Analísis Dra Amanda

Objetivos

library(readxl)
dbdraamanda <- read_excel("C:/Users/fidel/OneDrive - CINVESTAV/PROYECTO MDatos/TRABAJOS/Dra. Amanda Azócar/dbdraamanda.xlsx",sheet=1)

  str(dbdraamanda)
## tibble [45 × 11] (S3: tbl_df/tbl/data.frame)
##  $ EXPEDIENTE            : chr [1:45] "225106" "223140" "225341" "142234" ...
##  $ DIAGNÓSTICO ONCOLÓGICO: chr [1:45] "CA. DE MAMA IZQUIERDO" "CARCINOMA EPIDERMOIDE IV B" "LINFOMA DIFUSO DE CEULAS GRANDES B" "LINFOMA DIFUSO DE CEULAS GRANDES B + CA DE ENDOMETRIO" ...
##  $ DIAGNÓSTICO ALGOLÓGICO: chr [1:45] "SX. DOLOROSO NOCICEPTIVO SOMATICO CON COMPOENTE NEUROPATICO EN MPD SEC A SINDROME MEDULAR INCOMPLETO" "SX. DOLOROSO NOCICEPTIVO VISCERAL EN HEMIABDOMEN INFERIOR PB SEC A AT" "SX. DOLOROSO NOCICEPTIVO SOMATICO EN MIEMBRO PELVICO IZQUIERDO OB SEC A AT" "DOLOR ABDOMINAL AGUDO DE ORIGEN A DETERMINAR + NEUROPATIA SENSITIVA PERIFERICA + SINDROME DOLOROSO NEUROPATICO "| __truncated__ ...
##  $ EDAD                  : num [1:45] 66 52 76 56 51 36 41 48 50 51 ...
##  $ SEXO                  : chr [1:45] "F" "F" "F" "F" ...
##  $ ENAB                  : num [1:45] 5 6 5 3 6 4 10 5 7 5 ...
##  $ ENA A LOS 5 MIN       : num [1:45] 2 3 1 0 6 1 4 0 3 1 ...
##  $ ENA A LOS 10 MIN      : num [1:45] 2 2 1 0 6 1 2 0 2 1 ...
##  $ EFECTOS ADVERSOS      : chr [1:45] "NO" "NO" "MAREO" "NO" ...
##  $ LIKERT                : num [1:45] NA 4 4 4 4 3 4 4 4 4 ...
##  $ MEDD DE MORFINA:      : logi [1:45] NA NA NA NA NA NA ...
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(stringr)
library(Hmisc)
## Loading required package: lattice
## Loading required package: survival
## Loading required package: Formula
## Loading required package: ggplot2
## 
## Attaching package: 'Hmisc'
## The following objects are masked from 'package:dplyr':
## 
##     src, summarize
## The following objects are masked from 'package:base':
## 
##     format.pval, units
library(funModeling)
## funModeling v.1.9.4 :)
## Examples and tutorials at livebook.datascienceheroes.com
##  / Now in Spanish: librovivodecienciadedatos.ai
library(tidyverse)
## ── Attaching packages
## ───────────────────────────────────────
## tidyverse 1.3.2 ──
## ✔ tibble  3.1.7     ✔ purrr   0.3.4
## ✔ tidyr   1.2.0     ✔ forcats 0.5.1
## ✔ readr   2.1.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter()    masks stats::filter()
## ✖ dplyr::lag()       masks stats::lag()
## ✖ Hmisc::src()       masks dplyr::src()
## ✖ Hmisc::summarize() masks dplyr::summarize()
library(gtsummary)

glimpse(dbdraamanda)
## Rows: 45
## Columns: 11
## $ EXPEDIENTE               <chr> "225106", "223140", "225341", "142234", "2216…
## $ `DIAGNÓSTICO ONCOLÓGICO` <chr> "CA. DE MAMA IZQUIERDO", "CARCINOMA EPIDERMOI…
## $ `DIAGNÓSTICO ALGOLÓGICO` <chr> "SX. DOLOROSO NOCICEPTIVO SOMATICO CON COMPOE…
## $ EDAD                     <dbl> 66, 52, 76, 56, 51, 36, 41, 48, 50, 51, 47, 4…
## $ SEXO                     <chr> "F", "F", "F", "F", "F", "F", "F", "F", "F", …
## $ ENAB                     <dbl> 5, 6, 5, 3, 6, 4, 10, 5, 7, 5, 6, 6, 10, 7, 6…
## $ `ENA A LOS 5 MIN`        <dbl> 2, 3, 1, 0, 6, 1, 4, 0, 3, 1, 1, 1, 2, 2, 3, …
## $ `ENA A LOS 10 MIN`       <dbl> 2, 2, 1, 0, 6, 1, 2, 0, 2, 1, 1, 0, 2, 1, 1, …
## $ `EFECTOS ADVERSOS`       <chr> "NO", "NO", "MAREO", "NO", "NO", "NO", "NO", …
## $ LIKERT                   <dbl> NA, 4, 4, 4, 4, 3, 4, 4, 4, 4, 4, 3, 3, 3, 3,…
## $ `MEDD DE MORFINA:`       <lgl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
cancer <- dbdraamanda %>% mutate(dxca = case_when(str_detect(`DIAGNÓSTICO ONCOLÓGICO`,"\\MAMA") ~ "CA MAMA",str_detect(`DIAGNÓSTICO ONCOLÓGICO`,"\\CERVIX ") ~ "CA CERVIX",str_detect(`DIAGNÓSTICO ONCOLÓGICO`,"\\LINFOMA") ~ "LINFOMA", str_detect(`DIAGNÓSTICO ONCOLÓGICO`,"\\OVARIO") ~ "CA OVARIO", str_detect(`DIAGNÓSTICO ONCOLÓGICO`,"\\OVARIO ") ~ "CA OVARIO", str_detect(`DIAGNÓSTICO ONCOLÓGICO`,"\\ENDOMETRIO ") ~ "CA ENDOMETRIO",str_detect(`DIAGNÓSTICO ONCOLÓGICO`,"\\GERMINAL ") ~ "TUMOR GERMINAL"))

