library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.3 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(dplyr)
library(stringi)
library(tinytex)
library(ggplot2)
library(janitor)##
## Attaching package: 'janitor'
##
## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.testlibrary(flextable)##
## Attaching package: 'flextable'
##
## The following object is masked from 'package:purrr':
##
## composelibrary(highcharter)## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
##
## Attaching package: 'highcharter'
##
## The following object is masked from 'package:flextable':
##
## colorizeRead in the flaps dataset from 2016-2019
#setwd("C:/Users/kathyochoa/Documents/DATA_205/Project")
flaps2016 <- read.csv("2016_Flap.csv", na = c("", "NA"))
flaps2017 <- read.csv("2017_Flap.csv", na = c("", "NA"))
flaps2018 <- read.csv("2018_Flap.csv", na = c("", "NA"))
flaps2019 <- read.csv("2019_Flap.csv", na = c("", "NA"))# comCols used to merge flaps2016 and flaps2017
# comCols2 used to merge flaps2016/2017 and 2018/2019
comCols1 <- intersect(names(flaps2016), names(flaps2017))
comCols2 <- intersect(names(flaps2018), names(flaps2019))
# Full join the 4 dataframes
allYears <- flaps2016 %>%
full_join(flaps2017, by = comCols1) %>%
full_join(flaps2018, by = comCols2) %>%
full_join(flaps2019, by = comCols2)
head(allYears)## X.1 X age age_neonate amonth aweekend died discwt dispuniform dqtr drg
## 1 12 12 58 -9 2 0 0 4.999956 6 1 623
## 2 272 272 53 -9 2 0 0 4.999956 5 1 264
## 3 321 321 69 -9 1 0 0 4.999956 1 1 572
## 4 440 440 53 -9 8 0 0 4.999956 1 3 624
## 5 528 528 63 -9 7 0 0 4.999956 6 3 854
## 6 1046 1046 72 -9 6 0 0 4.999956 5 2 570
## drgver drg_nopoa dxver elective female hcup_ed hcup_division hosp_nis i10_dx1
## 1 33 623 10 0 0 2 1 10001 E11621
## 2 33 264 10 0 1 2 1 10001 E1152
## 3 33 572 10 0 0 2 1 10001 L02416
## 4 33 624 10 0 0 2 1 10001 E11621
## 5 33 854 10 0 0 2 1 10001 A419
## 6 33 570 10 0 1 2 1 10001 L89154
## i10_dx2 i10_dx3 i10_dx4 i10_dx5 i10_dx6 i10_dx7 i10_dx8 i10_dx9 i10_dx10
## 1 K921 L97519 E1142 E1165 I10 E785 I480 Z7901 E668
## 2 E11621 L03116 L97529 I2510 I10 Z720 E785 J45909 Z8619
## 3 B9561 L03116 I10 I252 I2510 E785 F17210 T783XXS R7309
## 4 L97519 I10 Z794 K449 K219 F17210 E669 Z6835 Z89429
## 5 L03115 E1140 E11621 L97419 B952 Z794 I10 E669 E785
## 6 F0390 E119 I10 D649 I5181 R791 E039 M1990 Z96643
## i10_dx11 i10_dx12 i10_dx13 i10_dx14 i10_dx15 i10_dx16 i10_dx17 i10_dx18
## 1 Z6832 I739 F17210 N401 R3911 E11649 Z794 <NA>
## 2 F319 L570 Z6839 I739 B951 Z9114 E1165 Z794
## 3 T63304A <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 4 F418 Z8614 G8929 M545 B954 <NA> <NA> <NA>
## 5 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 6 Z87891 G40909 I351 Z86718 Z7901 Z95828 I2510 L0889
## i10_dx19 i10_dx20 i10_dx21 i10_dx22 i10_dx23 i10_dx24 i10_dx25 i10_dx26
## 1 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 2 E669 <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 3 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 4 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 5 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 6 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## i10_dx27 i10_dx28 i10_dx29 i10_dx30 i10_ecause1 i10_ecause2 i10_ecause3
## 1 <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 2 <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 3 <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 4 <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 5 <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 6 <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## i10_ecause4 i10_ndx i10_necause i10_npr i10_pr1 i10_pr2 i10_pr3 i10_pr4
## 1 <NA> 17 0 3 0JBQ0ZZ 02HV33Z B546ZZA <NA>
## 2 <NA> 19 0 2 0JBR0ZZ 0Y9N3ZX <NA> <NA>
## 3 <NA> 11 0 1 0JBM0ZZ <NA> <NA> <NA>
## 4 <NA> 15 0 1 0JBQ0ZZ <NA> <NA> <NA>
## 5 <NA> 10 0 2 0JBQ0ZZ 02HV33Z <NA> <NA>
## 6 <NA> 18 0 4 0HD8XZZ 30233K1 30233N1 0JB90ZZ
## i10_pr5 i10_pr6 i10_pr7 i10_pr8 i10_pr9 i10_pr10 i10_pr11 i10_pr12 i10_pr13
## 1 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 2 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 3 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 4 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 5 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 6 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## i10_pr14 i10_pr15 key_nis los mdc mdc_nopoa nis_stratum pay1 pl_nchs prday1
## 1 <NA> <NA> 10004372 4 10 10 1221 2 3 1
## 2 <NA> <NA> 10063532 2 5 5 1221 2 1 0
## 3 <NA> <NA> 10074390 4 9 9 1221 1 3 1
## 4 <NA> <NA> 10100884 3 10 10 1221 2 1 0
## 5 <NA> <NA> 10122030 5 18 18 1221 3 1 0
## 6 <NA> <NA> 10233573 5 9 9 1221 1 1 1
## prday2 prday3 prday4 prday5 prday6 prday7 prday8 prday9 prday10 prday11
## 1 3 3 -99 -99 -99 -99 -99 -99 -99 -99
## 2 0 -99 -99 -99 -99 -99 -99 -99 -99 -99
## 3 -99 -99 -99 -99 -99 -99 -99 -99 -99 -99
## 4 -99 -99 -99 -99 -99 -99 -99 -99 -99 -99
## 5 0 -99 -99 -99 -99 -99 -99 -99 -99 -99
## 6 1 1 2 -99 -99 -99 -99 -99 -99 -99
## prday12 prday13 prday14 prday15 prver race totchg tran_in tran_out year
## 1 -99 -99 -99 -99 10 2 25219 0 0 2016
## 2 -99 -99 -99 -99 10 3 21814 0 2 2016
## 3 -99 -99 -99 -99 10 1 25152 0 0 2016
## 4 -99 -99 -99 -99 10 1 19816 0 0 2016
## 5 -99 -99 -99 -99 10 1 31522 0 0 2016
## 6 -99 -99 -99 -99 10 1 41261 0 2 2016
## zipinc_qrtl flap i10_dx31 i10_dx32 i10_dx33 i10_dx34 i10_dx35 i10_dx36
## 1 1 TRUE <NA> <NA> <NA> <NA> <NA> <NA>
## 2 3 TRUE <NA> <NA> <NA> <NA> <NA> <NA>
## 3 4 TRUE <NA> <NA> <NA> <NA> <NA> <NA>
## 4 3 TRUE <NA> <NA> <NA> <NA> <NA> <NA>
## 5 3 TRUE <NA> <NA> <NA> <NA> <NA> <NA>
## 6 3 TRUE <NA> <NA> <NA> <NA> <NA> <NA>
## i10_dx37 i10_dx38 i10_dx39 i10_dx40 i10_pr16 i10_pr17 i10_pr18 i10_pr19
## 1 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 2 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 3 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 4 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 5 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## 6 <NA> <NA> <NA> <NA> <NA> <NA> <NA> <NA>
## i10_pr20 i10_pr21 i10_pr22 i10_pr23 i10_pr24 i10_pr25 prday16 prday17 prday18
## 1 <NA> <NA> <NA> <NA> <NA> <NA> NA NA NA
## 2 <NA> <NA> <NA> <NA> <NA> <NA> NA NA NA
## 3 <NA> <NA> <NA> <NA> <NA> <NA> NA NA NA
## 4 <NA> <NA> <NA> <NA> <NA> <NA> NA NA NA
## 5 <NA> <NA> <NA> <NA> <NA> <NA> NA NA NA
## 6 <NA> <NA> <NA> <NA> <NA> <NA> NA NA NA
## prday19 prday20 prday21 prday22 prday23 prday24 prday25 i10_birth
## 1 NA NA NA NA NA NA NA NA
## 2 NA NA NA NA NA NA NA NA
## 3 NA NA NA NA NA NA NA NA
## 4 NA NA NA NA NA NA NA NA
## 5 NA NA NA NA NA NA NA NA
## 6 NA NA NA NA NA NA NA NA
## i10_delivery i10_injury i10_multinjury i10_serviceline pclass_orproc
## 1 NA NA NA NA NA
## 2 NA NA NA NA NA
## 3 NA NA NA NA NA
## 4 NA NA NA NA NA
## 5 NA NA NA NA NA
## 6 NA NA NA NA NACheck the summary of allYears
summary(allYears)## X.1 X age age_neonate
## Min. : 12 Min. : 12 Min. :-99.00 Min. :-9.000
## 1st Qu.:1789937 1st Qu.:1789937 1st Qu.: 44.00 1st Qu.:-9.000
## Median :3564736 Median :3564736 Median : 57.00 Median :-9.000
## Mean :3564778 Mean :3564778 Mean : 55.45 Mean :-8.886
## 3rd Qu.:5330628 3rd Qu.:5330628 3rd Qu.: 69.00 3rd Qu.:-9.000
## Max. :7159031 Max. :7159031 Max. : 90.00 Max. : 1.000
##
## amonth aweekend died discwt
## Min. :-9.00 Min. :-9.0000 Min. :-9.00000 Min. :4.992
## 1st Qu.: 4.00 1st Qu.: 0.0000 1st Qu.: 0.00000 1st Qu.:5.000
## Median : 7.00 Median : 0.0000 Median : 0.00000 Median :5.000
## Mean : 6.52 Mean : 0.1708 Mean : 0.01212 Mean :5.000
## 3rd Qu.: 9.00 3rd Qu.: 0.0000 3rd Qu.: 0.00000 3rd Qu.:5.000
## Max. :12.00 Max. : 1.0000 Max. : 1.00000 Max. :5.004
##
## dispuniform dqtr drg drgver
## Min. :-9.000 Min. :-9.000 Min. : 1.0 Min. :33.00
## 1st Qu.: 1.000 1st Qu.: 2.000 1st Qu.:464.0 1st Qu.:34.00
## Median : 5.000 Median : 3.000 Median :580.0 Median :35.00
## Mean : 3.822 Mean : 2.513 Mean :601.3 Mean :34.78
## 3rd Qu.: 6.000 3rd Qu.: 3.000 3rd Qu.:853.0 3rd Qu.:36.00
## Max. :99.000 Max. : 4.000 Max. :999.0 Max. :37.00
##
## drg_nopoa dxver elective female
## Min. : 1.0 Min. :10 Min. :-9.0000 Min. :-9.0000
## 1st Qu.:464.0 1st Qu.:10 1st Qu.: 0.0000 1st Qu.: 0.0000
## Median :580.0 Median :10 Median : 0.0000 Median : 0.0000
## Mean :600.5 Mean :10 Mean : 0.2514 Mean : 0.4469
## 3rd Qu.:853.0 3rd Qu.:10 3rd Qu.: 1.0000 3rd Qu.: 1.0000
## Max. :999.0 Max. :10 Max. : 1.0000 Max. : 1.0000
## NA's :124164
## hcup_ed hcup_division hosp_nis i10_dx1
## Min. :0.0000 Min. :1.000 Min. :10001 Length:243422
## 1st Qu.:0.0000 1st Qu.:3.000 1st Qu.:30338 Class :character
## Median :1.0000 Median :5.000 Median :50328 Mode :character
## Mean :0.7636 Mean :5.078 Mean :51083
## 3rd Qu.:1.0000 3rd Qu.:7.000 3rd Qu.:70460
## Max. :4.0000 Max. :9.000 Max. :90536
##
## i10_dx2 i10_dx3 i10_dx4 i10_dx5
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx6 i10_dx7 i10_dx8 i10_dx9
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx10 i10_dx11 i10_dx12 i10_dx13
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx14 i10_dx15 i10_dx16 i10_dx17
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx18 i10_dx19 i10_dx20 i10_dx21
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx22 i10_dx23 i10_dx24 i10_dx25
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx26 i10_dx27 i10_dx28 i10_dx29
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx30 i10_ecause1 i10_ecause2 i10_ecause3
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_ecause4 i10_ndx i10_necause i10_npr
## Length:243422 Min. : 0.00 Min. :0.00 Min. : 1.000
## Class :character 1st Qu.:10.00 1st Qu.:0.00 1st Qu.: 2.000
## Mode :character Median :15.00 Median :0.00 Median : 3.000
## Mean :15.64 Mean :0.55 Mean : 4.802
## 3rd Qu.:21.00 3rd Qu.:1.00 3rd Qu.: 6.000
## Max. :40.00 Max. :4.00 Max. :25.000
## NA's :184739
## i10_pr1 i10_pr2 i10_pr3 i10_pr4
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_pr5 i10_pr6 i10_pr7 i10_pr8
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_pr9 i10_pr10 i10_pr11 i10_pr12
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_pr13 i10_pr14 i10_pr15 key_nis
