list(UVLocalizedOR, MVORTableLocalizedOR),
  tab_spanner = c("Localized, **Univariable**", "**Multivariable**")
) %>%
  bold_labels() %>%
  italicize_levels()

Characteristic	Localized, Univariable				Multivariable
Characteristic	N	OR¹	95% CI¹	p-value	OR¹	95% CI¹	p-value
Primary.Payer.at.DX	791
Insured		—	—		—	—
Medicaid		2.86	1.21, 8.41	0.030	2.08	0.81, 6.44	0.16
Uninsured		0.40	0.09, 1.69	0.19	0.31	0.06, 1.46	0.13
Marital.Status.at.DX	834
Divorced/Separated		—	—		—	—
Married		0.57	0.32, 0.98	0.049	0.52	0.25, 0.99	0.058
Single		1.29	0.62, 2.68	0.50	0.95	0.39, 2.26	0.91
Widowed		0.55	0.29, 1.01	0.059	0.49	0.22, 1.03	0.067
AJCC.Clinical.Stage.Group	868
EminentlyResectable		—	—		—	—
LocallyAdvanced		0.40	0.28, 0.56	<0.001	0.43	0.29, 0.64	<0.001
Surgery	868
No		—	—		—	—
Yes		2.78	2.03, 3.85	<0.001	2.85	1.95, 4.23	<0.001
Radiation	868
No		—	—		—	—
Yes		0.43	0.32, 0.58	<0.001	0.40	0.26, 0.60	<0.001
X1st.Course.Chemotherapy.Summ	857
No		—	—		—	—
Yes		0.68	0.48, 0.96	0.028	1.02	0.63, 1.65	0.94
¹ OR = Odds Ratio, CI = Confidence Interval

UVEminentlyOR <- OREminentlyResectable %>%
  select(Age, Marital.Status.at.DX, Surgery, Radiation, Era) %>%
  tbl_uvregression(
    method = glm,
    y = Era,
    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 Eminentlyresectable
MVOREminentlyOR <- 
  glm(Era ~ Age + Surgery + Radiation, 
      data = OREminentlyResectable,
      family = binomial("logit"), 
      na.action =na.omit)

###continue on to merge the table sets
MVORTableEminentlyOR <-
  tbl_regression(MVOREminentlyOR, exponentiate = T,
                 pvalue_fun = ~style_pvalue(.x, digits = 2),
  ) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

tbl_merge(
  list(UVEminentlyOR, MVORTableEminentlyOR),
  tab_spanner = c("Eminently Resectable, **Univariable**", "**Multivariable**")
) %>%
  bold_labels() %>%
  italicize_levels()

Characteristic	Eminently Resectable, Univariable				Multivariable
Characteristic	N	OR¹	95% CI¹	p-value	OR¹	95% CI¹	p-value
Age	309
0-65		—	—		—	—
65-74		1.11	0.53, 2.34	0.78	1.19	0.56, 2.55	0.65
75-84		0.83	0.39, 1.79	0.63	0.95	0.42, 2.15	0.89
85+		0.49	0.19, 1.35	0.15	0.58	0.20, 1.72	0.31
Marital.Status.at.DX	297
Divorced/Separated		—	—
Married		0.26	0.04, 0.94	0.078
Single		0.83	0.10, 5.36	0.85
Widowed		0.29	0.04, 1.17	0.12
Surgery	309
No		—	—		—	—
Yes		1.75	0.98, 3.15	0.057	1.65	0.87, 3.16	0.13
Radiation	309
No		—	—		—	—
Yes		0.59	0.33, 1.05	0.072	0.52	0.29, 0.96	0.034
¹ OR = Odds Ratio, CI = Confidence Interval

UVLocallyAdvancedOR <- ORLocallyAdvanced %>%
  select(Primary.Payer.at.DX, Marital.Status.at.DX, Surgery, X1st.Course.Chemotherapy.Summ, Radiation, Era) %>%
  tbl_uvregression(
    method = glm,
    y = Era,
    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 Locally Advanced
MVORLocallyAdvnacedOR <- 
  glm(Era ~ Primary.Payer.at.DX + Surgery + X1st.Course.Chemotherapy.Summ + Radiation, 
      data = ORLocallyAdvanced,
      family = binomial("logit"), 
      na.action =na.omit)

###continue on to merge the table sets
MVORTableLocallyAdvancedOR <-
  tbl_regression(MVORLocallyAdvnacedOR, exponentiate = T,
                 pvalue_fun = ~style_pvalue(.x, digits = 2),
  ) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

tbl_merge(
  list(UVLocallyAdvancedOR, MVORTableLocallyAdvancedOR),
  tab_spanner = c("Locally Advanced, **Univariable**", "**Multivariable**")
) %>%
  bold_labels() %>%
  italicize_levels()

Characteristic	Locally Advanced, Univariable				Multivariable
Characteristic	N	OR¹	95% CI¹	p-value	OR¹	95% CI¹	p-value
Primary.Payer.at.DX	508
Insured		—	—		—	—
Medicaid		4.07	1.39, 17.4	0.024	3.80	1.23, 16.8	0.038
Uninsured		0.42	0.08, 1.91	0.26	0.31	0.06, 1.56	0.15
Marital.Status.at.DX	537
Divorced/Separated		—	—
Married		0.69	0.36, 1.27	0.24
Single		1.40	0.62, 3.22	0.42
Widowed		0.58	0.27, 1.18	0.14
Surgery	559
No		—	—		—	—
Yes		2.85	1.92, 4.29	<0.001	3.74	2.39, 6.00	<0.001
X1st.Course.Chemotherapy.Summ	550
No		—	—		—	—
Yes		0.57	0.37, 0.86	0.009	0.90	0.52, 1.54	0.70
Radiation	559
No		—	—		—	—
Yes		0.42	0.29, 0.59	<0.001	0.36	0.22, 0.57	<0.001
¹ OR = Odds Ratio, CI = Confidence Interval