dbdraamanda$`ENA A LOS 5 MIN`= as.character(dbdraamanda$`ENA A LOS 5 MIN`)
dbdraamanda$`ENA A LOS 10 MIN`=as.character(dbdraamanda$`ENA A LOS 10 MIN`)
dbdraamanda$LIKERT = as.character(dbdraamanda$LIKERT )

dbdraamanda %>% select(`DIAGNÓSTICO ONCOLÓGICO`,`DIAGNÓSTICO ALGOLÓGICO`,EDAD,SEXO,ENAB,`ENA A LOS 5 MIN`,`ENA A LOS 10 MIN`,`EFECTOS ADVERSOS`,LIKERT) %>%  tbl_summary()
## Warning: The `fmt_missing()` function is deprecated and will soon be removed
## * Use the `sub_missing()` function instead
Characteristic N = 451
DIAGNÓSTICO ONCOLÓGICO
ADENOCARCINOMA DE ENDOMETRIO + ADENOCARCINOMA ENDOMETRIOIDE DE OVARIO 1 (2.2%)
ADENOCARCINOMA DE PULMON 1 (2.2%)
ADENOCARCINOMA DE PULMON EC IIIC 1 (2.2%)
CA. DE MAMA DERECHA + CA RENAL DERECHO 1 (2.2%)
CA. DE MAMA IZQUIERDO 1 (2.2%)
CANCER DE CERVIX EC IIIC 1 (2.2%)
CANCER DE CERVIX EN ESTUDIO 1 (2.2%)
CANCER DE CERVIX IIB 1 (2.2%)
CANCER DE ENDOMETRIO 1 (2.2%)
CANCER DE ENDOMETRIO EC IB G2 1 (2.2%)
CANCER DE ENDOMETRIO IVB 1 (2.2%)
CANCER DE ESOFAGO 1 (2.2%)
CANCER DE MAMA 1 (2.2%)
CANCER DE MAMA EC IV 1 (2.2%)
CANCER DE MAMA EN ESTUDIO 1 (2.2%)
CANCER DE MAMA IZQUIERDO EC IIA 1 (2.2%)
CANCER DE MAMA TRIPLE NEGATIVO 1 (2.2%)
CANCER DE OVARIO 1 (2.2%)
CANCER DE PROSTATA 1 (2.2%)
CANCER DE PROSTATA METASTASICO 1 (2.2%)
CANCER DE RECTO 1 (2.2%)
CANCER EPIDERMOIDE DE LENGUA 1 (2.2%)
CANCER UROTELIAL DE VEJIGA 1 (2.2%)
CANCINOMA EPIDERMOIDE DE CAVIDAD ORAL 1 (2.2%)
CARCINOMA DE OVARIO SEROSO 1 (2.2%)
CARCINOMA EPIDERMOIDE DE CERVIX 2 (4.4%)
CARCINOMA EPIDERMOIDE DE CERVIX EC IIIC2 1 (2.2%)
CARCINOMA EPIDERMOIDE DE PULMON IVB 1 (2.2%)
CARCINOMA EPIDERMOIDE IV B 1 (2.2%)
CONDROSARCOMA 1 (2.2%)
LINFOMA DIFUSO DE CEULAS GRANDES B 1 (2.2%)
LINFOMA DIFUSO DE CEULAS GRANDES B + CA DE ENDOMETRIO 1 (2.2%)
LINFOMA FOLICULAR GRADO 1 1 (2.2%)
LINFOMA FOLICULAR TRANSFORMADO A LBDCG 1 (2.2%)
LIPOSARCOMA BIEN DIFERENCIADO DE MUSLO DERECHO 1 (2.2%)
MIELOMA MULTIPLE 1 (2.2%)
OSTEOSARCOMA DE ALTO GRADO 1 (2.2%)
SARCOMA SINOVIAL METASTATICO 1 (2.2%)
TUMOR DE KRUKENBERG 1 (2.2%)
TUMOR GENITOURINARIO EN ESTUDIO 1 (2.2%)
TUMOR GERMINAL NO SEMINOMATOSO 1 (2.2%)
TUMOR GERMINAL SEMINOMATOSO 1 (2.2%)
TUMOR PELVICO EN ESTUDIO 2 (4.4%)
DIAGNÓSTICO ALGOLÓGICO
CEFALEA AGUDA EN ESTUDIO 1 (2.2%)
CEFALEA AGUDA EN ESTUDIO PB ECV ISQUEMICO 1 (2.2%)
CEFALEA EN ESTUDIO + SINDROME DOLOROSO NOCICEPTIVO SOMATICO EN HOMBRO DERECHO 1 (2.2%)
DOLOR ABDOMINAL AGUDO DE ORIGEN A DETERMINAR + NEUROPATIA SENSITIVA PERIFERICA + SINDROME DOLOROSO NEUROPATICO EN MUSLO DERECHO 1 (2.2%)
DOLOR ABDOMINAL AGUDO DE ORIGEN VISCERAL SEC A PROBABLE AT 1 (2.2%)
DOLOR ABDOMINAL AGUDO EN ESTUDIO 4 (8.9%)
DOLOR ABDOMINAL AGUDO OB SEC A AT 1 (2.2%)
DOLOR ABDOMINAL AGUDO PB SEC A AT 1 (2.2%)
DOLOR ABDOMINAL EN ESTUDIO PB SEC A AT 1 (2.2%)