## Length:243422 Length:243422 Length:243422 Min. :10000016
## Class :character Class :character Class :character 1st Qu.:30477956
## Mode :character Mode :character Mode :character Median :50695430
## Mean :51258557
## 3rd Qu.:70486873
## Max. :90983758
##
## los mdc mdc_nopoa nis_stratum
## Min. :-6666.000 Min. : 0.0 Min. : 0.00 Min. :1111
## 1st Qu.: 4.000 1st Qu.: 8.0 1st Qu.: 8.00 1st Qu.:3232
## Median : 6.000 Median : 9.0 Median : 9.00 Median :5232
## Mean : 9.131 Mean :11.6 Mean :11.64 Mean :5307
## 3rd Qu.: 12.000 3rd Qu.:18.0 3rd Qu.:18.00 3rd Qu.:7233
## Max. : 359.000 Max. :25.0 Max. :25.00 Max. :9333
##
## pay1 pl_nchs prday1 prday2
## Min. :-9.000 Min. :-99.000 Min. :-99.0000 Min. :-99.00
## 1st Qu.: 1.000 1st Qu.: 1.000 1st Qu.: 0.0000 1st Qu.: 0.00
## Median : 2.000 Median : 2.000 Median : 1.0000 Median : 1.00
## Mean : 2.082 Mean : 1.927 Mean : 0.1057 Mean :-16.77
## 3rd Qu.: 3.000 3rd Qu.: 4.000 3rd Qu.: 3.0000 3rd Qu.: 3.00
## Max. : 6.000 Max. : 6.000 Max. :343.0000 Max. :319.00
##
## prday3 prday4 prday5 prday6
## Min. :-99.00 Min. :-99.00 Min. :-99.00 Min. :-99.00
## 1st Qu.:-99.00 1st Qu.:-99.00 1st Qu.:-99.00 1st Qu.:-99.00
## Median : 0.00 Median :-99.00 Median :-99.00 Median :-99.00
## Mean :-35.66 Mean :-50.31 Mean :-61.18 Mean :-69.17
## 3rd Qu.: 2.00 3rd Qu.: 1.00 3rd Qu.: 0.00 3rd Qu.: 0.00
## Max. :337.00 Max. :342.00 Max. :366.00 Max. :312.00
##
## prday7 prday8 prday9 prday10
## Min. :-99.00 Min. :-99.00 Min. :-99.0 Min. :-99.00
## 1st Qu.:-99.00 1st Qu.:-99.00 1st Qu.:-99.0 1st Qu.:-99.00
## Median :-99.00 Median :-99.00 Median :-99.0 Median :-99.00
## Mean :-77.54 Mean :-81.52 Mean :-84.5 Mean :-86.98
## 3rd Qu.:-99.00 3rd Qu.:-99.00 3rd Qu.:-99.0 3rd Qu.:-99.00
## Max. :320.00 Max. :320.00 Max. :320.0 Max. :308.00
##
## prday11 prday12 prday13 prday14
## Min. :-99.00 Min. :-99.00 Min. :-99.00 Min. :-99.00
## 1st Qu.:-99.00 1st Qu.:-99.00 1st Qu.:-99.00 1st Qu.:-99.00
## Median :-99.00 Median :-99.00 Median :-99.00 Median :-99.00
## Mean :-88.99 Mean :-90.56 Mean :-92.02 Mean :-93.13
## 3rd Qu.:-99.00 3rd Qu.:-99.00 3rd Qu.:-99.00 3rd Qu.:-99.00
## Max. :355.00 Max. :361.00 Max. :335.00 Max. :302.00
##
## prday15 prver race totchg
## Min. :-99.0 Min. :10 Min. :-9.000 Min. :-999999999
## 1st Qu.:-99.0 1st Qu.:10 1st Qu.: 1.000 1st Qu.: 34591
## Median :-99.0 Median :10 Median : 1.000 Median : 65211
## Mean :-94.1 Mean :10 Mean : 1.317 Mean : -6491144
## 3rd Qu.:-99.0 3rd Qu.:10 3rd Qu.: 2.000 3rd Qu.: 131770
## Max. :343.0 Max. :10 Max. : 6.000 Max. : 9999999
## NA's :124164
## tran_in tran_out year zipinc_qrtl
## Min. :-9.0000 Min. :-9.0000 Min. :2016 Min. :-9.000
## 1st Qu.: 0.0000 1st Qu.: 0.0000 1st Qu.:2017 1st Qu.: 1.000
## Median : 0.0000 Median : 0.0000 Median :2018 Median : 2.000
## Mean : 0.1062 Mean : 0.5584 Mean :2018 Mean : 2.015
## 3rd Qu.: 0.0000 3rd Qu.: 2.0000 3rd Qu.:2019 3rd Qu.: 3.000
## Max. : 2.0000 Max. : 2.0000 Max. :2019 Max. : 4.000
##
## flap i10_dx31 i10_dx32 i10_dx33
## Mode:logical Length:243422 Length:243422 Length:243422
## TRUE:243422 Class :character Class :character Class :character
## Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx34 i10_dx35 i10_dx36 i10_dx37
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx38 i10_dx39 i10_dx40 i10_pr16
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_pr17 i10_pr18 i10_pr19 i10_pr20
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_pr21 i10_pr22 i10_pr23 i10_pr24
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_pr25 prday16 prday17 prday18
## Length:243422 Min. :-99.00 Min. :-99.00 Min. :-99.00
## Class :character 1st Qu.:-99.00 1st Qu.:-99.00 1st Qu.:-99.00
## Mode :character Median :-99.00 Median :-99.00 Median :-99.00
## Mean :-94.67 Mean :-95.24 Mean :-95.68
## 3rd Qu.:-99.00 3rd Qu.:-99.00 3rd Qu.:-99.00
## Max. :321.00 Max. :302.00 Max. :313.00
## NA's :58683 NA's :58683 NA's :58683
## prday19 prday20 prday21 prday22
## Min. :-99.00 Min. :-99.00 Min. :-99.00 Min. :-99.00
## 1st Qu.:-99.00 1st Qu.:-99.00 1st Qu.:-99.00 1st Qu.:-99.00
## Median :-99.00 Median :-99.00 Median :-99.00 Median :-99.00
## Mean :-96.07 Mean :-96.43 Mean :-96.83 Mean :-97.28
## 3rd Qu.:-99.00 3rd Qu.:-99.00 3rd Qu.:-99.00 3rd Qu.:-99.00
## Max. :313.00 Max. :302.00 Max. :302.00 Max. :302.00
## NA's :58683 NA's :58683 NA's :58683 NA's :58683
## prday23 prday24 prday25 i10_birth
## Min. :-99.00 Min. :-99.00 Min. :-99.00 Min. :0
## 1st Qu.:-99.00 1st Qu.:-99.00 1st Qu.:-99.00 1st Qu.:0
## Median :-99.00 Median :-99.00 Median :-99.00 Median :0
## Mean :-97.48 Mean :-97.63 Mean :-97.79 Mean :0
## 3rd Qu.:-99.00 3rd Qu.:-99.00 3rd Qu.:-99.00 3rd Qu.:0
## Max. :302.00 Max. :305.00 Max. :305.00 Max. :2
## NA's :58683 NA's :58683 NA's :58683 NA's :180732
## i10_delivery i10_injury i10_multinjury i10_serviceline
## Min. :0.00 Min. :0.00 Min. :0.0 Min. :1.00
## 1st Qu.:0.00 1st Qu.:0.00 1st Qu.:0.0 1st Qu.:4.00
## Median :0.00 Median :0.00 Median :0.0 Median :4.00
## Mean :0.02 Mean :0.26 Mean :0.1 Mean :3.85
## 3rd Qu.:0.00 3rd Qu.:0.00 3rd Qu.:0.0 3rd Qu.:4.00
## Max. :1.00 Max. :2.00 Max. :1.0 Max. :5.00
## NA's :180732 NA's :180732 NA's :180732 NA's :180732
## pclass_orproc
## Min. :0.00
## 1st Qu.:1.00
## Median :1.00
## Mean :0.93
## 3rd Qu.:1.00
## Max. :1.00
## NA's :180732We can see some variables contain negative values. Is it possible to be negative years old? Why do categorical variables have a -9 value? These negative values are actually NA’s.