UVSurgeryOR <- ORSurgery %>%
  select(Primary.Payer.at.DX, Marital.Status.at.DX, AJCC.Clinical.Stage.Group, Radiation, Era) %>%
  tbl_uvregression(
    method = glm,
    y = Era,
    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 Surgery
MVORSurgeryOR <- 
  glm(Era ~ Primary.Payer.at.DX + AJCC.Clinical.Stage.Group + Radiation, 
      data = ORSurgery,
      family = binomial("logit"), 
      na.action =na.omit)

###continue on to merge the table sets
MVORTableSurgeryOR <-
  tbl_regression(MVORSurgeryOR, exponentiate = T,
                 pvalue_fun = ~style_pvalue(.x, digits = 2),
  ) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

tbl_merge(
  list(UVSurgeryOR, MVORTableSurgeryOR),
  tab_spanner = c("Surgery, **Univariable**", "**Multivariable**")
) %>%
  bold_labels() %>%
  italicize_levels()

Characteristic	Surgery, Univariable				Multivariable
Characteristic	N	OR¹	95% CI¹	p-value	OR¹	95% CI¹	p-value
Primary.Payer.at.DX	469
Insured		—	—		—	—
Medicaid		0.97	0.44, 2.36	0.95	1.88	0.51, 12.1	0.41
Uninsured		0.20	0.03, 1.22	0.080	0.21	0.02, 1.90	0.14
Marital.Status.at.DX	491
Divorced/Separated		—	—
Married		0.82	0.41, 1.53	0.54
Single		1.64	0.69, 3.95	0.26
Widowed		1.24	0.50, 3.18	0.65
AJCC.Clinical.Stage.Group	367
EminentlyResectable		—	—		—	—
LocallyAdvanced		0.63	0.37, 1.08	0.10	0.68	0.36, 1.25	0.22
Radiation	515
No		—	—		—	—
Yes		0.53	0.35, 0.78	0.002	0.34	0.18, 0.63	<0.001
¹ OR = Odds Ratio, CI = Confidence Interval

UVStage4OR <- ORLocalDataStage4 %>%
  select(Primary.Payer.at.DX, Radiation, Era) %>%
  tbl_uvregression(
    method = glm,
    y = Era,
    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 complications
MVORStage4OR <- 
  glm(Era ~ Primary.Payer.at.DX + Radiation, 
      data = ORLocalDataStage4,
      family = binomial("logit"), 
      na.action =na.omit)

###continue on to merge the table sets
MVORTableORStage4 <-
  tbl_regression(MVORStage4OR, exponentiate = T,
                 pvalue_fun = ~style_pvalue(.x, digits = 2),
  ) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

tbl_merge(
  list(UVStage4OR, MVORTableORStage4),
  tab_spanner = c("Stage 4, **Univariable**", "**Multivariable**")
) %>%
  bold_labels() %>%
  italicize_levels()

Characteristic	Stage 4, Univariable				Multivariable
Characteristic	N	OR¹	95% CI¹	p-value	OR¹	95% CI¹	p-value
Primary.Payer.at.DX	427
Insured		—	—		—	—
Medicaid		2.91	0.96, 12.6	0.093	2.86	0.93, 12.5	0.10
Uninsured		0.77	0.27, 2.34	0.63	0.95	0.32, 3.01	0.93
Radiation	482
No		—	—		—	—
Yes		0.41	0.21, 0.80	0.009	0.34	0.17, 0.70	0.003
¹ OR = Odds Ratio, CI = Confidence Interval

### Univariant Survival Neoadj
UVSurvEveryone <-
  SurvivalLocalData %>%
  select(Age, Sex, Race.1, Era, AJCC.Clinical.Stage.Group, Primary.Payer.at.DX, Marital.Status.at.DX, Vital.Status, MonthDate) %>%
  tbl_uvregression(
    method = coxph,
    y = Surv(MonthDate, Vital.Status),
    exponentiate = TRUE) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

###Multivariant survival Neoadj
MVSurvEveryone <- 
  coxph(Surv(MonthDate, Vital.Status) ~ Age + Primary.Payer.at.DX + Era + AJCC.Clinical.Stage.Group + Marital.Status.at.DX,
        data = SurvivalLocalData) %>%
  tbl_regression(exponentiate = T
  ) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

###Merged Neo Univariant and Multivariant
tbl_merge(
  list(UVSurvEveryone, MVSurvEveryone),
  tab_spanner = c("Everyone,**Univariable**", "**Multivariable**")
) %>%
  bold_labels() %>%
  italicize_levels()

Characteristic	Everyone,Univariable				Multivariable
Characteristic	N	HR¹	95% CI¹	p-value	HR¹	95% CI¹	p-value
Age	1,568
0-65		—	—		—	—
65-74		1.24	1.09, 1.43	0.002	1.35	1.14, 1.61	<0.001
75-84		1.71	1.48, 1.97	<0.001	1.87	1.55, 2.25	<0.001
85+		2.90	2.35, 3.58	<0.001	2.96	2.25, 3.89	<0.001
Sex	1,568
1 Male		—	—
2 Female		1.03	0.92, 1.15	0.6
Race.1	1,568
Non-White		—	—
White		0.74	0.45, 1.21	0.2
Era	1,568
Era1		—	—		—	—
Era2		0.74	0.67, 0.83	<0.001	0.79	0.69, 0.91	<0.001
AJCC.Clinical.Stage.Group	1,348
EminentlyResectable		—	—		—	—
LocallyAdvanced		1.62	1.37, 1.91	<0.001	1.57	1.31, 1.87	<0.001
Stage4		3.59	3.02, 4.26	<0.001	3.92	3.25, 4.74	<0.001
Primary.Payer.at.DX	1,408
Insured		—	—		—	—
Medicaid		0.67	0.51, 0.88	0.004	0.99	0.72, 1.37	>0.9
Uninsured		1.55	1.02, 2.34	0.039	1.34	0.86, 2.10	0.2
Marital.Status.at.DX	1,492
Divorced/Separated		—	—		—	—
Married		0.91	0.76, 1.10	0.3	0.95	0.77, 1.17	0.6
Single		0.86	0.68, 1.09	0.2	0.97	0.74, 1.28	0.8
Widowed		1.40	1.12, 1.74	0.003	1.14	0.88, 1.48	0.3
¹ HR = Hazard Ratio, CI = Confidence Interval