DOLOR AGUDO EN SITIO DE COLOCACION DE CATETER PERCUTÁNEO 1 (2.2%)
DOLOR AGUDO POSTOPERATORIO ABDOMINAL 1 (2.2%)
DOLOR AGUDO POSTQUIRÚRGICO 1 (2.2%)
DOLOR AGUDO POSTQUIRURGICO EN TOMA DE INJERTO DE MPI 1 (2.2%)
DOLOR AGUDO VISCERAL ABDOMINAL SEC A AT 1 (2.2%)
DOLOR AGUDO VISCERAL SEC A RETIRO DE DOBLE JJ 1 (2.2%)
DOLOR VISCERAL EN RECTO SEC A AT 1 (2.2%)
LUMBALGIA AGUDA EN ESTUDIO 2 (4.4%)
LUMBALGIA CRONICA EN ESTUDIO 1 (2.2%)
LUMBALGIA EN ESTUDIO 1 (2.2%)
NEURALGIA DE LA 3ERA RAMA DEL NERVIO TRIGEMINO + PB NEURALGIA DEL GLOSOFARINGEO 1 (2.2%)
NEURALGIA POSTHERPETICA 1 (2.2%)
NEURALGIA POSTHERPETICA AGUDA 1 (2.2%)
SINDROME DOLOROSO DE MIEMBRO FANTASMA 1 (2.2%)
SINDROME DOLOROSO NOCICEPTIVO SOMATICO EN PARRILLA COSTAL DERECHA SEC A POSTTORACOTOMIA (AGUDO) 1 (2.2%)
SINDROME DOLOROSO NOCICEPTIVO VISCERAL ABDOMINAL PB SEC A AT 1 (2.2%)
SINDROME DOLOROSO NOCICEPTIVO Y NEUROPATICO EN MPD SEC A TROMBOSIS VENOSA PROFUNDA 1 (2.2%)
SINDROME MIOFASCIAL EN TRAPECIO DERECHO AGUDO 1 (2.2%)
SX DOLOROSO NOCICEPTIVO SOMATICO AXIAL SEC A RT 1 (2.2%)
SX DOLOROSO NOCICEPTIVO SOMATICO CON COMPONENTE NEUROPATCIO EN REGIÓN SACRA SEC A AT 1 (2.2%)
SX DOLOROSO NOCICEPTIVO SOMATICO CON COMPONENTE NEUROPATICO EN MPD SEC A PB AT 1 (2.2%)
SX DOLOROSO NOCICEPTIVO SOMATICO EN HEMICUELLO DERECHO SEC A PB AT 1 (2.2%)
SX DOLOROSO NOCICEPTIVO SOMATICO EN MPD SEC A TVP 1 (2.2%)
SX DOLOROSO NOCICEPTIVO SOMATICO EN MUSLO DERECHO SEC A INFECCION DE SITIO QUIRURGICO (AGUDO) 1 (2.2%)
SX DOLOROSO NOCICEPTIVO SOMATICO EN REGION COSTAL SEC A TRAUMA (AGUDO) 1 (2.2%)
SX DOLOROSO NOCICEPTIVO SOMATICO EN TORAX SEC A PROCEDIMIENTO QUIRURGICO (AGUDO) 1 (2.2%)
SX DOLOROSO NOCICEPTIVO VISCERAL CON COMPONENTE NEUROPATICO EN HIPOGASTRIO PB SEC A AT 1 (2.2%)
SX DOLOROSO NOCICEPTIVO VISCERAL EN HEMIABDOMEN INFERIOR SEC A AT 1 (2.2%)
SX DOLOROSO NOCICPETIVO SOMATICO CON COMPONENTE NEUROPATICO EN REGION MANDIBULAR IZQ PB SEC A AT 1 (2.2%)
SX. DOLOROSO NOCICEPTIVO SOMATICO CON COMPOENTE NEUROPATICO EN MPD SEC A SINDROME MEDULAR INCOMPLETO 1 (2.2%)
SX. DOLOROSO NOCICEPTIVO SOMATICO EN MIEMBRO PELVICO IZQUIERDO OB SEC A AT 1 (2.2%)
SX. DOLOROSO NOCICEPTIVO VISCERAL EN HEMIABDOMEN INFERIOR PB SEC A AT 1 (2.2%)
EDAD 52 (46, 63)
SEXO
F 36 (80%)
M 9 (20%)
ENAB
3 1 (2.2%)
4 4 (8.9%)
5 10 (22%)
6 12 (27%)
7 2 (4.4%)
8 8 (18%)
9 1 (2.2%)
10 7 (16%)
ENA A LOS 5 MIN
0 6 (13%)
1 7 (16%)
2 10 (22%)
3 9 (20%)
4 5 (11%)
5 6 (13%)
6 2 (4.4%)
ENA A LOS 10 MIN
0 14 (31%)
1 14 (31%)
2 13 (29%)
3 2 (4.4%)
5 1 (2.2%)
6 1 (2.2%)
EFECTOS ADVERSOS
MAREO 1 (2.2%)
NO 44 (98%)
LIKERT
3 7 (16%)
4 32 (73%)
5 5 (11%)
Unknown 1
1 n (%); Median (IQR) 
dbdraamandacode <- read_excel("C:/Users/fidel/OneDrive - CINVESTAV/PROYECTO MDatos/TRABAJOS/Dra. Amanda Azócar/dbdraamanda.xlsx",sheet=2)

