#### Analisis COMPARATIVO : NUMERO DIAS VAC 17-02-2021
### Proyecto: CARDIOVAC
### Investigadores: Dra. Chaparro - Dr. Cruz
## Analistas: Yaset Caicedo - Akemi Arango


library(readxl)
library(dplyr)
## Warning: replacing previous import 'vctrs::data_frame' by 'tibble::data_frame'
## when loading 'dplyr'
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(janitor)
## 
## Attaching package: 'janitor'
## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test
library(skimr)
library(ggplot2)


### Lectura de Base de Datos
cardiovac <- read_excel("DATA/CARDIOVAC_2020-05-06_registros_1-120.xlsx")
cardiovac <- cardiovac %>%
  filter(edad >= 1)
### 120 datos
#### Variable de Division
cardiovac %>%
  tabyl(diasvac)
##  diasvac  n     percent
##        1 39 0.325000000
##        2 43 0.358333333
##        3 29 0.241666667
##        4  4 0.033333333
##        5  4 0.033333333
##       23  1 0.008333333
cardiovac <- cardiovac %>%
  mutate(npv3 = ifelse(diasvac >= 3,1,0))

cardiovac %>%
  tabyl(npv3)
##  npv3  n   percent
##     0 82 0.6833333
##     1 38 0.3166667
cardiovac$npv3 <- as.factor(cardiovac$npv3)
levels(cardiovac$npv3) <- c("Menor 48 h", "Mayor 48h")


### DESCRIPCION DE LOS DATOS

# Edad
cardiovac %>%
  group_by(npv3) %>%
  skim(edad)
Data summary
Name Piped data
Number of rows 120
Number of columns 43
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
edad Menor 48 h 0 1 58.99 13.78 21 51.00 61.0 69.00 80 ▂▂▅▇▆
edad Mayor 48h 0 1 62.37 10.06 37 58.25 63.5 68.75 82 ▃▂▇▇▂
with(data = cardiovac, t.test(edad ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  edad by npv3
## t = -1.5149, df = 96.128, p-value = 0.1331
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -7.810121  1.048889
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 58.98780                 62.36842
#Genero
cardiovac %>%
  tabyl(sexo, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##             npv3                      
##  sexo Menor 48 h  Mayor 48h      Total
##     0 26 (31.7%) 11 (28.9%) 37 (30.8%)
##     1 56 (68.3%) 27 (71.1%) 83 (69.2%)
cardiovac %>%
  tabyl(sexo, npv3) %>%
  chisq.test()
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  .
## X-squared = 0.0084772, df = 1, p-value = 0.9266
## IMC
cardiovac %>%
  tabyl(imc, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##            npv3                      
##  imc Menor 48 h  Mayor 48h      Total
##    0  5  (6.1%)  2  (5.3%)  7  (5.8%)
##    1 35 (42.7%) 13 (34.2%) 48 (40.0%)
##    2 29 (35.4%) 13 (34.2%) 42 (35.0%)
##    3  9 (11.0%)  7 (18.4%) 16 (13.3%)
##    4  2  (2.4%)  0  (0.0%)  2  (1.7%)
##   SD  2  (2.4%)  3  (7.9%)  5  (4.2%)
cardiovac %>%
  tabyl(imc, npv3) %>%
  chisq.test()
## Warning in stats::chisq.test(., ...): Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  .
## X-squared = 4.3682, df = 5, p-value = 0.4977
## Clase Funcional
cardiovac %>%
  tabyl(nyha, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##             npv3                      
##  nyha Menor 48 h  Mayor 48h      Total
##     1 32 (39.0%) 14 (36.8%) 46 (38.3%)
##     2 16 (19.5%)  4 (10.5%) 20 (16.7%)
##     3 24 (29.3%) 17 (44.7%) 41 (34.2%)
##     4  7  (8.5%)  3  (7.9%) 10  (8.3%)
##    SD  3  (3.7%)  0  (0.0%)  3  (2.5%)
cardiovac %>%
  tabyl(nyha, npv3) %>%
  chisq.test()
## Warning in stats::chisq.test(., ...): Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  .
## X-squared = 4.5119, df = 4, p-value = 0.3411
################# Tipo de Cx Cardiovascular