survfit(Surv(MonthDate, Vital.Status) ~ Era, data = SurvivalLocalData)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Era, data = SurvivalLocalData)
## 
##    8 observations deleted due to missingness 
##             n events median 0.95LCL 0.95UCL
## Era=Era1  562    536      8       7       9
## Era=Era2 1006    746     10       9      11

survfit(Surv(MonthDate, Vital.Status) ~ Age, data = SurvivalLocalData)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Age, data = SurvivalLocalData)
## 
##    8 observations deleted due to missingness 
##             n events median 0.95LCL 0.95UCL
## Age=0-65  533    410     13      11      14
## Age=65-74 521    418     10       8      11
## Age=75-84 389    343      7       6       8
## Age=85+   125    111      3       2       4

survfit(Surv(MonthDate, Vital.Status) ~ Sex, data = SurvivalLocalData)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Sex, data = SurvivalLocalData)
## 
##    8 observations deleted due to missingness 
##                 n events median 0.95LCL 0.95UCL
## Sex=1  Male   811    668      9       8      10
## Sex=2  Female 757    614      9       8      10

survfit(Surv(MonthDate, Vital.Status) ~ Race.1, data = SurvivalLocalData)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Race.1, data = SurvivalLocalData)
## 
##    8 observations deleted due to missingness 
##                     n events median 0.95LCL 0.95UCL
## Race.1=Non-White   20     16    4.5       3      27
## Race.1=White     1548   1266    9.0       9      10

survfit(Surv(MonthDate, Vital.Status) ~ AJCC.Clinical.Stage.Group, data = SurvivalLocalData)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ AJCC.Clinical.Stage.Group, 
##     data = SurvivalLocalData)
## 
##    228 observations deleted due to missingness 
##                                                 n events median 0.95LCL 0.95UCL
## AJCC.Clinical.Stage.Group=EminentlyResectable 307    201     18      15      24
## AJCC.Clinical.Stage.Group=LocallyAdvanced     559    468     10       9      12
## AJCC.Clinical.Stage.Group=Stage4              482    440      4       3       5

survfit(Surv(MonthDate, Vital.Status) ~ Marital.Status.at.DX, data = SurvivalLocalData)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Marital.Status.at.DX, 
##     data = SurvivalLocalData)
## 
##    84 observations deleted due to missingness 
##                                           n events median 0.95LCL 0.95UCL
## Marital.Status.at.DX=Divorced/Separated 169    137      8       6      10
## Marital.Status.at.DX=Married            908    751     10       9      11
## Marital.Status.at.DX=Single             181    135     11       8      14
## Marital.Status.at.DX=Widowed            234    199      6       5       8

survfit(Surv(MonthDate, Vital.Status) ~ Primary.Payer.at.DX, data = SurvivalLocalData)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Primary.Payer.at.DX, 
##     data = SurvivalLocalData)
## 
##    168 observations deleted due to missingness 
##                                  n events median 0.95LCL 0.95UCL
## Primary.Payer.at.DX=Insured   1306   1065      9       8      10
## Primary.Payer.at.DX=Medicaid    76     55     13       8      26
## Primary.Payer.at.DX=Uninsured   26     23      3       2      13

fit <- survfit(Surv(MonthDate, Vital.Status) ~ Era,
               data = SurvivalLocalData)



ggsurvplot(fit, data = SurvivalLocalData, risk.table = TRUE)

## Warning: Vectorized input to `element_text()` is not officially supported.
## Results may be unexpected or may change in future versions of ggplot2.

ggsurvplot(
   fit,                     # survfit object with calculated statistics.
   data = SurvivalLocalData,  # data used to fit survival curves. 
   risk.table = TRUE,       # show risk table.
   pval = TRUE,             # show p-value of log-rank test.
   conf.int = TRUE,         # show confidence intervals for 
                            # point estimaes of survival curves.
   xlim = c(0,200),        # present narrower X axis, but not affect
                            # survival estimates.
   break.time.by = 25,     # break X axis in time intervals by 500.
   ggtheme = theme_minimal(), # customize plot and risk table with a theme.
 risk.table.y.text.col = T, # colour risk table text annotations.
  risk.table.y.text = FALSE # show bars instead of names in text annotations
                            # in legend of risk table
)

## Warning: Vectorized input to `element_text()` is not officially supported.
## Results may be unexpected or may change in future versions of ggplot2.

### Univariant Survival Neoadj

UVSurvStage4 <-
  SurvivalLocalDataStage4 %>%
  select(Age, Sex, Race.1, Era, Primary.Payer.at.DX, Marital.Status.at.DX, Vital.Status, MonthDate) %>%
  tbl_uvregression(
    method = coxph,
    y = Surv(MonthDate, Vital.Status),
    exponentiate = TRUE) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

###Multivariant survival Neoadj
MVSurvStage4 <- 
  coxph(Surv(MonthDate, Vital.Status) ~ Age + Sex + Primary.Payer.at.DX + Era,
        data = SurvivalLocalDataStage4) %>%
  tbl_regression(exponentiate = T
  ) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

###Merged Neo Univariant and Multivariant
tbl_merge(
  list(UVSurvStage4, MVSurvStage4),
  tab_spanner = c("Stage4, **Univariable**", "**Multivariable**")
) %>%
  bold_labels() %>%
  italicize_levels()