To not skew our data, let’s replace these negative values with NA
allYears[allYears < 0] <- NACheck the summary once again
summary(allYears)## X.1 X age age_neonate
## Min. : 12 Min. : 12 Min. : 0.00 Min. :0.00
## 1st Qu.:1789937 1st Qu.:1789937 1st Qu.:44.00 1st Qu.:0.00
## Median :3564736 Median :3564736 Median :57.00 Median :0.00
## Mean :3564778 Mean :3564778 Mean :55.46 Mean :0.22
## 3rd Qu.:5330628 3rd Qu.:5330628 3rd Qu.:69.00 3rd Qu.:0.00
## Max. :7159031 Max. :7159031 Max. :90.00 Max. :1.00
## NA's :10 NA's :240401
## amonth aweekend died discwt
## Min. : 1.000 Min. :0.0000 Min. :0.00000 Min. :4.992
## 1st Qu.: 4.000 1st Qu.:0.0000 1st Qu.:0.00000 1st Qu.:5.000
## Median : 7.000 Median :0.0000 Median :0.00000 Median :5.000
## Mean : 6.535 Mean :0.1709 Mean :0.01695 Mean :5.000
## 3rd Qu.: 9.000 3rd Qu.:0.0000 3rd Qu.:0.00000 3rd Qu.:5.000
## Max. :12.000 Max. :1.0000 Max. :1.00000 Max. :5.004
## NA's :234 NA's :1 NA's :138
## dispuniform dqtr drg drgver
## Min. : 1.000 Min. :1.000 Min. : 1.0 Min. :33.00
## 1st Qu.: 1.000 1st Qu.:2.000 1st Qu.:464.0 1st Qu.:34.00
## Median : 5.000 Median :3.000 Median :580.0 Median :35.00
## Mean : 3.829 Mean :2.524 Mean :601.3 Mean :34.78
## 3rd Qu.: 6.000 3rd Qu.:3.000 3rd Qu.:853.0 3rd Qu.:36.00
## Max. :99.000 Max. :4.000 Max. :999.0 Max. :37.00
## NA's :138 NA's :234
## drg_nopoa dxver elective female
## Min. : 1.0 Min. :10 Min. :0.000 Min. :0.000
## 1st Qu.:464.0 1st Qu.:10 1st Qu.:0.000 1st Qu.:0.000
## Median :580.0 Median :10 Median :0.000 Median :0.000
## Mean :600.5 Mean :10 Mean :0.275 Mean :0.453
## 3rd Qu.:853.0 3rd Qu.:10 3rd Qu.:1.000 3rd Qu.:1.000
## Max. :999.0 Max. :10 Max. :1.000 Max. :1.000
## NA's :124164 NA's :618 NA's :209
## hcup_ed hcup_division hosp_nis i10_dx1
## Min. :0.0000 Min. :1.000 Min. :10001 Length:243422
## 1st Qu.:0.0000 1st Qu.:3.000 1st Qu.:30338 Class :character
## Median :1.0000 Median :5.000 Median :50328 Mode :character
## Mean :0.7636 Mean :5.078 Mean :51083
## 3rd Qu.:1.0000 3rd Qu.:7.000 3rd Qu.:70460
## Max. :4.0000 Max. :9.000 Max. :90536
##
## i10_dx2 i10_dx3 i10_dx4 i10_dx5
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx6 i10_dx7 i10_dx8 i10_dx9
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx10 i10_dx11 i10_dx12 i10_dx13
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx14 i10_dx15 i10_dx16 i10_dx17
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx18 i10_dx19 i10_dx20 i10_dx21
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx22 i10_dx23 i10_dx24 i10_dx25
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx26 i10_dx27 i10_dx28 i10_dx29
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx30 i10_ecause1 i10_ecause2 i10_ecause3
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_ecause4 i10_ndx i10_necause i10_npr
## Length:243422 Min. : 0.00 Min. :0.00 Min. : 1.000
## Class :character 1st Qu.:10.00 1st Qu.:0.00 1st Qu.: 2.000
## Mode :character Median :15.00 Median :0.00 Median : 3.000
## Mean :15.64 Mean :0.55 Mean : 4.802
## 3rd Qu.:21.00 3rd Qu.:1.00 3rd Qu.: 6.000
## Max. :40.00 Max. :4.00 Max. :25.000
## NA's :184739
## i10_pr1 i10_pr2 i10_pr3 i10_pr4
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_pr5 i10_pr6 i10_pr7 i10_pr8
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_pr9 i10_pr10 i10_pr11 i10_pr12
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_pr13 i10_pr14 i10_pr15 key_nis