###  Tipo de Cirugia por Frecuencia Original
cardiovac %>%
  tabyl(tipocx, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##               npv3                     
##  tipocx Menor 48 h Mayor 48h      Total
##       0  2  (2.4%) 5 (13.2%)  7  (5.8%)
##       1  3  (3.7%) 0  (0.0%)  3  (2.5%)
##       2  1  (1.2%) 1  (2.6%)  2  (1.7%)
##       3  4  (4.9%) 7 (18.4%) 11  (9.2%)
##       4  8  (9.8%) 6 (15.8%) 14 (11.7%)
##       5 15 (18.3%) 6 (15.8%) 21 (17.5%)
##       6 36 (43.9%) 9 (23.7%) 45 (37.5%)
##       7  3  (3.7%) 2  (5.3%)  5  (4.2%)
##       8 10 (12.2%) 2  (5.3%) 12 (10.0%)
cardiovac %>%
  tabyl(tipocx, npv3) %>%
  chisq.test()
## Warning in stats::chisq.test(., ...): Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  .
## X-squared = 17.153, df = 8, p-value = 0.02856
## Tipos de Cirugia
cardiovac <- cardiovac %>%
  mutate(tipocx_2 = case_when(
    tipocx == 0 ~ "Trasplante",
    tipocx == 4 | tipocx == 5 | tipocx == 6 ~ "Cx Aorta Ascendente",
    tipocx == 1 ~ " Cx Valvular Aortica",
    tipocx == 2 ~ "Cx Valvular Mitral",
    tipocx == 7 ~ "Revascularizacion",
    tipocx == 3 | tipocx == 8 ~ "Combinadas"))