Characteristic	Stage4, Univariable				Multivariable
Characteristic	N	HR¹	95% CI¹	p-value	HR¹	95% CI¹	p-value
Age	482
0-65		—	—		—	—
65-74		1.36	1.08, 1.70	0.008	1.41	1.09, 1.83	0.009
75-84		1.64	1.27, 2.11	<0.001	1.88	1.41, 2.51	<0.001
85+		3.29	2.22, 4.89	<0.001	3.50	2.28, 5.38	<0.001
Sex	482
1 Male		—	—		—	—
2 Female		1.02	0.84, 1.23	0.8	0.88	0.71, 1.08	0.2
Race.1	482
Non-White		—	—
White		0.46	0.20, 1.03	0.058
Era	482
Era1		—	—		—	—
Era2		0.87	0.72, 1.06	0.2	0.87	0.71, 1.08	0.2
Primary.Payer.at.DX	427
Insured		—	—		—	—
Medicaid		0.62	0.37, 1.03	0.066	0.88	0.52, 1.51	0.7
Uninsured		0.98	0.57, 1.67	>0.9	1.27	0.73, 2.22	0.4
Marital.Status.at.DX	454
Divorced/Separated		—	—
Married		0.93	0.70, 1.24	0.6
Single		0.93	0.63, 1.38	0.7
Widowed		1.42	0.99, 2.05	0.060
¹ HR = Hazard Ratio, CI = Confidence Interval

survfit(Surv(MonthDate, Vital.Status) ~ Era, data = SurvivalLocalDataStage4)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Era, data = SurvivalLocalDataStage4)
## 
##            n events median 0.95LCL 0.95UCL
## Era=Era1 170    168      4       3       5
## Era=Era2 312    272      4       3       5

survfit(Surv(MonthDate, Vital.Status) ~ Age, data = SurvivalLocalDataStage4)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Age, data = SurvivalLocalDataStage4)
## 
##             n events median 0.95LCL 0.95UCL
## Age=0-65  175    158      6       5       8
## Age=65-74 163    150      4       3       5
## Age=75-84 110    101      3       2       4
## Age=85+    34     31      2       1       3

survfit(Surv(MonthDate, Vital.Status) ~ Sex, data = SurvivalLocalDataStage4)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Sex, data = SurvivalLocalDataStage4)
## 
##                 n events median 0.95LCL 0.95UCL
## Sex=1  Male   271    248      4       3       5
## Sex=2  Female 211    192      4       3       5

survfit(Surv(MonthDate, Vital.Status) ~ Race.1, data = SurvivalLocalData)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Race.1, data = SurvivalLocalData)
## 
##    8 observations deleted due to missingness 
##                     n events median 0.95LCL 0.95UCL
## Race.1=Non-White   20     16    4.5       3      27
## Race.1=White     1548   1266    9.0       9      10

survfit(Surv(MonthDate, Vital.Status) ~ Marital.Status.at.DX, data = SurvivalLocalDataStage4)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Marital.Status.at.DX, 
##     data = SurvivalLocalDataStage4)
## 
##    28 observations deleted due to missingness 
##                                           n events median 0.95LCL 0.95UCL
## Marital.Status.at.DX=Divorced/Separated  65     56      3       2       5
## Marital.Status.at.DX=Married            275    252      5       4       6
## Marital.Status.at.DX=Single              51     48      3       2       7
## Marital.Status.at.DX=Widowed             63     60      2       2       3

survfit(Surv(MonthDate, Vital.Status) ~ Primary.Payer.at.DX, data = SurvivalLocalDataStage4)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Primary.Payer.at.DX, 
##     data = SurvivalLocalDataStage4)
## 
##    55 observations deleted due to missingness 
##                                 n events median 0.95LCL 0.95UCL
## Primary.Payer.at.DX=Insured   392    359      4       3       5
## Primary.Payer.at.DX=Medicaid   20     16      7       2      14
## Primary.Payer.at.DX=Uninsured  15     14      3       2      NA

fit <- survfit(Surv(MonthDate, Vital.Status) ~ Era,
               data = SurvivalLocalDataStage4)



ggsurvplot(fit, data = SurvivalLocalDataStage4, risk.table = TRUE)

## Warning: Vectorized input to `element_text()` is not officially supported.
## Results may be unexpected or may change in future versions of ggplot2.

ggsurvplot(
   fit,                     # survfit object with calculated statistics.
   data = SurvivalLocalDataStage4,  # data used to fit survival curves. 
   risk.table = TRUE,       # show risk table.
   pval = TRUE,             # show p-value of log-rank test.
   conf.int = TRUE,         # show confidence intervals for 
                            # point estimaes of survival curves.
   xlim = c(0,200),        # present narrower X axis, but not affect
                            # survival estimates.
   break.time.by = 25,     # break X axis in time intervals by 500.
   ggtheme = theme_minimal(), # customize plot and risk table with a theme.
 risk.table.y.text.col = T, # colour risk table text annotations.
  risk.table.y.text = FALSE # show bars instead of names in text annotations
                            # in legend of risk table
)

## Warning: Vectorized input to `element_text()` is not officially supported.
## Results may be unexpected or may change in future versions of ggplot2.

### Univariant Survival Neoadj
UVSurvLocalized <-
  SurvivalLocalized %>%
  select(Age, Sex, Race.1, Era, Primary.Payer.at.DX, Marital.Status.at.DX, Vital.Status, MonthDate) %>%
  tbl_uvregression(
    method = coxph,
    y = Surv(MonthDate, Vital.Status),
    exponentiate = TRUE) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

###Multivariant survival Neoadj
MVSurvLocalized <- 
  coxph(Surv(MonthDate, Vital.Status) ~ Age + Marital.Status.at.DX + Era,
        data = SurvivalLocalized) %>%
  tbl_regression(exponentiate = T
  ) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

###Merged Neo Univariant and Multivariant
tbl_merge(
  list(UVSurvLocalized, MVSurvLocalized),
  tab_spanner = c("Localized, **Univariable**", "**Multivariable**")
) %>%
  bold_labels() %>%
  italicize_levels()