## Length:243422 Length:243422 Length:243422 Min. :10000016
## Class :character Class :character Class :character 1st Qu.:30477956
## Mode :character Mode :character Mode :character Median :50695430
## Mean :51258557
## 3rd Qu.:70486873
## Max. :90983758
##
## los mdc mdc_nopoa nis_stratum pay1
## Min. : 0.0 Min. : 0.0 Min. : 0.00 Min. :1111 Min. :1.000
## 1st Qu.: 4.0 1st Qu.: 8.0 1st Qu.: 8.00 1st Qu.:3232 1st Qu.:1.000
## Median : 6.0 Median : 9.0 Median : 9.00 Median :5232 Median :2.000
## Mean : 10.2 Mean :11.6 Mean :11.64 Mean :5307 Mean :2.099
## 3rd Qu.: 12.0 3rd Qu.:18.0 3rd Qu.:18.00 3rd Qu.:7233 3rd Qu.:3.000
## Max. :359.0 Max. :25.0 Max. :25.00 Max. :9333 Max. :6.000
## NA's :39 NA's :371
## pl_nchs prday1 prday2 prday3
## Min. :1.000 Min. : 0.000 Min. : 0.00 Min. : 0.0
## 1st Qu.:1.000 1st Qu.: 0.000 1st Qu.: 0.00 1st Qu.: 0.0
## Median :2.000 Median : 1.000 Median : 1.00 Median : 2.0
## Mean :2.658 Mean : 2.488 Mean : 3.27 Mean : 3.7
## 3rd Qu.:4.000 3rd Qu.: 3.000 3rd Qu.: 4.00 3rd Qu.: 5.0
## Max. :6.000 Max. :343.000 Max. :319.00 Max. :337.0
## NA's :1750 NA's :10854 NA's :51495 NA's :95937
## prday4 prday5 prday6 prday7
## Min. : 0.00 Min. : 0.0 Min. : 0.00 Min. : 0.00
## 1st Qu.: 0.00 1st Qu.: 0.0 1st Qu.: 0.00 1st Qu.: 0.00
## Median : 2.00 Median : 2.0 Median : 3.00 Median : 3.00
## Mean : 4.26 Mean : 4.9 Mean : 5.57 Mean : 6.28
## 3rd Qu.: 6.00 3rd Qu.: 6.0 3rd Qu.: 7.00 3rd Qu.: 8.00
## Max. :342.00 Max. :366.0 Max. :312.00 Max. :320.00
## NA's :130436 NA's :156008 NA's :174829 NA's :194344
## prday8 prday9 prday10 prday11
## Min. : 0.00 Min. : 0.00 Min. : 0.00 Min. : 0.00
## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.: 1.00 1st Qu.: 1.00
## Median : 3.00 Median : 4.00 Median : 4.00 Median : 5.00
## Mean : 6.94 Mean : 7.64 Mean : 8.32 Mean : 9.09
## 3rd Qu.: 9.00 3rd Qu.: 10.00 3rd Qu.: 11.00 3rd Qu.: 12.00
## Max. :320.00 Max. :320.00 Max. :308.00 Max. :355.00
## NA's :203667 NA's :210658 NA's :216382 NA's :221034
## prday12 prday13 prday14 prday15
## Min. : 0.00 Min. : 0.00 Min. : 0.00 Min. : 0.00
## 1st Qu.: 1.00 1st Qu.: 1.00 1st Qu.: 1.00 1st Qu.: 1.00
## Median : 5.00 Median : 6.00 Median : 6.00 Median : 7.00
## Mean : 9.79 Mean : 10.69 Mean : 11.31 Mean : 12.22
## 3rd Qu.: 13.00 3rd Qu.: 14.00 3rd Qu.: 15.00 3rd Qu.: 16.00
## Max. :361.00 Max. :335.00 Max. :302.00 Max. :343.00
## NA's :224670 NA's :228051 NA's :230544 NA's :232772
## prver race totchg tran_in
## Min. :10 Min. :1.000 Min. : 109 Min. :0.0000
## 1st Qu.:10 1st Qu.:1.000 1st Qu.: 35061 1st Qu.:0.0000
## Median :10 Median :1.000 Median : 65754 Median :0.0000
## Mean :10 Mean :1.654 Mean : 126465 Mean :0.1409
## 3rd Qu.:10 3rd Qu.:2.000 3rd Qu.: 132548 3rd Qu.:0.0000
## Max. :10 Max. :6.000 Max. :9999999 Max. :2.0000
## NA's :124164 NA's :7704 NA's :1619 NA's :925
## tran_out year zipinc_qrtl flap
## Min. :0.0000 Min. :2016 Min. :1.000 Mode:logical
## 1st Qu.:0.0000 1st Qu.:2017 1st Qu.:1.000 TRUE:243422
## Median :0.0000 Median :2018 Median :2.000
## Mean :0.5638 Mean :2018 Mean :2.251
## 3rd Qu.:2.0000 3rd Qu.:2019 3rd Qu.:3.000
## Max. :2.0000 Max. :2019 Max. :4.000
## NA's :138 NA's :5121
## i10_dx31 i10_dx32 i10_dx33 i10_dx34
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx35 i10_dx36 i10_dx37 i10_dx38
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_dx39 i10_dx40 i10_pr16 i10_pr17
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_pr18 i10_pr19 i10_pr20 i10_pr21
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## i10_pr22 i10_pr23 i10_pr24 i10_pr25
## Length:243422 Length:243422 Length:243422 Length:243422
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## prday16 prday17 prday18 prday19