cardiovac %>%
  tabyl(tipocx_2, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##                             npv3                      
##              tipocx_2 Menor 48 h  Mayor 48h      Total
##   Cx Valvular Aortica  3  (3.7%)  0  (0.0%)  3  (2.5%)
##            Combinadas 14 (17.1%)  9 (23.7%) 23 (19.2%)
##   Cx Aorta Ascendente 59 (72.0%) 21 (55.3%) 80 (66.7%)
##    Cx Valvular Mitral  1  (1.2%)  1  (2.6%)  2  (1.7%)
##     Revascularizacion  3  (3.7%)  2  (5.3%)  5  (4.2%)
##            Trasplante  2  (2.4%)  5 (13.2%)  7  (5.8%)
cardiovac %>%
  tabyl(tipocx_2, npv3) %>%
  chisq.test()
## Warning in stats::chisq.test(., ...): Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  .
## X-squared = 8.6526, df = 5, p-value = 0.1237
#### Antecedentes
## ERC
cardiovac %>%
  tabyl(anterc, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##               npv3                       
##  anterc Menor 48 h  Mayor 48h       Total
##       0 80 (97.6%) 32 (84.2%) 112 (93.3%)
##       1  2  (2.4%)  6 (15.8%)   8  (6.7%)
cardiovac %>%
  tabyl(anterc, npv3) %>%
  fisher.test()
## 
##  Fisher's Exact Test for Count Data
## 
## data:  .
## p-value = 0.0122
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##   1.233798 78.178670
## sample estimates:
## odds ratio 
##   7.358211
## Enf Hepatica
cardiovac %>%
  tabyl(anthepatopatia, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##                       npv3                       
##  anthepatopatia Menor 48 h  Mayor 48h       Total
##               0 81 (98.8%) 36 (94.7%) 117 (97.5%)
##               1  1  (1.2%)  2  (5.3%)   3  (2.5%)
cardiovac %>%
  tabyl(anthepatopatia, npv3) %>%
  fisher.test()
## 
##  Fisher's Exact Test for Count Data
## 
## data:  .
## p-value = 0.2353
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##    0.2243481 268.2066110
## sample estimates:
## odds ratio 
##   4.437473
## ICC
cardiovac %>%
  tabyl(anticc, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##               npv3                      
##  anticc Menor 48 h  Mayor 48h      Total
##       0 57 (69.5%) 27 (71.1%) 84 (70.0%)
##       1 25 (30.5%) 11 (28.9%) 36 (30.0%)
cardiovac %>%
  tabyl(anticc, npv3) %>%
  chisq.test()
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  .
## X-squared = 2.7679e-31, df = 1, p-value = 1
## DM2
cardiovac %>%
  tabyl(antdm, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##              npv3                       
##  antdm Menor 48 h  Mayor 48h       Total
##      0 76 (92.7%) 32 (84.2%) 108 (90.0%)
##      1  6  (7.3%)  6 (15.8%)  12 (10.0%)
cardiovac %>%
  tabyl(antdm, npv3) %>%
  fisher.test()
## 
##  Fisher's Exact Test for Count Data
## 
## data:  .
## p-value = 0.1923
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.5820933 9.5591548
## sample estimates:
## odds ratio 
##   2.356126
## HTP
cardiovac %>%
  tabyl(anthtp, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##               npv3                       
##  anthtp Menor 48 h  Mayor 48h       Total
##       0 72 (87.8%) 32 (84.2%) 104 (86.7%)
##       1 10 (12.2%)  6 (15.8%)  16 (13.3%)
cardiovac %>%
  tabyl(anthtp, npv3) %>%
  fisher.test()
## 
##  Fisher's Exact Test for Count Data
## 
## data:  .
## p-value = 0.5766
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.3689762 4.5141589
## sample estimates:
## odds ratio 
##   1.346542
## Coagulopatia
cardiovac %>%
  tabyl(antcoagulopatia, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##                        npv3                       
##  antcoagulopatia Menor 48 h  Mayor 48h       Total
##                0 81 (98.8%) 35 (92.1%) 116 (96.7%)
##                1  1  (1.2%)  3  (7.9%)   4  (3.3%)
cardiovac %>%
  tabyl(antcoagulopatia, npv3) %>%
  fisher.test()
## 
##  Fisher's Exact Test for Count Data
## 
## data:  .
## p-value = 0.0932
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##    0.5270379 368.0328964
## sample estimates:
## odds ratio 
##    6.82063
##### Medicamentos Pre-QX

## ACO
cardiovac %>%
  tabyl(anticoagpreqx, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##                      npv3                      
##  anticoagpreqx Menor 48 h  Mayor 48h      Total
##              0 62 (75.6%) 26 (68.4%) 88 (73.3%)
##              1 15 (18.3%)  5 (13.2%) 20 (16.7%)
##              2  4  (4.9%)  6 (15.8%) 10  (8.3%)
##              4  1  (1.2%)  0  (0.0%)  1  (0.8%)
##              5  0  (0.0%)  1  (2.6%)  1  (0.8%)
cardiovac %>%
  tabyl(anticoagpreqx, npv3) %>%
  chisq.test()
## Warning in stats::chisq.test(., ...): Chi-squared approximation may be incorrect
## 
##  Pearson's Chi-squared test
## 
## data:  .
## X-squared = 6.925, df = 4, p-value = 0.1399
## Antiagregante
cardiovac %>%
  tabyl(antiagregpreqx, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##                       npv3                      
##  antiagregpreqx Menor 48 h  Mayor 48h      Total
##               0 58 (70.7%) 28 (73.7%) 86 (71.7%)
##               1 19 (23.2%)  9 (23.7%) 28 (23.3%)
##               2  4  (4.9%)  1  (2.6%)  5  (4.2%)
##               3  1  (1.2%)  0  (0.0%)  1  (0.8%)
cardiovac %>%
  tabyl(antiagregpreqx, npv3) %>%
  fisher.test()
## 
##  Fisher's Exact Test for Count Data
## 
## data:  .
## p-value = 1
## alternative hypothesis: two.sided
#### CONDICION PREVIA