Characteristic	Localized, Univariable				Multivariable
Characteristic	N	HR¹	95% CI¹	p-value	HR¹	95% CI¹	p-value
Age	866
0-65		—	—		—	—
65-74		1.27	1.05, 1.54	0.016	1.29	1.06, 1.58	0.012
75-84		1.91	1.57, 2.33	<0.001	1.86	1.51, 2.30	<0.001
85+		3.00	2.24, 4.02	<0.001	2.51	1.80, 3.49	<0.001
Sex	866
1 Male		—	—
2 Female		1.02	0.87, 1.18	0.8
Race.1	866
Non-White		—	—
White		0.89	0.42, 1.88	0.8
Era	866
Era1		—	—		—	—
Era2		0.66	0.56, 0.77	<0.001	0.69	0.58, 0.81	<0.001
Primary.Payer.at.DX	789
Insured		—	—
Medicaid		0.77	0.54, 1.12	0.2
Uninsured		1.24	0.59, 2.61	0.6
Marital.Status.at.DX	833
Divorced/Separated		—	—		—	—
Married		1.00	0.77, 1.30	>0.9	0.86	0.66, 1.12	0.3
Single		0.84	0.60, 1.19	0.3	0.89	0.63, 1.26	0.5
Widowed		1.51	1.11, 2.06	0.009	1.00	0.72, 1.39	>0.9
¹ HR = Hazard Ratio, CI = Confidence Interval

survfit(Surv(MonthDate, Vital.Status) ~ Era, data = SurvivalLocalized)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Era, data = SurvivalLocalized)
## 
##    2 observations deleted due to missingness 
##            n events median 0.95LCL 0.95UCL
## Era=Era1 259    249     10       9      11
## Era=Era2 607    420     15      13      16

survfit(Surv(MonthDate, Vital.Status) ~ Age, data = SurvivalLocalized)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Age, data = SurvivalLocalized)
## 
##    2 observations deleted due to missingness 
##             n events median 0.95LCL 0.95UCL
## Age=0-65  283    198     17      15      21
## Age=65-74 286    214     14      12      16
## Age=75-84 229    198      9       8      10
## Age=85+    68     59      5       3       9

survfit(Surv(MonthDate, Vital.Status) ~ Sex, data = SurvivalLocalized)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Sex, data = SurvivalLocalized)
## 
##    2 observations deleted due to missingness 
##                 n events median 0.95LCL 0.95UCL
## Sex=1  Male   426    337     13      11      15
## Sex=2  Female 440    332     12      10      14

survfit(Surv(MonthDate, Vital.Status) ~ Race.1, data = SurvivalLocalized)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Race.1, data = SurvivalLocalized)
## 
##    2 observations deleted due to missingness 
##                    n events median 0.95LCL 0.95UCL
## Race.1=Non-White  10      7      9       5      NA
## Race.1=White     856    662     12      11      14

survfit(Surv(MonthDate, Vital.Status) ~ Marital.Status.at.DX, data = SurvivalLocalized)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Marital.Status.at.DX, 
##     data = SurvivalLocalized)
## 
##    35 observations deleted due to missingness 
##                                           n events median 0.95LCL 0.95UCL
## Marital.Status.at.DX=Divorced/Separated  84     64     13      10      19
## Marital.Status.at.DX=Married            508    401     14      12      15
## Marital.Status.at.DX=Single             103     67     17      13      21
## Marital.Status.at.DX=Widowed            138    111      9       7      10

survfit(Surv(MonthDate, Vital.Status) ~ Primary.Payer.at.DX, data = SurvivalLocalized)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Primary.Payer.at.DX, 
##     data = SurvivalLocalized)
## 
##    79 observations deleted due to missingness 
##                                 n events median 0.95LCL 0.95UCL
## Primary.Payer.at.DX=Insured   740    567   12.0      11      14
## Primary.Payer.at.DX=Medicaid   41     30   19.0      10      34
## Primary.Payer.at.DX=Uninsured   8      7   14.5       1      NA

fit <- survfit(Surv(MonthDate, Vital.Status) ~ Era,
               data = SurvivalLocalized)



ggsurvplot(fit, data = SurvivalLocalized, risk.table = TRUE)

## Warning: Vectorized input to `element_text()` is not officially supported.
## Results may be unexpected or may change in future versions of ggplot2.

ggsurvplot(
   fit,                     # survfit object with calculated statistics.
   data = SurvivalLocalized,  # data used to fit survival curves. 
   risk.table = TRUE,       # show risk table.
   pval = TRUE,             # show p-value of log-rank test.
   conf.int = TRUE,         # show confidence intervals for 
                            # point estimaes of survival curves.
   xlim = c(0,150),        # present narrower X axis, but not affect
                            # survival estimates.
   break.time.by = 25,     # break X axis in time intervals by 500.
   ggtheme = theme_minimal(), # customize plot and risk table with a theme.
 risk.table.y.text.col = T, # colour risk table text annotations.
  risk.table.y.text = FALSE # show bars instead of names in text annotations
                            # in legend of risk table
)

## Warning: Vectorized input to `element_text()` is not officially supported.
## Results may be unexpected or may change in future versions of ggplot2.

### Univariant Survival Neoadj
UVSurvLocallyAdvanced <-
  SurvivalLocallyAdvanced %>%
  select(Age, Sex, Race.1, Era, Primary.Payer.at.DX, Marital.Status.at.DX, Vital.Status, MonthDate) %>%
  tbl_uvregression(
    method = coxph,
    y = Surv(MonthDate, Vital.Status),
    exponentiate = TRUE) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

###Multivariant survival Neoadj
MVSurvLocallyAdvanced <- 
  coxph(Surv(MonthDate, Vital.Status) ~ Age + Marital.Status.at.DX + Era,
        data = SurvivalLocallyAdvanced) %>%
  tbl_regression(exponentiate = T
  ) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

###Merged Neo Univariant and Multivariant
tbl_merge(
  list(UVSurvLocallyAdvanced, MVSurvLocallyAdvanced),
  tab_spanner = c("Locally Advanced, **Univariable**", "**Multivariable**")
) %>%
  bold_labels() %>%
  italicize_levels()