dbamandacod<-dbdraamandacode

dbamanda <- dbdraamandacode %>% mutate(`DIAGNÓSTICO ONCOLÓGICO`=recode(`DIAGNÓSTICO ONCOLÓGICO`, `1`= "CANCER DE MAMA", 
                                                    `2` ="CANCER DE CERVIX",
                                                    `3` ="LINFOMA",
                                                    `4` = "CANCER DE OVARIO Y ENDOMETRIO",
                                                    `5` = "TUMOR GERMINAL",
                                                    `6` = "CANCER DE PROSTATA",
                                                    `7` = "CANCER DE PULMON",
                                                    `8` = "CANCER GENITOURINARIO",
                                                    `9` = "CA CAVIDAD ORAL",
                                                    `10` = "SARCOMAS",
                                                    `11` = "OTROS",
                                                    ),
                                  `DIAGNÓSTICO ALGOLÓGICO`=recode(`DIAGNÓSTICO ALGOLÓGICO`, `1` = "CANCER",
                                             `2` = "TX QUIRURGICO",
                                             `3` = "TX QT/RT",
                                             `4` = "NO RELACIONADO A CANCER"), EDAD=recode(EDAD, `1` = "18-29",
                                             `2` = "30-49",
                                             `3` = "50-59",
                                             `4` = "60-69",
                                             `5` = "70-79",
                                            `6` = "80-89"),
                                  SEXO=recode(SEXO, `1`="Femenino",
                                              `2`= "Masculino"),
                                  ENAB=recode(ENAB, `1`= "0-3",
                                              `2`="4-6",
                                              `3`="7-10"),
                                  `ENA A LOS 5 MIN`=recode(`ENA A LOS 5 MIN`, `1`= "0-3",
                                  `2`="4-6", `3`="7-10"),
`ENA A LOS 10 MIN`=recode(`ENA A LOS 10 MIN`, `1`="0-3",
                          `2`="4-6", `3`="7-10"),
`EFECTOS ADVERSOS` = recode(`EFECTOS ADVERSOS`, `1`="MAREO",
                            `2`= "NINGUNO"))
glimpse(dbamanda)
## Rows: 45
## Columns: 14
## $ EXPEDIENTE               <chr> "225106", "223140", "225341", "142234", "2216…
## $ `DIAGNÓSTICO ONCOLÓGICO` <chr> "CANCER DE MAMA", "CANCER DE CERVIX", "LINFOM…
## $ `DIAGNÓSTICO ALGOLÓGICO` <chr> "CANCER", "CANCER", "CANCER", "CANCER", "CANC…
## $ EDAD                     <chr> "60-69", "50-59", "70-79", "50-59", "50-59", …
## $ SEXO                     <chr> "Femenino", "Femenino", "Femenino", "Femenino…
## $ ENAB                     <chr> "4-6", "4-6", "4-6", "0-3", "4-6", "4-6", "7-…
## $ `ENA A LOS 5 MIN`        <chr> "0-3", "0-3", "0-3", "0-3", "4-6", "0-3", "4-…
## $ `ENA A LOS 10 MIN`       <chr> "0-3", "0-3", "0-3", "0-3", "4-6", "0-3", "0-…
## $ `EFECTOS ADVERSOS`       <chr> "NINGUNO", "NINGUNO", "MAREO", "NINGUNO", "NI…
## $ LIKERT                   <dbl> 4, 4, 4, 4, 4, 3, 4, 4, 4, 4, 4, 3, 5, 3, 3, …
## $ `MEDD DE MORFINA`        <dbl> 1, 1, 3, 1, 1, 2, 1, 1, 5, 1, 1, 6, 1, 1, 2, …
## $ `ENA 5 MIN`              <dbl> 2, 3, 1, 0, 6, 1, 4, 0, 3, 1, 1, 1, 2, 2, 3, …
## $ `ENA 10 MIN`             <dbl> 2, 2, 1, 0, 6, 1, 2, 0, 2, 1, 1, 0, 2, 1, 1, …
## $ `MEDD_MORFINA:`          <dbl> 0.00, 18.75, 41.58, 10.00, 0.00, 28.12, 9.37,…

Distribución edades

## 
## Attaching package: 'dlookr'
## The following object is masked from 'package:tidyr':
## 
##     extract
## The following object is masked from 'package:Hmisc':
## 
##     describe
## The following object is masked from 'package:base':
## 
##     transform
## # A tibble: 1 × 4
##   vars  statistic p_value sample
##   <chr>     <dbl>   <dbl>  <dbl>
## 1 EDAD      0.989   0.941     45
## Warning: geom_vline(): Ignoring `mapping` because `xintercept` was provided.
## Warning: geom_vline(): Ignoring `data` because `xintercept` was provided.

dbdraamanda%>% select(EDAD, SEXO) %>% drop_na() %>% tbl_summary(by=SEXO) %>% add_p() %>% add_overall()
## Warning for variable 'EDAD':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): cannot compute exact p-value with ties
## Warning: The `fmt_missing()` function is deprecated and will soon be removed
## * Use the `sub_missing()` function instead
Characteristic Overall, N = 451 F, N = 361 M, N = 91 p-value2
EDAD 52 (46, 63) 52 (46, 61) 53 (48, 65) 0.9
1 Median (IQR)
2 Wilcoxon rank sum test

EDADES y Sexo, boxplots

bpl <- ggplot(dbdraamanda, aes(x="", y=EDAD))

A<-bpl  + geom_boxplot(fill="skyblue") + theme_pubclean() +labs(y = "Años", x ="")

A

sex <- bpl + geom_boxplot(aes(fill=SEXO)) + theme_pubclean() 

sx<-sex + theme(legend.position = "none")+labs(y = "Años", x ="") 
sx

library(cowplot)
## 
## Attaching package: 'cowplot'
## The following object is masked from 'package:ggpubr':
## 
##     get_legend
plot_grid(A, sex, labels = c('A', 'B'), label_size = 12, ncol = 1, nrow = 2)

ggarrange(A, sex + rremove("x.text"), 
          labels = c("A", "B"),
          ncol = 1, nrow = 2,  common.legend = TRUE, legend = "top")