## FEVI Pre-QX
cardiovac %>%
  group_by(npv3) %>%
  skim(fevipreqx)
Data summary
Name Piped data
Number of rows 120
Number of columns 44
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
fevipreqx Menor 48 h 0 1 53.46 12.24 5 49.00 58.0 60 75 ▁▁▂▇▂
fevipreqx Mayor 48h 0 1 50.03 16.64 5 41.25 58.5 60 73 ▁▂▂▃▇
with(data = cardiovac, wilcox.test(fevipreqx ~ npv3))
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  fevipreqx by npv3
## W = 1640, p-value = 0.64
## alternative hypothesis: true location shift is not equal to 0
cardiovac <- cardiovac %>%
  mutate(fevi40 = ifelse(fevipreqx <= 40,1,0))

cardiovac %>%
  tabyl(fevi40, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##               npv3                      
##  fevi40 Menor 48 h  Mayor 48h      Total
##       0 71 (86.6%) 28 (73.7%) 99 (82.5%)
##       1 11 (13.4%) 10 (26.3%) 21 (17.5%)
cardiovac %>%
  tabyl(fevi40, npv3) %>%
  chisq.test()
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  .
## X-squared = 2.1666, df = 1, p-value = 0.141
## Creatinina Pre-Qx
cardiovac %>%
  group_by(npv3) %>%
  skim(crepreqx)
Data summary
Name Piped data
Number of rows 120
Number of columns 45
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
crepreqx Menor 48 h 0 1 0.95 0.24 0.51 0.78 0.92 1.10 1.89 ▅▇▃▁▁
crepreqx Mayor 48h 0 1 1.19 0.94 0.55 0.81 1.00 1.28 6.35 ▇▁▁▁▁
with(data = cardiovac, t.test(crepreqx ~ npv3) )
## 
##  Welch Two Sample t-test
## 
## data:  crepreqx by npv3
## t = -1.5744, df = 39.358, p-value = 0.1234
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.55433919  0.06899901
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                0.9454878                1.1881579
## Endocarditis
cardiovac %>%
  tabyl(endocarditispreqx, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##                          npv3                       
##  endocarditispreqx Menor 48 h  Mayor 48h       Total
##                  0 77 (93.9%) 35 (92.1%) 112 (93.3%)
##                  1  5  (6.1%)  3  (7.9%)   8  (6.7%)
cardiovac %>%
  tabyl(endocarditispreqx, npv3) %>%
  fisher.test()
## 
##  Fisher's Exact Test for Count Data
## 
## data:  .
## p-value = 0.707
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##  0.1937414 7.2100913
## sample estimates:
## odds ratio 
##    1.31687
####MANEJO QUIRURGICO
## Hipotermia
cardiovac %>%
  tabyl(tempintraop, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##                    npv3                      
##  tempintraop Menor 48 h  Mayor 48h      Total
##            0  3  (3.7%)  1  (2.6%)  4  (3.3%)
##            1 51 (62.2%) 21 (55.3%) 72 (60.0%)
##            2  2  (2.4%)  2  (5.3%)  4  (3.3%)
##            3 26 (31.7%) 14 (36.8%) 40 (33.3%)
cardiovac %>%
  tabyl(tempintraop, npv3) %>%
  fisher.test()
## 
##  Fisher's Exact Test for Count Data
## 
## data:  .
## p-value = 0.7715
## alternative hypothesis: two.sided
## Hipotermia Profunda - Arresto Cardiaco
cardiovac %>%
  tabyl(hipotermiaprof, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##                       npv3                      
##  hipotermiaprof Menor 48 h  Mayor 48h      Total
##               0 68 (82.9%) 27 (71.1%) 95 (79.2%)
##               1 14 (17.1%) 11 (28.9%) 25 (20.8%)
cardiovac %>%
  tabyl(hipotermiaprof, npv3) %>%
  chisq.test()
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  .
## X-squared = 1.5583, df = 1, p-value = 0.2119
### Tiempo de Isquemia
cardiovac %>%
  group_by(npv3) %>%
  skim(tisquemia)
Data summary
Name Piped data
Number of rows 120
Number of columns 45
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
tisquemia Menor 48 h 0 1 97.09 34.65 21 77.25 95.5 113.75 233 ▂▇▅▁▁
tisquemia Mayor 48h 0 1 103.82 40.94 33 82.25 101.5 122.75 201 ▃▆▇▂▂
with(data = cardiovac, t.test(tisquemia ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  tisquemia by npv3
## t = -0.87813, df = 62.504, p-value = 0.3832
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -22.049132   8.588285
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 97.08537                103.81579
### Tiempo Circulacion Extracorporea
cardiovac %>%
  group_by(npv3) %>%
  skim(tcextracorporea)
Data summary
Name Piped data
Number of rows 120
Number of columns 45
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
tcextracorporea Menor 48 h 0 1 135.98 42.52 52 110.25 126.5 162.00 235 ▃▇▆▅▂
tcextracorporea Mayor 48h 0 1 157.26 60.60 60 121.75 144.5 185.25 328 ▃▇▃▂▁
with(data = cardiovac, t.test(tcextracorporea ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  tcextracorporea by npv3
## t = -1.954, df = 54.509, p-value = 0.05584
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -43.1250681   0.5499718
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 135.9756                 157.2632
### Recibio Transfusiones durante Cirugia