## Min. : 0.00 Min. : 0.00 Min. : 0.00 Min. : 0.00
## 1st Qu.: 1.00 1st Qu.: 2.00 1st Qu.: 2.00 1st Qu.: 2.00
## Median : 7.00 Median : 8.00 Median : 8.00 Median : 9.00
## Mean : 12.89 Mean : 13.95 Mean : 14.58 Mean : 15.12
## 3rd Qu.: 17.00 3rd Qu.: 18.00 3rd Qu.: 19.00 3rd Qu.: 20.00
## Max. :321.00 Max. :302.00 Max. :313.00 Max. :313.00
## NA's :236308 NA's :237301 NA's :238055 NA's :238700
## prday20 prday21 prday22 prday23
## Min. : 0.00 Min. : 0.00 Min. : 0.00 Min. : 0.00
## 1st Qu.: 2.00 1st Qu.: 3.00 1st Qu.: 3.00 1st Qu.: 3.00
## Median : 9.00 Median : 10.00 Median : 10.00 Median : 11.00
## Mean : 15.63 Mean : 16.23 Mean : 17.24 Mean : 17.33
## 3rd Qu.: 21.00 3rd Qu.: 22.00 3rd Qu.: 22.00 3rd Qu.: 22.50
## Max. :302.00 Max. :302.00 Max. :302.00 Max. :302.00
## NA's :239293 NA's :239967 NA's :240707 NA's :241023
## prday24 prday25 i10_birth i10_delivery
## Min. : 0.00 Min. : 0.00 Min. :0 Min. :0.00
## 1st Qu.: 3.00 1st Qu.: 3.00 1st Qu.:0 1st Qu.:0.00
## Median : 11.00 Median : 12.00 Median :0 Median :0.00
## Mean : 18.51 Mean : 19.24 Mean :0 Mean :0.02
## 3rd Qu.: 24.00 3rd Qu.: 24.00 3rd Qu.:0 3rd Qu.:0.00
## Max. :305.00 Max. :305.00 Max. :2 Max. :1.00
## NA's :241279 NA's :241549 NA's :180732 NA's :180732
## i10_injury i10_multinjury i10_serviceline pclass_orproc
## Min. :0.00 Min. :0.0 Min. :1.00 Min. :0.00
## 1st Qu.:0.00 1st Qu.:0.0 1st Qu.:4.00 1st Qu.:1.00
## Median :0.00 Median :0.0 Median :4.00 Median :1.00
## Mean :0.26 Mean :0.1 Mean :3.85 Mean :0.93
## 3rd Qu.:0.00 3rd Qu.:0.0 3rd Qu.:4.00 3rd Qu.:1.00
## Max. :2.00 Max. :1.0 Max. :5.00 Max. :1.00
## NA's :180732 NA's :180732 NA's :180732 NA's :180732Summary looks good.
Take the combined dataset and select the procedure columns
procedures <- allYears %>%
select(year, contains("i10_pr"))Lengthen the procedures column
procLong <- pivot_longer(procedures, cols = -c(year))
# Remove white space from the codes
procLong$value <- stri_trim_both(procLong$value)
head(procLong)## # A tibble: 6 × 3
## year name value
## <int> <chr> <chr>
## 1 2016 i10_pr1 0JBQ0ZZ
## 2 2016 i10_pr2 02HV33Z
## 3 2016 i10_pr3 B546ZZA
## 4 2016 i10_pr4 <NA>
## 5 2016 i10_pr5 <NA>
## 6 2016 i10_pr6 <NA>Create new columns for categorical variables
for(i in 1:length(month.name)) {
allYears$month[allYears$amonth == i] <- month.name[i]
}
# Reorder the months in consecutive order
allYears$month <- factor(allYears$month, levels = month.name)allYears$day[allYears$aweekend == 0] <- "Mon-Fri"
allYears$day[allYears$aweekend == 1] <- "Sat-Sun"allYears$status[allYears$died == 0] <- "Did not die"
allYears$status[allYears$died == 1] <- "Died"dispList <- c("Routine", "Transfer to short-term hospital", "Transfer Other", "Home Health Care", "Against medical advice", "Died in hospital", "Discharged/transferred to court/law enforcement", "Discharged alive, destination unknown")
allYears$disposition[allYears$dispuniform == 1] <- dispList[1]
allYears$disposition[allYears$dispuniform == 2] <- dispList[2]
allYears$disposition[allYears$dispuniform == 5] <- dispList[3]
allYears$disposition[allYears$dispuniform == 6] <- dispList[4]
allYears$disposition[allYears$dispuniform == 7] <- dispList[5]
allYears$disposition[allYears$dispuniform == 20] <- dispList[6]
allYears$disposition[allYears$dispuniform == 21] <- dispList[7]
allYears$disposition[allYears$dispuniform == 99] <- dispList[8]
# Reorder disposition
allYears$disposition <- factor(allYears$disposition, levels = dispList)qtrList <- c("1st: Jan - Mar", "2nd: Apr - Jun", "3rd: Jul - Sep", "4th: Oct - Dec")
for(i in 1:length(qtrList)) {
allYears$disQtr[allYears$dqtr == i] <- qtrList[i]
}
# Reorder disQtr
allYears$disQtr <- factor(allYears$disQtr, levels = qtrList)allYears$electiveStr[allYears$elective == 0] <- "Non-elective"
allYears$electiveStr[allYears$elective == 1] <- "Elective"allYears$sex[allYears$female == 0] <- "Male"
allYears$sex[allYears$female == 1] <- "Female"divList <- c("New England", "Middle Atlantic", "East North Central", "West North Central", "South Atlantic", "East South Central", "West South Central", "Mountain", "Pacific")
for (i in 1:length(divList)) {
allYears$division[allYears$hcup_division == i] <- divList[i]
}
# Reorder division
allYears$division <- factor(allYears$division, levels = divList)payList <- c("Medicare", "Medicaid", "Private insurance",
"Self-pay", "No charge", "Other")
for (i in 1:length(payList)) {
allYears$payer[allYears$pay1 == i] <- payList[i]
}
# Reorder payer
allYears$payer <- factor(allYears$payer, levels = payList)raceList <- c("White", "Black", "Hispanic", "Asian or Pacific Islander", "Native American", "Other")
for (i in 1:length(raceList)) {
allYears$raceStr[allYears$race == i] <- raceList[i]
}
# Reorder raceStr
allYears$raceStr <- factor(allYears$raceStr, levels = raceList)incomeList <- c("0-25th percentile", "26th to 50th percentile (median)", "51st to 75th percentile", "76th to 100th percentile")
for(i in 1:length(incomeList)) {
allYears$income[allYears$zipinc_qrtl == i] <- incomeList[i]
}Take the combined dataset, group by the year, then count the number of surgeries
annualIncidence <- allYears %>%
group_by(year) %>%
summarize(count = n())Plot the annual incidence as a line chart
annualIncidencePlot <- annualIncidence %>%
ggplot(aes(x = year, y = count)) +
ggtitle("Annual Flaps Incidence") +
theme_minimal(base_size = 12) +
geom_line() +
xlab("Year") +
ylab("Annual Incidence") +
ylim(0, 70000)
annualIncidencePlot
There was a steady increase of flaps surgeries from 2016 - 2019. This is most likely correlated to the population increase in the U.S.