freq(dbamanda)
## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.
##    EXPEDIENTE frequency percentage cumulative_perc
## 1      120933         1       2.22            2.22
## 2      131993         1       2.22            4.44
## 3      141864         1       2.22            6.66
## 4      142234         1       2.22            8.88
## 5      165339         1       2.22           11.10
## 6      170037         1       2.22           13.32
## 7      171270         1       2.22           15.54
## 8      172809         1       2.22           17.76
## 9      185132         1       2.22           19.98
## 10     185523         1       2.22           22.20
## 11     194817         1       2.22           24.42
## 12     195296         1       2.22           26.64
## 13     212934         1       2.22           28.86
## 14     213974         1       2.22           31.08
## 15     215381         1       2.22           33.30
## 16     220458         1       2.22           35.52
## 17     221477         1       2.22           37.74
## 18     221698         1       2.22           39.96
## 19     223140         1       2.22           42.18
## 20     223175         1       2.22           44.40
## 21     223387         1       2.22           46.62
## 22     223714         1       2.22           48.84
## 23     223901         1       2.22           51.06
## 24     223984         1       2.22           53.28
## 25     224442         1       2.22           55.50
## 26     224695         1       2.22           57.72
## 27     225106         1       2.22           59.94
## 28     225127         1       2.22           62.16
## 29     225164         1       2.22           64.38
## 30     225203         1       2.22           66.60
## 31     225208         1       2.22           68.82
## 32     225304         1       2.22           71.04
## 33     225341         1       2.22           73.26
## 34     225505         1       2.22           75.48
## 35     225558         1       2.22           77.70
## 36     225662         1       2.22           79.92
## 37     225666         1       2.22           82.14
## 38     225759         1       2.22           84.36
## 39     225829         1       2.22           86.58
## 40     225837         1       2.22           88.80
## 41     225914         1       2.22           91.02
## 42      80784         1       2.22           93.24
## 43      81644         1       2.22           95.46
## 44      81850         1       2.22           97.68
## 45  FOL016586         1       2.22          100.00
## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.

##           DIAGNÓSTICO.ONCOLÓGICO frequency percentage cumulative_perc
## 1               CANCER DE CERVIX         9      20.00           20.00
## 2                 CANCER DE MAMA         7      15.56           35.56
## 3                          OTROS         6      13.33           48.89
## 4  CANCER DE OVARIO Y ENDOMETRIO         4       8.89           57.78
## 5                        LINFOMA         4       8.89           66.67
## 6                       SARCOMAS         4       8.89           75.56
## 7               CANCER DE PULMON         3       6.67           82.23
## 8                CA CAVIDAD ORAL         2       4.44           86.67
## 9             CANCER DE PROSTATA         2       4.44           91.11
## 10         CANCER GENITOURINARIO         2       4.44           95.55
## 11                TUMOR GERMINAL         2       4.44          100.00
## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.

##    DIAGNÓSTICO.ALGOLÓGICO frequency percentage cumulative_perc
## 1                  CANCER        21      46.67           46.67
## 2 NO RELACIONADO A CANCER        14      31.11           77.78
## 3           TX QUIRURGICO         9      20.00           97.78
## 4                TX QT/RT         1       2.22          100.00
## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.

##    EDAD frequency percentage cumulative_perc
## 1 50-59        16      35.56           35.56
## 2 30-49        14      31.11           66.67
## 3 60-69         9      20.00           86.67
## 4 70-79         4       8.89           95.56
## 5 18-29         2       4.44          100.00
## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.

##        SEXO frequency percentage cumulative_perc
## 1  Femenino        36         80              80
## 2 Masculino         9         20             100
## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.

##   ENAB frequency percentage cumulative_perc
## 1  4-6        26      57.78           57.78
## 2 7-10        18      40.00           97.78
## 3  0-3         1       2.22          100.00
## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.

##   ENA.A.LOS.5.MIN frequency percentage cumulative_perc
## 1             0-3        33      73.33           73.33
## 2             4-6        12      26.67          100.00
## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.

##   ENA.A.LOS.10.MIN frequency percentage cumulative_perc
## 1              0-3        43      95.56           95.56
## 2              4-6         2       4.44          100.00
## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.

##   EFECTOS.ADVERSOS frequency percentage cumulative_perc
## 1          NINGUNO        41      91.11           91.11
## 2            MAREO         4       8.89          100.00
## [1] "Variables processed: EXPEDIENTE, DIAGNÓSTICO.ONCOLÓGICO, DIAGNÓSTICO.ALGOLÓGICO, EDAD, SEXO, ENAB, ENA.A.LOS.5.MIN, ENA.A.LOS.10.MIN, EFECTOS.ADVERSOS"
sex <- dbamanda %>%
  group_by(SEXO) %>% 
  summarise(counts = n())


sex <- sex%>%
  arrange(desc(SEXO)) %>%
  mutate(prop = round(counts*100/sum(counts), 1),
         res = str_c(counts, "(", prop, "%)"),
         lab.ypos = cumsum(prop) - 0.5*prop)
head(df, 4)
##                                            
## 1 function (x, df1, df2, ncp, log = FALSE) 
## 2 {                                        
## 3     if (missing(ncp))                    
## 4         .Call(C_df, x, df1, df2, log)
sexpie<-ggplot(sex , aes(x = "", y = prop, fill = SEXO)) +
  geom_bar(width = 1, stat = "identity", color = "white") +
  geom_text(aes(y = lab.ypos, label = res), color = "black",
            fontface=2, size= 6)+
  coord_polar("y", start = 0)+
  ggpubr::fill_palette("")+
  theme_void() + labs(fill = "SEXO") + 
  theme(text = element_text(size = 16, face="bold"))

sexpie

tab1<-dbdraamanda %>% select(EDAD,SEXO) %>% tbl_summary(by=SEXO) %>% add_p() %>% add_overall()
## Warning for variable 'EDAD':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): cannot compute exact p-value with ties
tab1
## Warning: The `fmt_missing()` function is deprecated and will soon be removed
## * Use the `sub_missing()` function instead
Characteristic Overall, N = 451 F, N = 361 M, N = 91 p-value2
EDAD 52 (46, 63) 52 (46, 61) 53 (48, 65) 0.9
1 Median (IQR)
2 Wilcoxon rank sum test 
ggarrange(sexpie, A, sex, tab1,
          labels = c("A", "B", "C", "D"),
          ncol = 2, nrow = 2)
## Warning in as_grob.default(plot): Cannot convert object of class
## tbl_dftbldata.frame into a grob.
## Warning in as_grob.default(plot): Cannot convert object of class
## tbl_summarygtsummary into a grob.