cardiovac %>%
  tabyl(transfusionintraop, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##                           npv3                       
##  transfusionintraop Menor 48 h  Mayor 48h       Total
##                   0  4  (4.9%)  1  (2.6%)   5  (4.2%)
##                   1 78 (95.1%) 37 (97.4%) 115 (95.8%)
cardiovac %>%
  tabyl(transfusionintraop, npv3) %>%
  fisher.test()
## 
##  Fisher's Exact Test for Count Data
## 
## data:  .
## p-value = 1
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##   0.1786088 95.8903773
## sample estimates:
## odds ratio 
##   1.888548
### Numero de Globulos Rojos Transfundidos IntraQX
cardiovac %>%
  filter(grintraop >= 1) %>%
  group_by(npv3) %>%
  skim(grintraop)
Data summary
Name Piped data
Number of rows 93
Number of columns 45
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
grintraop Menor 48 h 0 1 3.41 2.18 1 2 3 4.00 10 ▇▅▂▁▁
grintraop Mayor 48h 0 1 4.44 2.54 1 3 4 5.75 12 ▇▇▃▁▁
with(data = cardiovac[cardiovac$grintraop >=1,], t.test(grintraop ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  grintraop by npv3
## t = -1.9906, df = 60.851, p-value = 0.05102
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -2.073508125  0.004714506
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 3.406780                 4.441176
## Plasma Congelado Intraqx
cardiovac %>%
  filter(pfcintraop >= 1) %>%
  group_by(npv3) %>%
  skim(pfcintraop)
Data summary
Name Piped data
Number of rows 96
Number of columns 45
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
pfcintraop Menor 48 h 0 1 6.02 2.65 1 4 6.0 6.75 14 ▂▇▂▁▁
pfcintraop Mayor 48h 0 1 7.65 3.55 2 6 6.5 10.00 15 ▃▇▂▃▃
with(data = cardiovac[cardiovac$pfcintraop >=1,], t.test(pfcintraop ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  pfcintraop by npv3
## t = -2.3456, df = 53.486, p-value = 0.02274
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -3.0252490 -0.2366106
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 6.016129                 7.647059
## Plaquetas Congelado Intraqx
cardiovac %>%
  filter(pltintraop >= 1) %>%
  group_by(npv3) %>%
  skim(pltintraop)
Data summary
Name Piped data
Number of rows 103
Number of columns 45
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
pltintraop Menor 48 h 0 1 1.40 0.71 1 1 1 2 4 ▇▂▁▁▁
pltintraop Mayor 48h 0 1 1.91 1.10 1 1 2 2 5 ▇▇▁▂▁
with(data = cardiovac[cardiovac$pltintraop >=1,], t.test(pltintraop ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  pltintraop by npv3
## t = -2.4304, df = 45.003, p-value = 0.01913
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.93098838 -0.08719344
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 1.400000                 1.909091
## Crioprecipitado Congelado Intraqx
cardiovac %>%
  filter(criointraop >= 1) %>%
  group_by(npv3) %>%
  skim(criointraop)
Data summary
Name Piped data
Number of rows 103
Number of columns 45
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
criointraop Menor 48 h 0 1 10.48 4.20 4 8 10 12.00 25 ▇▇▃▂▁
criointraop Mayor 48h 0 1 10.94 5.77 3 8 10 11.75 30 ▆▇▂▁▁
with(data = cardiovac[cardiovac$criointraop >=1,], t.test(criointraop ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  criointraop by npv3
## t = -0.41633, df = 50.806, p-value = 0.6789
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -2.695337  1.769506
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 10.47826                 10.94118
#######################################
##### Post-QX