Take the combined dataset, group by the year, then calculate the average annual charge
annualCharge <- allYears %>%
filter(totchg > 0) %>%
group_by(year) %>%
summarize(avgCharge = round(mean(totchg)))annualChargePlot <- annualCharge %>%
ggplot(aes(x = year, y = avgCharge)) +
ggtitle("Mean Annual Total Charges of Procedures") +
theme_minimal(base_size = 12) +
geom_line() +
scale_y_continuous(labels = scales::dollar_format(scale = 0.001, suffix = "K")) +
xlab("Year") +
ylab("Mean Annual Charge") +
expand_limits(y = 0)
annualChargePlot
There was a steady increase in the average cost of flaps surgeries from 2016 - 2019. From 2018-2019, there was a sharper increase in cost compared to the previous years. This is most likely as a result of the raising inflation rate and sharper inflation from 2018-2019.
myChart <- highchart() %>%
hc_plotOptions (
series = list (animation = FALSE)
)%>%
hc_yAxis_multiples(
list(title = list(text = "Annual Incidence")),
list(title = list(text = "Average Cost ($)"),
opposite = TRUE)
) %>%
hc_add_series(data = annualIncidence$count,
name = "Annual Incidence",
type = "column",
yAxis = 0) %>%
hc_add_series(data = annualCharge$avgCharge,
name = "Average Cost ($)",
type = "line",
yAxis = 1) %>%
hc_xAxis(categories = annualIncidence$year) %>%
hc_colors(c("black", "blue")) %>%
hc_title(text = "Annual Incidence Vs Mean Annual Charge of Flaps Procedures")
myChartBox plot: Race and age
plot1 <- allYears %>%
filter(raceStr != "NA") %>%
ggplot(aes(x = raceStr, y = age, group = raceStr, fill = raceStr)) +
geom_boxplot() +
ggtitle("Median Age Among all Races \nis between 50-60 Years") +
xlab("Race") +
ylab("Age") +
scale_y_continuous(breaks = seq(0,100, by=10)) +
scale_fill_discrete(name = "Race") +
theme(axis.text.x = element_text(angle = 25))
plot1## Warning: Removed 10 rows containing non-finite values (`stat_boxplot()`).
The median age of patients throughout the racial groups lies between 50 and 60 years old with White patients on the higher end and Native Americans on the lower end.
Frequency Table: Race and sex
sexVrace <- table(allYears$raceStr, allYears$sex) %>%
prop.table(margin = 1) %>%
as.data.frame() %>%
arrange(Var1)
tab1 <- flextable(sexVrace)
tab1 <- set_header_labels(tab1, Var1 = "Race", Var2 = "Sex", Freq = "Obs.(%)")
tab1Race | Sex | Obs.(%) |
|---|---|---|
White | Female | 0.4520737 |
White | Male | 0.5479263 |
Black | Female | 0.4756832 |
Black | Male | 0.5243168 |
Hispanic | Female | 0.4217613 |
Hispanic | Male | 0.5782387 |
Asian or Pacific Islander | Female | 0.5109738 |
Asian or Pacific Islander | Male | 0.4890262 |
Native American | Female | 0.4504754 |
Native American | Male | 0.5495246 |
Other | Female | 0.4391323 |
Other | Male | 0.5608677 |
With the exception of Asian/Pacific Islander, over 50% of patients in each racial group were male.
Bar Chart: ICD-10 Codes
byValue <- procLong %>%
na.omit() %>%
group_by(value) %>%
summarize(count = n()) %>%
arrange(desc(count)) %>%
head(10) %>%
ggplot(aes(x = value, y = count, fill = value)) +
geom_bar(stat = 'identity') +
labs(title = "Top 10 Flap Procedure ICD-10 Codes") +
xlab("ICD-10 Code") +
ylab("Number of procedures") +
theme_classic() +
scale_fill_discrete(name = "ICD-10 Code") +
theme(axis.text.x = element_text(face = "bold",
size = 7, angle = 10))
byValue
Most of the associated procedures contained the prefix “0JB” which are classified as tissue and fascia excision
lmFit1 <- glm(count ~ year, data = annualIncidence)
summary(lmFit1)##
## Call:
## glm(formula = count ~ year, data = annualIncidence)
##
## Deviance Residuals:
## 1 2 3 4
## -234.5 365.5 -27.5 -103.5
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -2545754.5 285352.6 -8.921 0.0123 *
## year 1292.0 141.4 9.135 0.0118 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 100024.5)
##
## Null deviance: 8546369 on 3 degrees of freedom
## Residual deviance: 200049 on 2 degrees of freedom
## AIC: 60.632
##
## Number of Fisher Scoring iterations: 2Count is the response variable and year is predictor variable We are 95% confident that the actual slope lies within (1016, 1568) Annual incidence is increasing at a rate of 1,292 surgeries Formula: y = 1292x - 2545754
summary(annualIncidence$count - lmFit1$fitted.values)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -234.50 -136.25 -65.50 0.00 70.75 365.50Distribution is slightly right-skewed
lmFit2 <- glm(avgCharge ~ year, data = annualCharge)
summary(lmFit2)##
## Call:
## glm(formula = avgCharge ~ year, data = annualCharge)
##
## Deviance Residuals:
## 1 2 3 4
## 319.3 93.1 -1144.1 731.7
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.352e+07 8.920e+05 -15.16 0.00432 **
## year 6.765e+03 4.422e+02 15.30 0.00424 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 977484.9)
##
## Null deviance: 230794625 on 3 degrees of freedom
## Residual deviance: 1954970 on 2 degrees of freedom
## AIC: 69.75
##
## Number of Fisher Scoring iterations: 2Average charge is the response variable and year is the predictor variable We are 95% confident that the actual slope lies within ($5702, $7764) Mean annual charge is increasing at a rate of $6733 Formula: y = 6733x - 13457644
summary(annualCharge$avgCharge - lmFit2$fitted.values)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -1144.1 -216.2 206.2 0.0 422.4 731.7Distribution is slightly right-skewed
What predictor variables are statistically significant when evaluating a patient’s chance of survival?
dieGLM <- glm(died ~ year + female + race + age + i10_ndx + i10_npr + hcup_division + zipinc_qrtl, data = allYears, family = binomial)
summary(dieGLM)##
## Call:
## glm(formula = died ~ year + female + race + age + i10_ndx + i10_npr +
## hcup_division + zipinc_qrtl, family = binomial, data = allYears)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.5662 -0.1792 -0.1146 -0.0716 3.9819
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 318.581210 31.456657 10.128 < 2e-16 ***
## year -0.162416 0.015597 -10.413 < 2e-16 ***
## female 0.079968 0.033817 2.365 0.018042 *
## race 0.054079 0.014871 3.637 0.000276 ***
## age 0.035191 0.001187 29.638 < 2e-16 ***
## i10_ndx 0.100403 0.002547 39.416 < 2e-16 ***
## i10_npr 0.118859 0.002646 44.916 < 2e-16 ***
## hcup_division 0.010918 0.007062 1.546 0.122101
## zipinc_qrtl -0.062091 0.015344 -4.047 5.2e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 39437 on 230459 degrees of freedom
## Residual deviance: 32261 on 230451 degrees of freedom
## (12962 observations deleted due to missingness)
## AIC: 32279
##
## Number of Fisher Scoring iterations: 8Died is the response variable and year, sex, race, age, length of stay, number of diagnoses, number of procedures, hospital division and household income are the response variables. At an alpha level of 0.05, hospital division is not statistically significant and sex is only slightly significant. All other variables are statistically significant.