ggarrange(sexpie,                                                 # First row with scatter plot
          ggarrange(A, sx, ncol = 2, labels = c("B", "C")), # Second row with box and dot plots
          nrow = 2, 
          labels = "A",  common.legend = TRUE, legend = "top"# Labels of the scatter plot
          ) 

glimpse(dbamanda)
## Rows: 45
## Columns: 14
## $ EXPEDIENTE               <chr> "225106", "223140", "225341", "142234", "2216…
## $ `DIAGNÓSTICO ONCOLÓGICO` <chr> "CANCER DE MAMA", "CANCER DE CERVIX", "LINFOM…
## $ `DIAGNÓSTICO ALGOLÓGICO` <chr> "CANCER", "CANCER", "CANCER", "CANCER", "CANC…
## $ EDAD                     <chr> "60-69", "50-59", "70-79", "50-59", "50-59", …
## $ SEXO                     <chr> "Femenino", "Femenino", "Femenino", "Femenino…
## $ ENAB                     <chr> "4-6", "4-6", "4-6", "0-3", "4-6", "4-6", "7-…
## $ `ENA A LOS 5 MIN`        <chr> "0-3", "0-3", "0-3", "0-3", "4-6", "0-3", "4-…
## $ `ENA A LOS 10 MIN`       <chr> "0-3", "0-3", "0-3", "0-3", "4-6", "0-3", "0-…
## $ `EFECTOS ADVERSOS`       <chr> "NINGUNO", "NINGUNO", "MAREO", "NINGUNO", "NI…
## $ LIKERT                   <dbl> 4, 4, 4, 4, 4, 3, 4, 4, 4, 4, 4, 3, 5, 3, 3, …
## $ `MEDD DE MORFINA`        <dbl> 1, 1, 3, 1, 1, 2, 1, 1, 5, 1, 1, 6, 1, 1, 2, …
## $ `ENA 5 MIN`              <dbl> 2, 3, 1, 0, 6, 1, 4, 0, 3, 1, 1, 1, 2, 2, 3, …
## $ `ENA 10 MIN`             <dbl> 2, 2, 1, 0, 6, 1, 2, 0, 2, 1, 1, 0, 2, 1, 1, …
## $ `MEDD_MORFINA:`          <dbl> 0.00, 18.75, 41.58, 10.00, 0.00, 28.12, 9.37,…

ENAB CHART PIE

dbamandaca <- dbamanda %>% filter(`DIAGNÓSTICO ALGOLÓGICO` == "CANCER"| `DIAGNÓSTICO ALGOLÓGICO` =="TX QUIRURGICO" | `DIAGNÓSTICO ALGOLÓGICO` == "TX QT/RT")
dbamandaca
## # A tibble: 31 × 14
##    EXPEDIENTE DIAGNÓS…¹ DIAGN…² EDAD  SEXO  ENAB  ENA A…³ ENA A…⁴ EFECT…⁵ LIKERT
##    <chr>      <chr>     <chr>   <chr> <chr> <chr> <chr>   <chr>   <chr>    <dbl>
##  1 225106     CANCER D… CANCER  60-69 Feme… 4-6   0-3     0-3     NINGUNO      4
##  2 223140     CANCER D… CANCER  50-59 Feme… 4-6   0-3     0-3     NINGUNO      4
##  3 225341     LINFOMA   CANCER  70-79 Feme… 4-6   0-3     0-3     MAREO        4
##  4 142234     LINFOMA   CANCER  50-59 Feme… 0-3   0-3     0-3     NINGUNO      4
##  5 221698     CA CAVID… CANCER  50-59 Feme… 4-6   4-6     4-6     NINGUNO      4
##  6 223175     SARCOMAS  TX QUI… 30-49 Feme… 4-6   0-3     0-3     NINGUNO      3
##  7 223714     CANCER D… TX QUI… 30-49 Feme… 4-6   0-3     0-3     NINGUNO      4
##  8 225662     OTROS     CANCER  50-59 Masc… 4-6   0-3     0-3     NINGUNO      4
##  9 225829     SARCOMAS  CANCER  30-49 Feme… 4-6   0-3     0-3     NINGUNO      3
## 10 225666     OTROS     CANCER  30-49 Feme… 7-10  0-3     0-3     NINGUNO      3
## # … with 21 more rows, 4 more variables: `MEDD DE MORFINA` <dbl>,
## #   `ENA 5 MIN` <dbl>, `ENA 10 MIN` <dbl>, `MEDD_MORFINA:` <dbl>, and
## #   abbreviated variable names ¹​`DIAGNÓSTICO ONCOLÓGICO`,
## #   ²​`DIAGNÓSTICO ALGOLÓGICO`, ³​`ENA A LOS 5 MIN`, ⁴​`ENA A LOS 10 MIN`,
## #   ⁵​`EFECTOS ADVERSOS`
enab <- dbamandaca %>%
  group_by(ENAB) %>% 
  summarise(counts = n())