####### Sangrado en las primeras 12 h
cardiovac %>%
  group_by(npv3) %>%
    skim(sangrado12h)
Data summary
Name Piped data
Number of rows 120
Number of columns 45
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
sangrado12h Menor 48 h 0 1 668.28 393.77 100 400 525.0 872.5 2110 ▇▅▂▁▁
sangrado12h Mayor 48h 0 1 879.08 379.00 300 600 832.5 1175.0 1850 ▇▇▆▅▁
with(data = cardiovac, t.test(sangrado12h ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  sangrado12h by npv3
## t = -2.7992, df = 74.734, p-value = 0.006514
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -360.82461  -60.77231
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 668.2805                 879.0789
####### Sangrado en  12 h a 24 h
cardiovac %>%
  group_by(npv3) %>%
  skim(sangrado24h)
Data summary
Name Piped data
Number of rows 120
Number of columns 45
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
sangrado24h Menor 48 h 0 1 243.10 153.45 0 150.0 200 300.0 954 ▅▇▁▁▁
sangrado24h Mayor 48h 0 1 260.13 159.20 0 142.5 225 327.5 610 ▇▇▇▂▅
with(data = cardiovac, t.test(sangrado24h ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  sangrado24h by npv3
## t = -0.55146, df = 69.81, p-value = 0.5831
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -78.64252  44.57448
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 243.0976                 260.1316
#### Sangrado Total