Characteristic	Locally Advanced, Univariable				Multivariable
Characteristic	N	HR¹	95% CI¹	p-value	HR¹	95% CI¹	p-value
Age	559
0-65		—	—		—	—
65-74		1.18	0.94, 1.49	0.2	1.21	0.95, 1.53	0.12
75-84		1.69	1.34, 2.14	<0.001	1.59	1.23, 2.05	<0.001
85+		3.01	2.10, 4.32	<0.001	2.33	1.57, 3.46	<0.001
Sex	559
1 Male		—	—
2 Female		1.10	0.92, 1.32	0.3
Race.1	559
Non-White		—	—
White		0.80	0.36, 1.80	0.6
Era	559
Era1		—	—		—	—
Era2		0.70	0.58, 0.84	<0.001	0.71	0.59, 0.86	<0.001
Primary.Payer.at.DX	508
Insured		—	—
Medicaid		0.74	0.47, 1.16	0.2
Uninsured		1.36	0.64, 2.87	0.4
Marital.Status.at.DX	537
Divorced/Separated		—	—		—	—
Married		0.92	0.67, 1.27	0.6	0.83	0.60, 1.15	0.3
Single		0.93	0.62, 1.40	0.7	0.98	0.64, 1.48	>0.9
Widowed		1.73	1.19, 2.53	0.004	1.22	0.81, 1.84	0.3
¹ HR = Hazard Ratio, CI = Confidence Interval

survfit(Surv(MonthDate, Vital.Status) ~ Era, data = SurvivalLocallyAdvanced)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Era, data = SurvivalLocallyAdvanced)
## 
##            n events median 0.95LCL 0.95UCL
## Era=Era1 202    197     10       9      11
## Era=Era2 357    271     12      10      15

survfit(Surv(MonthDate, Vital.Status) ~ Age, data = SurvivalLocallyAdvanced)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Age, data = SurvivalLocallyAdvanced)
## 
##             n events median 0.95LCL 0.95UCL
## Age=0-65  178    142     15      12      17
## Age=65-74 186    149     11       9      14
## Age=75-84 154    139      8       7      10
## Age=85+    41     38      3       2       9

survfit(Surv(MonthDate, Vital.Status) ~ Sex, data = SurvivalLocallyAdvanced)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Sex, data = SurvivalLocallyAdvanced)
## 
##                 n events median 0.95LCL 0.95UCL
## Sex=1  Male   280    237     11      10      14
## Sex=2  Female 279    231     10       9      11

survfit(Surv(MonthDate, Vital.Status) ~ Race.1, data = SurvivalLocallyAdvanced)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Race.1, data = SurvivalLocallyAdvanced)
## 
##                    n events median 0.95LCL 0.95UCL
## Race.1=Non-White   7      6      9       3      NA
## Race.1=White     552    462     10       9      12

survfit(Surv(MonthDate, Vital.Status) ~ Marital.Status.at.DX, data = SurvivalLocallyAdvanced)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Marital.Status.at.DX, 
##     data = SurvivalLocallyAdvanced)
## 
##    22 observations deleted due to missingness 
##                                           n events median 0.95LCL 0.95UCL
## Marital.Status.at.DX=Divorced/Separated  54     44     10       8      14
## Marital.Status.at.DX=Married            335    287     12      10      14
## Marital.Status.at.DX=Single              65     49     10       7      18
## Marital.Status.at.DX=Widowed             83     71      7       5       9

survfit(Surv(MonthDate, Vital.Status) ~ Primary.Payer.at.DX, data = SurvivalLocallyAdvanced)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Primary.Payer.at.DX, 
##     data = SurvivalLocallyAdvanced)
## 
##    51 observations deleted due to missingness 
##                                 n events median 0.95LCL 0.95UCL
## Primary.Payer.at.DX=Insured   476    396     10       9      12
## Primary.Payer.at.DX=Medicaid   25     20     13       6      45
## Primary.Payer.at.DX=Uninsured   7      7      9       1      NA

fit <- survfit(Surv(MonthDate, Vital.Status) ~ Era,
               data = SurvivalLocallyAdvanced)



ggsurvplot(fit, data = SurvivalLocallyAdvanced, risk.table = TRUE)

## Warning: Vectorized input to `element_text()` is not officially supported.
## Results may be unexpected or may change in future versions of ggplot2.

ggsurvplot(
   fit,                     # survfit object with calculated statistics.
   data = SurvivalLocallyAdvanced,  # data used to fit survival curves. 
   risk.table = TRUE,       # show risk table.
   pval = TRUE,             # show p-value of log-rank test.
   conf.int = TRUE,         # show confidence intervals for 
                            # point estimaes of survival curves.
   xlim = c(0,150),        # present narrower X axis, but not affect
                            # survival estimates.
   break.time.by = 25,     # break X axis in time intervals by 500.
   ggtheme = theme_minimal(), # customize plot and risk table with a theme.
 risk.table.y.text.col = T, # colour risk table text annotations.
  risk.table.y.text = FALSE # show bars instead of names in text annotations
                            # in legend of risk table
)

## Warning: Vectorized input to `element_text()` is not officially supported.
## Results may be unexpected or may change in future versions of ggplot2.

### Univariant Survival Neoadj
UVSurvEminentlyResectable <-
  SurvivalEminentlyResectable %>%
  select(Age, Sex, Race.1, Era, Primary.Payer.at.DX, Marital.Status.at.DX, Vital.Status, MonthDate) %>%
  tbl_uvregression(
    method = coxph,
    y = Surv(MonthDate, Vital.Status),
    exponentiate = TRUE) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

## Warning: Problem with `mutate()` input `model`.
## x Loglik converged before variable  2 ; coefficient may be infinite. 
## ℹ Input `model` is `map(...)`.

## Warning in fitter(X, Y, istrat, offset, init, control, weights = weights, :
## Loglik converged before variable 2 ; coefficient may be infinite.