enab <- enab%>%
  arrange(desc(ENAB)) %>%
  mutate(prop = round(counts*100/sum(counts), 1),
         res = str_c(counts, "(", prop, "%)"),
         lab.ypos = cumsum(prop) - 0.5*prop)
head(df, 4)
##                                            
## 1 function (x, df1, df2, ncp, log = FALSE) 
## 2 {                                        
## 3     if (missing(ncp))                    
## 4         .Call(C_df, x, df1, df2, log)
enabpie<-ggplot(enab , aes(x = "", y = prop, fill = ENAB)) +
  geom_bar(width = 1, stat = "identity", color = "white") +
  geom_text(aes(y = lab.ypos, label = res), color = "black",
            fontface=2, size= 6)+
  coord_polar("y", start = 0)+
  ggpubr::fill_palette("")+
  theme_void() + labs(fill = "ENAB") + 
  theme(text = element_text(size = 16, face="bold"))

enabpie

enaev <- dbamandaca %>% select(`ENA A LOS 5 MIN`,`ENA A LOS 10 MIN`)

enaev 
## # A tibble: 31 × 2
##    `ENA A LOS 5 MIN` `ENA A LOS 10 MIN`
##    <chr>             <chr>             
##  1 0-3               0-3               
##  2 0-3               0-3               
##  3 0-3               0-3               
##  4 0-3               0-3               
##  5 4-6               4-6               
##  6 0-3               0-3               
##  7 0-3               0-3               
##  8 0-3               0-3               
##  9 0-3               0-3               
## 10 0-3               0-3               
## # … with 21 more rows
enaevo <-gather(enaev, key="tiempo", value="ENA")

enaevo <- enaevo %>% mutate(tiempo = factor(tiempo, levels=c("ENA A LOS 5 MIN", "ENA A LOS 10 MIN"))) 

df <- enaevo %>% group_by(tiempo, ENA) %>%  summarise(n = n()) %>% 
  mutate(
    perc = round(proportions(n) * 100, 1),
    res = str_c(n, "(", perc, "%)"))
## Warning in gzfile(file, mode): cannot open compressed file 'C:/Users/fidel/
## AppData/Local/Temp/RtmpymG1AW\file34846515a0c', probable reason 'No such file or
## directory'
## `summarise()` has grouped output by 'tiempo'. You can override using the
## `.groups` argument.
# Use position = position_dodge() 
p <- ggplot(df, aes(x = tiempo, y = n)) +
  geom_bar(
    aes(color = ENA, fill = ENA),
    stat = "identity", position = position_dodge(0.8),
    width = 0.7
    )

p +  theme_pubclean()+ylab("conteo")+xlab("") + geom_text(
  aes(label = res, group = ENA), 
  position = position_dodge(0.8),
  vjust = -0.3, size = 3.5
)

Tablas cruzadas

t1<-dbamandaca %>%
  tbl_cross(
    row = ENAB,
    col = `ENA A LOS 5 MIN`,
    percent = "cell"
  ) %>%
  add_p()

t2<-dbamandaca %>%
  tbl_cross(
    row = ENAB,
    col = `ENA A LOS 10 MIN`,
    percent = "cell"
  ) %>%
  add_p()

tbl_merge_ex2 <-
  tbl_merge(tbls = list(t1, t2),
    tab_spanner = c("**ENA A LOS 5 MIN**", "**ENA A LOS 10 MIN**")
  )
tbl_merge_ex2
## Warning: The `fmt_missing()` function is deprecated and will soon be removed
## * Use the `sub_missing()` function instead
ENA A LOS 5 MIN ENA A LOS 10 MIN
0-3 4-6 Total p-value1 0-3 4-6 Total p-value1
ENAB 0.052 >0.9
0-3 1 (3.2%) 0 (0%) 1 (3.2%) 1 (3.2%) 0 (0%) 1 (3.2%)
4-6 18 (58%) 2 (6.5%) 20 (65%) 19 (61%) 1 (3.2%) 20 (65%)
7-10 5 (16%) 5 (16%) 10 (32%) 10 (32%) 0 (0%) 10 (32%)
Total 24 (77%) 7 (23%) 31 (100%) 30 (97%) 1 (3.2%) 31 (100%)
1 Fisher's exact test 
dbamandaca %>%
  tbl_cross(
    row = `ENA A LOS 5 MIN`,
    col = `ENA A LOS 10 MIN`,
    percent = "cell"
  ) %>%
  add_p(source_note = TRUE)
## Warning: The `fmt_missing()` function is deprecated and will soon be removed
## * Use the `sub_missing()` function instead
ENA A LOS 10 MIN Total
0-3 4-6
ENA A LOS 5 MIN
0-3 24 (77%) 0 (0%) 24 (77%)
4-6 6 (19%) 1 (3.2%) 7 (23%)
Total 30 (97%) 1 (3.2%) 31 (100%)
Fisher's exact test, p=0.2 
glimpse(dbamanda)
## Rows: 45
## Columns: 14
## $ EXPEDIENTE               <chr> "225106", "223140", "225341", "142234", "2216…
## $ `DIAGNÓSTICO ONCOLÓGICO` <chr> "CANCER DE MAMA", "CANCER DE CERVIX", "LINFOM…
## $ `DIAGNÓSTICO ALGOLÓGICO` <chr> "CANCER", "CANCER", "CANCER", "CANCER", "CANC…
## $ EDAD                     <chr> "60-69", "50-59", "70-79", "50-59", "50-59", …
## $ SEXO                     <chr> "Femenino", "Femenino", "Femenino", "Femenino…
## $ ENAB                     <chr> "4-6", "4-6", "4-6", "0-3", "4-6", "4-6", "7-…
## $ `ENA A LOS 5 MIN`        <chr> "0-3", "0-3", "0-3", "0-3", "4-6", "0-3", "4-…
## $ `ENA A LOS 10 MIN`       <chr> "0-3", "0-3", "0-3", "0-3", "4-6", "0-3", "0-…
## $ `EFECTOS ADVERSOS`       <chr> "NINGUNO", "NINGUNO", "MAREO", "NINGUNO", "NI…
## $ LIKERT                   <dbl> 4, 4, 4, 4, 4, 3, 4, 4, 4, 4, 4, 3, 5, 3, 3, …
## $ `MEDD DE MORFINA`        <dbl> 1, 1, 3, 1, 1, 2, 1, 1, 5, 1, 1, 6, 1, 1, 2, …
## $ `ENA 5 MIN`              <dbl> 2, 3, 1, 0, 6, 1, 4, 0, 3, 1, 1, 1, 2, 2, 3, …
## $ `ENA 10 MIN`             <dbl> 2, 2, 1, 0, 6, 1, 2, 0, 2, 1, 1, 0, 2, 1, 1, …
## $ `MEDD_MORFINA:`          <dbl> 0.00, 18.75, 41.58, 10.00, 0.00, 28.12, 9.37,…