cardiovac <- cardiovac %>%
  mutate(sangradototal = sangrado12h + sangrado24h) 
cardiovac %>%
  group_by(npv3) %>%
  skim(sangradototal)
Data summary
Name Piped data
Number of rows 120
Number of columns 46
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
sangradototal Menor 48 h 0 1 911.38 461.44 320 600 800 1092.5 2810 ▇▅▂▁▁
sangradototal Mayor 48h 0 1 1139.21 481.13 370 800 1050 1442.5 2260 ▅▇▆▃▂
with(data = cardiovac, t.test(sangradototal ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  sangradototal by npv3
## t = -2.4442, df = 69.498, p-value = 0.01706
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -413.76169  -41.90326
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                  911.378                 1139.211
### Requirio Transfusiion Post-operatoria
cardiovac %>%
  tabyl(transfpop, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##                  npv3                      
##  transfpop Menor 48 h  Mayor 48h      Total
##          0 47 (57.3%) 11 (28.9%) 58 (48.3%)
##          1 35 (42.7%) 27 (71.1%) 62 (51.7%)
cardiovac %>%
  tabyl(transfpop, npv3) %>%
  chisq.test()
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  .
## X-squared = 7.2714, df = 1, p-value = 0.007006
### Transfusiones Postoperatorias
## Globulos Rojos
cardiovac %>%
  filter(grpop >= 1) %>%
  group_by(npv3) %>%
  skim(grpop)
Data summary
Name Piped data
Number of rows 56
Number of columns 46
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
grpop Menor 48 h 0 1 2.90 2.45 1 1 2 4 13 ▇▂▁▁▁
grpop Mayor 48h 0 1 3.16 1.93 1 2 2 4 9 ▇▅▁▁▁
with(data = cardiovac[cardiovac$grpop >=1,], t.test(grpop ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  grpop by npv3
## t = -0.43828, df = 53.976, p-value = 0.6629
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -1.4313869  0.9178385
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 2.903226                 3.160000
### Plasma Fresco Congelado
cardiovac %>%
  filter(pfcpop >= 1) %>%
  group_by(npv3) %>%
  skim(pfcpop)
Data summary
Name Piped data
Number of rows 27
Number of columns 46
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
pfcpop Menor 48 h 0 1 4.82 3.71 1 2.5 4 5 14 ▆▇▁▂▂
pfcpop Mayor 48h 0 1 5.50 3.71 1 2.5 5 8 12 ▇▅▃▆▃
with(data = cardiovac[cardiovac$pfcpop >=1,], t.test(pfcpop ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  pfcpop by npv3
## t = -0.46943, df = 21.637, p-value = 0.6435
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -3.696917  2.333281
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 4.818182                 5.500000
### Plaquetas
cardiovac %>%
  filter(pltpop >= 1) %>%
  group_by(npv3) %>%
  skim(pltpop)
Data summary
Name Piped data
Number of rows 29
Number of columns 46
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
pltpop Menor 48 h 0 1 1.56 0.81 1 1 1 2 4 ▇▅▁▁▁
pltpop Mayor 48h 0 1 2.15 1.41 1 1 2 3 6 ▇▂▁▁▁
with(data = cardiovac[cardiovac$pltpop >=1,], t.test(pltpop ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  pltpop by npv3
## t = -1.3451, df = 18.344, p-value = 0.195
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -1.5137462  0.3310539
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 1.562500                 2.153846
## Crioprecipitado

cardiovac %>%
  filter(criopop >= 1) %>%
  group_by(npv3) %>%
  skim(criopop)
Data summary
Name Piped data
Number of rows 17
Number of columns 46
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
criopop Menor 48 h 0 1 7.71 2.21 6 6.00 6 9.5 11 ▇▁▂▂▂
criopop Mayor 48h 0 1 8.10 4.20 3 5.25 8 10.0 16 ▇▅▇▂▂
with(data = cardiovac[cardiovac$criopop >=1,], t.test(criopop ~ npv3))
## 
##  Welch Two Sample t-test
## 
## data:  criopop by npv3
## t = -0.24561, df = 14.205, p-value = 0.8095
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -3.749386  2.977957
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 7.714286                 8.100000
###############
#### RESULTADOS CLINICOS######