###Multivariant survival Neoadj
MVSurvEminentlyResectable <- 
  coxph(Surv(MonthDate, Vital.Status) ~ Age + Marital.Status.at.DX + Era,
        data = SurvivalEminentlyResectable) %>%
  tbl_regression(exponentiate = T
  ) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

###Merged Neo Univariant and Multivariant
tbl_merge(
  list(UVSurvEminentlyResectable, MVSurvEminentlyResectable),
  tab_spanner = c("Eminently Resectable, **Univariable**", "**Multivariable**")
) %>%
  bold_labels() %>%
  italicize_levels()

Characteristic	Eminently Resectable, Univariable				Multivariable
Characteristic	N	HR¹	95% CI¹	p-value	HR¹	95% CI¹	p-value
Age	307
0-65		—	—		—	—
65-74		1.46	1.02, 2.09	0.038	1.53	1.05, 2.25	0.028
75-84		2.39	1.65, 3.44	<0.001	2.50	1.69, 3.72	<0.001
85+		3.43	2.07, 5.70	<0.001	3.68	2.01, 6.75	<0.001
Sex	307
1 Male		—	—
2 Female		0.91	0.69, 1.20	0.5
Race.1	307
Non-White		—	—
White		1.71	0.24, 12.2	0.6
Era	307
Era1		—	—		—	—
Era2		0.72	0.52, 0.99	0.042	0.88	0.63, 1.23	0.4
Primary.Payer.at.DX	281
Insured		—	—
Medicaid		0.84	0.44, 1.60	0.6
Uninsured		0.00	0.00, Inf	>0.9
Marital.Status.at.DX	296
Divorced/Separated		—	—		—	—
Married		1.09	0.68, 1.76	0.7	0.91	0.56, 1.47	0.7
Single		0.70	0.37, 1.32	0.3	0.76	0.40, 1.44	0.4
Widowed		1.43	0.83, 2.44	0.2	0.82	0.46, 1.48	0.5
¹ HR = Hazard Ratio, CI = Confidence Interval

survfit(Surv(MonthDate, Vital.Status) ~ Era, data = SurvivalEminentlyResectable)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Era, data = SurvivalEminentlyResectable)
## 
##    2 observations deleted due to missingness 
##            n events median 0.95LCL 0.95UCL
## Era=Era1  57     52     15      11      24
## Era=Era2 250    149     19      16      26

survfit(Surv(MonthDate, Vital.Status) ~ Age, data = SurvivalEminentlyResectable)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Age, data = SurvivalEminentlyResectable)
## 
##    2 observations deleted due to missingness 
##             n events median 0.95LCL 0.95UCL
## Age=0-65  105     56     29      23      51
## Age=65-74 100     65     22      15      29
## Age=75-84  75     59     10       9      15
## Age=85+    27     21      7       4      22

survfit(Surv(MonthDate, Vital.Status) ~ Sex, data = SurvivalEminentlyResectable)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Sex, data = SurvivalEminentlyResectable)
## 
##    2 observations deleted due to missingness 
##                 n events median 0.95LCL 0.95UCL
## Sex=1  Male   146    100     16      12      25
## Sex=2  Female 161    101     19      15      29

survfit(Surv(MonthDate, Vital.Status) ~ Race.1, data = SurvivalEminentlyResectable)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Race.1, data = SurvivalEminentlyResectable)
## 
##    2 observations deleted due to missingness 
##                    n events median 0.95LCL 0.95UCL
## Race.1=Non-White   3      1      8       8      NA
## Race.1=White     304    200     18      15      24

survfit(Surv(MonthDate, Vital.Status) ~ Marital.Status.at.DX, data = SurvivalEminentlyResectable)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Marital.Status.at.DX, 
##     data = SurvivalEminentlyResectable)
## 
##    13 observations deleted due to missingness 
##                                           n events median 0.95LCL 0.95UCL
## Marital.Status.at.DX=Divorced/Separated  30     20     22      12      NA
## Marital.Status.at.DX=Married            173    114     18      14      25
## Marital.Status.at.DX=Single              38     18     29      17      NA
## Marital.Status.at.DX=Widowed             55     40     12       9      22

survfit(Surv(MonthDate, Vital.Status) ~ Primary.Payer.at.DX, data = SurvivalEminentlyResectable)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Primary.Payer.at.DX, 
##     data = SurvivalEminentlyResectable)
## 
##    28 observations deleted due to missingness 
##                                 n events median 0.95LCL 0.95UCL
## Primary.Payer.at.DX=Insured   264    171     17      14      24
## Primary.Payer.at.DX=Medicaid   16     10     19      12      NA
## Primary.Payer.at.DX=Uninsured   1      0     NA      NA      NA

fit <- survfit(Surv(MonthDate, Vital.Status) ~ Era,
               data = SurvivalEminentlyResectable)



ggsurvplot(fit, data = SurvivalEminentlyResectable, risk.table = TRUE)

## Warning: Vectorized input to `element_text()` is not officially supported.
## Results may be unexpected or may change in future versions of ggplot2.

ggsurvplot(
   fit,                     # survfit object with calculated statistics.
   data = SurvivalEminentlyResectable,  # data used to fit survival curves. 
   risk.table = TRUE,       # show risk table.
   pval = TRUE,             # show p-value of log-rank test.
   conf.int = TRUE,         # show confidence intervals for 
                            # point estimaes of survival curves.
   xlim = c(0,150),        # present narrower X axis, but not affect
                            # survival estimates.
   break.time.by = 25,     # break X axis in time intervals by 500.
   ggtheme = theme_minimal(), # customize plot and risk table with a theme.
 risk.table.y.text.col = T, # colour risk table text annotations.
  risk.table.y.text = FALSE # show bars instead of names in text annotations
                            # in legend of risk table
)

## Warning: Vectorized input to `element_text()` is not officially supported.
## Results may be unexpected or may change in future versions of ggplot2.

### Univariant Survival Neoadj
UVSurvSurgery <-
  SurvivalSurgery %>%
  select(Age, Sex, Race.1, Era, AJCC.Clinical.Stage.Group, Primary.Payer.at.DX, Marital.Status.at.DX, Vital.Status, MonthDate) %>%
  tbl_uvregression(
    method = coxph,
    y = Surv(MonthDate, Vital.Status),
    exponentiate = TRUE) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

###Multivariant survival Neoadj
MVSurvSurgery <- 
  coxph(Surv(MonthDate, Vital.Status) ~ Age + Sex + AJCC.Clinical.Stage.Group + Primary.Payer.at.DX + Era,
        data = SurvivalSurgery) %>%
  tbl_regression(exponentiate = T
  ) %>%
  bold_p(t = 0.10) %>%
  bold_labels() %>%
  italicize_levels()

###Merged Neo Univariant and Multivariant
tbl_merge(
  list(UVSurvSurgery, MVSurvSurgery),
  tab_spanner = c("Surgery, **Univariable**", "**Multivariable**")
) %>%
  bold_labels() %>%
  italicize_levels()