#https://rstudio-pubs-static.s3.amazonaws.com/158214_3e5cc0d244f942f2a2dc33fecdf87764.html

Se me ocurrio la idea dividir cancer y no cancer y ver que efecto tiene a los 5 y 10 minutos

CANCER 21 46.67 46.67
NO RELACIONADO A CANCER 14 31.11 77.78
TX QUIRURGICO 9 20.00 97.78
TX QT/RT

    cadb<-dbamandacod %>% mutate(`DIAGNÓSTICO ALGOLÓGICO`=recode(`DIAGNÓSTICO ALGOLÓGICO`, `1` = "CANCER",
                                             `2` = "CANCER",
                                             `3` = "CANCER",
                                             `4` = "NO CANCER"),
                                  `ENA A LOS 5 MIN`=recode(`ENA A LOS 5 MIN`, `1`= "0-3",
                                  `2`="4-6", `3`="7-10"),
`ENA A LOS 10 MIN`=recode(`ENA A LOS 10 MIN`, `1`="0-3",
                          `2`="4-6", `3`="7-10"),
`MEDD DE MORFINA` =recode(`MEDD DE MORFINA` , `1`="0-20", `2`="21-40",`3`="41-60",`4`="61-80",`5`="81-100", `6`="más de 100"))


cadb$`ENA A LOS 10 MIN` = as.numeric(cadb$`ENA A LOS 10 MIN` )
## Warning: NAs introducidos por coerción
cadb$`ENA A LOS 5 MIN` = as.numeric(cadb$`ENA A LOS 5 MIN` ) 
## Warning: NAs introducidos por coerción
cadb %>% select(`DIAGNÓSTICO ALGOLÓGICO`,`ENA 5 MIN`, `ENA 10 MIN`,`ENA A LOS 5 MIN`, `ENA A LOS 10 MIN`) %>% tbl_summary(by= `DIAGNÓSTICO ALGOLÓGICO`,type = list(where(is.numeric) ~ "continuous2")) %>% add_p() %>% add_overall()
## Warning for variable 'ENA 5 MIN':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): cannot compute exact p-value with ties
## Warning for variable 'ENA 10 MIN':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): cannot compute exact p-value with ties
## There was an error in 'add_p()/add_difference()' for variable 'ENA A LOS 5 MIN', p-value omitted:
## Error in wilcox.test.formula(as.numeric(`ENA A LOS 5 MIN`) ~ as.factor(`DIAGNÓSTICO ALGOLÓGICO`), : grouping factor must have exactly 2 levels
## There was an error in 'add_p()/add_difference()' for variable 'ENA A LOS 10 MIN', p-value omitted:
## Error in wilcox.test.formula(as.numeric(`ENA A LOS 10 MIN`) ~ as.factor(`DIAGNÓSTICO ALGOLÓGICO`), : grouping factor must have exactly 2 levels
## Warning: The `fmt_missing()` function is deprecated and will soon be removed
## * Use the `sub_missing()` function instead
Characteristic Overall, N = 45 CANCER, N = 31 NO CANCER, N = 14 p-value1
ENA 5 MIN 0.3
Median (IQR) 2.00 (1.00, 4.00) 2.00 (1.00, 3.50) 3.00 (2.00, 4.00)
ENA 10 MIN 0.3
Median (IQR) 1.00 (0.00, 2.00) 1.00 (0.00, 2.00) 1.50 (0.25, 2.00)
ENA A LOS 5 MIN
Median (IQR) NA (NA, NA) NA (NA, NA) NA (NA, NA)
Unknown 45 31 14
ENA A LOS 10 MIN
Median (IQR) NA (NA, NA) NA (NA, NA) NA (NA, NA)
Unknown 45 31 14
1 Wilcoxon rank sum test

MEDD MORFINA

cadb %>% select(`DIAGNÓSTICO ALGOLÓGICO`,`MEDD_MORFINA:`,`MEDD DE MORFINA`) %>% tbl_summary(by= `DIAGNÓSTICO ALGOLÓGICO`,type = list(where(is.numeric) ~ "continuous2")) %>% add_p() %>% add_overall()
## Warning for variable 'MEDD_MORFINA:':
## simpleWarning in wilcox.test.default(x = DATA[[1L]], y = DATA[[2L]], ...): cannot compute exact p-value with ties
## Warning: The `fmt_missing()` function is deprecated and will soon be removed
## * Use the `sub_missing()` function instead
Characteristic Overall, N = 451 CANCER, N = 311 NO CANCER, N = 141 p-value2
MEDD_MORFINA: 0.4
Median (IQR) 9 (0, 28) 0 (0, 28) 15 (0, 37)
MEDD DE MORFINA 0.7
0-20 28 (62%) 20 (65%) 8 (57%)
21-40 6 (13%) 4 (13%) 2 (14%)
41-60 4 (8.9%) 3 (9.7%) 1 (7.1%)
61-80 2 (4.4%) 1 (3.2%) 1 (7.1%)
81-100 3 (6.7%) 1 (3.2%) 2 (14%)
más de 100 2 (4.4%) 2 (6.5%) 0 (0%)
1 n (%)
2 Wilcoxon rank sum test; Fisher's exact test