### Infeccion del Sitio Operatorio
cardiovac %>%
  tabyl(iso, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##            npv3                       
##  iso Menor 48 h  Mayor 48h       Total
##    0 77 (93.9%) 33 (86.8%) 110 (91.7%)
##    1  5  (6.1%)  5 (13.2%)  10  (8.3%)
cardiovac %>%
  tabyl(iso, npv3) %>%
  fisher.test()
## 
##  Fisher's Exact Test for Count Data
## 
## data:  .
## p-value = 0.2851
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##   0.496922 10.805172
## sample estimates:
## odds ratio 
##    2.31519
### Mediastinitis Postoperatoria
cardiovac %>%
  tabyl(mediastinitis, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##                      npv3                       
##  mediastinitis Menor 48 h  Mayor 48h       Total
##              0 77 (93.9%) 33 (86.8%) 110 (91.7%)
##              1  5  (6.1%)  5 (13.2%)  10  (8.3%)
cardiovac %>%
  tabyl(mediastinitis, npv3) %>%
  fisher.test()
## 
##  Fisher's Exact Test for Count Data
## 
## data:  .
## p-value = 0.2851
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##   0.496922 10.805172
## sample estimates:
## odds ratio 
##    2.31519
### AKI-Postoperatoria
cardiovac %>%
  tabyl(akipop, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##               npv3                      
##  akipop Menor 48 h  Mayor 48h      Total
##       0 66 (80.5%) 15 (39.5%) 81 (67.5%)
##       1 16 (19.5%) 23 (60.5%) 39 (32.5%)
cardiovac %>%
  tabyl(akipop, npv3) %>%
  fisher.test()
## 
##  Fisher's Exact Test for Count Data
## 
## data:  .
## p-value = 1.718e-05
## alternative hypothesis: true odds ratio is not equal to 1
## 95 percent confidence interval:
##   2.493921 16.142097
## sample estimates:
## odds ratio 
##   6.207924
#### Estancia en UCI
cardiovac %>%
  group_by(npv3) %>%
  skim(diasuci)
Data summary
Name Piped data
Number of rows 120
Number of columns 46
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
diasuci Menor 48 h 0 1 9.99 10.20 1 6.00 8 10.75 74 ▇▁▁▁▁
diasuci Mayor 48h 0 1 11.21 6.43 3 6.25 10 14.50 28 ▇▅▂▁▁
with(data = cardiovac, wilcox.test(diasuci ~ npv3 ))
## 
##  Wilcoxon rank sum test with continuity correction
## 
## data:  diasuci by npv3
## W = 1263, p-value = 0.09569
## alternative hypothesis: true location shift is not equal to 0
#### Tiempo de Intubacion
cardiovac %>%
  group_by(npv3) %>%
  skim(tintubacion)
Data summary
Name Piped data
Number of rows 120
Number of columns 46
_______________________
Column type frequency:
numeric 1
________________________
Group variables npv3

Variable type: numeric

skim_variable npv3 n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
tintubacion Menor 48 h 0 1 3.95 2.84 1 2 3 5.00 21 ▇▂▁▁▁
tintubacion Mayor 48h 0 1 5.76 2.79 2 4 5 6.75 15 ▇▆▂▁▁
with(data = cardiovac, t.test(tintubacion ~ npv3 ))
## 
##  Welch Two Sample t-test
## 
## data:  tintubacion by npv3
## t = -3.2869, df = 73.265, p-value = 0.001557
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -2.9105336 -0.7133432
## sample estimates:
## mean in group Menor 48 h  mean in group Mayor 48h 
##                 3.951220                 5.763158
### Necesidad de Reintervención
cardiovac %>%
  tabyl(reintervencion, npv3)  %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##                       npv3                      
##  reintervencion Menor 48 h  Mayor 48h      Total
##               0 66 (80.5%) 29 (76.3%) 95 (79.2%)
##               1 16 (19.5%)  9 (23.7%) 25 (20.8%)
cardiovac %>%
  tabyl(reintervencion, npv3)  %>%
  chisq.test()
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  .
## X-squared = 0.079454, df = 1, p-value = 0.778
### Mortalidad
cardiovac %>%
  tabyl(mortalidadintrahospitalaria, npv3) %>%
  adorn_totals(c("col")) %>%
  adorn_percentages(denominator = "col") %>%
  adorn_pct_formatting() %>%
  adorn_ns(position = "front") %>%
  adorn_title() 
##                                    npv3                       
##  mortalidadintrahospitalaria Menor 48 h  Mayor 48h       Total
##                            0 72 (87.8%) 28 (73.7%) 100 (83.3%)
##                            1 10 (12.2%) 10 (26.3%)  20 (16.7%)
cardiovac %>%
  tabyl(mortalidadintrahospitalaria, npv3) %>%
  chisq.test()
## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  .
## X-squared = 2.7805, df = 1, p-value = 0.09542