Characteristic	Surgery, Univariable				Multivariable
Characteristic	N	HR¹	95% CI¹	p-value	HR¹	95% CI¹	p-value
Age	514
0-65		—	—		—	—
65-74		1.26	0.99, 1.60	0.066	1.08	0.78, 1.50	0.6
75-84		1.58	1.19, 2.09	0.001	1.39	0.96, 2.01	0.077
85+		2.04	0.65, 6.40	0.2	1.66	0.40, 6.86	0.5
Sex	514
1 Male		—	—		—	—
2 Female		1.23	0.99, 1.52	0.062	1.08	0.82, 1.43	0.6
Race.1	514
Non-White		—	—
White		0.60	0.28, 1.27	0.2
Era	514
Era1		—	—		—	—
Era2		0.81	0.64, 1.02	0.075	0.76	0.55, 1.05	0.10
AJCC.Clinical.Stage.Group	366
EminentlyResectable		—	—		—	—
LocallyAdvanced		1.41	1.08, 1.83	0.010	1.37	1.04, 1.81	0.026
Primary.Payer.at.DX	468
Insured		—	—		—	—
Medicaid		0.60	0.38, 0.96	0.034	0.77	0.43, 1.40	0.4
Uninsured		1.19	0.44, 3.19	0.7	1.04	0.32, 3.31	>0.9
Marital.Status.at.DX	491
Divorced/Separated		—	—
Married		0.96	0.68, 1.35	0.8
Single		0.82	0.53, 1.27	0.4
Widowed		1.36	0.86, 2.14	0.2
¹ HR = Hazard Ratio, CI = Confidence Interval

survfit(Surv(MonthDate, Vital.Status) ~ Era, data = SurvivalSurgery)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Era, data = SurvivalSurgery)
## 
##    1 observation deleted due to missingness 
##            n events median 0.95LCL 0.95UCL
## Era=Era1 131    114     21      16      26
## Era=Era2 383    228     26      21      30

survfit(Surv(MonthDate, Vital.Status) ~ Age, data = SurvivalSurgery)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Age, data = SurvivalSurgery)
## 
##    1 observation deleted due to missingness 
##             n events median 0.95LCL 0.95UCL
## Age=0-65  228    137     28      24      35
## Age=65-74 187    126     24      19      28
## Age=75-84  94     76     16      13      22
## Age=85+     5      3      9       4      NA

survfit(Surv(MonthDate, Vital.Status) ~ Sex, data = SurvivalSurgery)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Sex, data = SurvivalSurgery)
## 
##    1 observation deleted due to missingness 
##                 n events median 0.95LCL 0.95UCL
## Sex=1  Male   270    177     26      23      30
## Sex=2  Female 244    165     20      18      26

survfit(Surv(MonthDate, Vital.Status) ~ Race.1, data = SurvivalSurgery)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Race.1, data = SurvivalSurgery)
## 
##    1 observation deleted due to missingness 
##                    n events median 0.95LCL 0.95UCL
## Race.1=Non-White  11      7     13       8      NA
## Race.1=White     503    335     24      21      27

survfit(Surv(MonthDate, Vital.Status) ~ Marital.Status.at.DX, data = SurvivalSurgery)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Marital.Status.at.DX, 
##     data = SurvivalSurgery)
## 
##    24 observations deleted due to missingness 
##                                           n events median 0.95LCL 0.95UCL
## Marital.Status.at.DX=Divorced/Separated  58     40     21      14      35
## Marital.Status.at.DX=Married            310    214     24      20      27
## Marital.Status.at.DX=Single              74     39     29      21      38
## Marital.Status.at.DX=Widowed             49     35     16      12      32

survfit(Surv(MonthDate, Vital.Status) ~ Primary.Payer.at.DX, data = SurvivalSurgery)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ Primary.Payer.at.DX, 
##     data = SurvivalSurgery)
## 
##    47 observations deleted due to missingness 
##                                 n events median 0.95LCL 0.95UCL
## Primary.Payer.at.DX=Insured   429    288     22      19      27
## Primary.Payer.at.DX=Medicaid   34     19     32      26      NA
## Primary.Payer.at.DX=Uninsured   5      4     25      20      NA

survfit(Surv(MonthDate, Vital.Status) ~ AJCC.Clinical.Stage.Group   , data = SurvivalSurgery)

## Call: survfit(formula = Surv(MonthDate, Vital.Status) ~ AJCC.Clinical.Stage.Group, 
##     data = SurvivalSurgery)
## 
##    149 observations deleted due to missingness 
##                                                 n events median 0.95LCL 0.95UCL
## AJCC.Clinical.Stage.Group=EminentlyResectable 175     98     31      26      38
## AJCC.Clinical.Stage.Group=LocallyAdvanced     191    136     21      18      28

fit <- survfit(Surv(MonthDate, Vital.Status) ~ Era,
               data = SurvivalSurgery)



ggsurvplot(fit, data = SurvivalSurgery, risk.table = TRUE)

## Warning: Vectorized input to `element_text()` is not officially supported.
## Results may be unexpected or may change in future versions of ggplot2.

ggsurvplot(
   fit,                     # survfit object with calculated statistics.
   data = SurvivalSurgery,  # data used to fit survival curves. 
   risk.table = TRUE,       # show risk table.
   pval = TRUE,             # show p-value of log-rank test.
   conf.int = TRUE,         # show confidence intervals for 
                            # point estimaes of survival curves.
   xlim = c(0,200),        # present narrower X axis, but not affect
                            # survival estimates.
   break.time.by = 25,     # break X axis in time intervals by 500.
   ggtheme = theme_minimal(), # customize plot and risk table with a theme.
 risk.table.y.text.col = T, # colour risk table text annotations.
  risk.table.y.text = FALSE # show bars instead of names in text annotations
                            # in legend of risk table
)

## Warning: Vectorized input to `element_text()` is not officially supported.
## Results may be unexpected or may change in future versions of ggplot2.

Local Data Survival Analysis

Abdimajid Mohamed

3/17/2021