What is the best model for patient survival? Sex?
die1 <- glm(died ~ female, data = allYears, family = binomial)
summary(die1)##
## Call:
## glm(formula = died ~ female, family = binomial, data = allYears)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.1862 -0.1862 -0.1840 -0.1840 2.8592
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.07062 0.02135 -190.649 <2e-16 ***
## female 0.02452 0.03152 0.778 0.437
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 41801 on 243074 degrees of freedom
## Residual deviance: 41800 on 243073 degrees of freedom
## (347 observations deleted due to missingness)
## AIC: 41804
##
## Number of Fisher Scoring iterations: 7AIC: 41804
Race?
die2 <- glm(died ~ race, data = allYears, family = binomial)
summary(die2)##
## Call:
## glm(formula = died ~ race, family = binomial, data = allYears)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.1853 -0.1843 -0.1841 -0.1841 2.8588
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.071921 0.028164 -144.580 <2e-16 ***
## race 0.002614 0.013979 0.187 0.852
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 40253 on 235584 degrees of freedom
## Residual deviance: 40253 on 235583 degrees of freedom
## (7837 observations deleted due to missingness)
## AIC: 40257
##
## Number of Fisher Scoring iterations: 7AIC: 40257
Age?
die3 <- glm(died ~ age, data = allYears, family = binomial)
summary(die3)##
## Call:
## glm(formula = died ~ age, family = binomial, data = allYears)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.3090 -0.2100 -0.1729 -0.1325 3.5306
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -6.230444 0.067723 -92.00 <2e-16 ***
## age 0.035692 0.001005 35.53 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 41808 on 243273 degrees of freedom
## Residual deviance: 40381 on 243272 degrees of freedom
## (148 observations deleted due to missingness)
## AIC: 40385
##
## Number of Fisher Scoring iterations: 7AIC: 40385
Hospital Division?
die4 <- glm(died ~ hcup_division, data = allYears, family = binomial)
summary(die4)##
## Call:
## glm(formula = died ~ hcup_division, family = binomial, data = allYears)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.1896 -0.1873 -0.1850 -0.1827 2.8727
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -3.997194 0.036134 -110.621 <2e-16 ***
## hcup_division -0.012515 0.006498 -1.926 0.0541 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 41808 on 243283 degrees of freedom
## Residual deviance: 41804 on 243282 degrees of freedom
## (138 observations deleted due to missingness)
## AIC: 41808
##
## Number of Fisher Scoring iterations: 7AIC: 41808
Household Income?
die5 <- glm(died ~ zipinc_qrtl, data = allYears, family = binomial)
summary(die5)##
## Call:
## glm(formula = died ~ zipinc_qrtl, family = binomial, data = allYears)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -0.1881 -0.1881 -0.1855 -0.1829 2.8729
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -3.99761 0.03589 -111.394 <2e-16 ***
## zipinc_qrtl -0.02820 0.01451 -1.944 0.0519 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 40919 on 238169 degrees of freedom
## Residual deviance: 40915 on 238168 degrees of freedom
## (5252 observations deleted due to missingness)
## AIC: 40919
##
## Number of Fisher Scoring iterations: 7AIC: 40919
Of the 5 models, race has the lowest AIC and hospital division has the highest AIC. Race is the best predictor variable to model a patient’s likelihood of survival and hospital division is least efficient predictor variable.
mostExpensive <- allYears %>%
select(X, year, i10_ndx, i10_npr, i10_pr1, totchg) %>%
na.omit() %>%
filter((totchg > 900000) & (i10_npr == 1)) %>%
group_by(i10_pr1) %>%
summarize(count = n(),
chgSum = sum(totchg),
avgChg = chgSum/count,
diagSum = sum(i10_ndx),
avgDiag = round(diagSum / count))
mostExpensive## # A tibble: 6 × 6
## i10_pr1 count chgSum avgChg diagSum avgDiag
## <chr> <int> <int> <dbl> <int> <dbl>
## 1 0HB6XZZ 1 920753 920753 18 18
## 2 0HBBXZZ 1 946020 946020 33 33
## 3 0HBNXZZ 1 929004 929004 8 8
## 4 0JB70ZZ 3 5387347 1795782. 68 23
## 5 0JB80ZZ 2 2538870 1269435 61 30
## 6 0JBL0ZZ 1 1227665 1227665 32 32myExpensiveChart <- highchart() %>%
hc_yAxis_multiples(
list(title = list(text = "Average Number of Diagnoses")),
list(title = list(text = "Average Cost of Procedure ($)"),
opposite = TRUE)
) %>%
hc_add_series(data = mostExpensive$avgDiag,
name = "Average Number of Diagnoses",
type = "column",
yAxis = 0) %>%
hc_add_series(data = mostExpensive$avgChg,
name = "Average Cost of Procedure ($)",
type = "line",
yAxis = 1) %>%
hc_xAxis(categories = mostExpensive$i10_pr1) %>%
hc_colors(c("red", "green")) %>%
hc_chart(style = list(fontFamily = "Georgia",
fontWeight = "bold")) %>%
hc_title(text = "Most Expensive Procedures & Their Associated Average Number of Diagnoses")
myExpensiveChartThe codes with the prefix “0JB”, tissue and fascia excision, tend to be among the most expensive procedural codes. Codes with the prefix “0HB”, Skin Excision, come in second.
With medicine growing faster than the average person can understand, it’s important for data scientists to gather medical data and present it in a way that the average person, especially policy makers, can understand. Over the years, the popularity of flap surgeries continues to grow and along with it, their cost. At a time when inflation is skyrocketing and people can hardly afford basic groceries, our quest to put patient care above profits should never end. To improve patient care throughout the nation, we must first understand who our patients are. Through analysis, we have found that a majority of flap sugery patients are within the 40 to 70 age bracket, with a majority of male patients across most racial groups. We’ve also discovered that skin and fascia incision are among the most common primary procedure and are also among the most expensive. In examining patient’s survival, we discovered that race plays a big role and hospital division does not. While it is good news that a hospital’s division does not affect a patient’s survival, it is quite concerning that a patient’s household income is statistically significant in predicting a patient’s survival. Ideally, economic status should never impact a patient’s care, especially their ability to live.