#Introduccion En este documento se realizara una “Tabla 1” sobre “Framingham Heart Study”, el cual trata sobre el estudio de las enfermedades cardiovasculares de una poblacion en Framinghan, Massachusetts. Es una investigacion de las mas durareas en la historia de la epidemiologia, la cual su proposito fue identificar factores de riesgo en enfermedades cardiovasculares a largo plazo de una cohorte de personas. El data set que se manejara para este proyecto sera un subconjunto mas pequeño de datos que la original, conteniendo asi 4240 observaciones con 16 variables.
#En esta seccion se importaran la base de datos
FHS <- read.csv("framingham_dataset.csv", header = TRUE)
head(FHS, 10)## X randid sex totchol age sysbp diabp cursmoke cigpday bmi diabetes bpmeds
## 1 1 2448 1 195 39 106.0 70.0 0 0 26.97 0 0
## 2 2 2448 1 209 52 121.0 66.0 0 0 NA 0 0
## 3 3 6238 2 250 46 121.0 81.0 0 0 28.73 0 0
## 4 4 6238 2 260 52 105.0 69.5 0 0 29.43 0 0
## 5 5 6238 2 237 58 108.0 66.0 0 0 28.50 0 0
## 6 6 9428 1 245 48 127.5 80.0 1 20 25.34 0 0
## 7 7 9428 1 283 54 141.0 89.0 1 30 25.34 0 0
## 8 8 10552 2 225 61 150.0 95.0 1 30 28.58 0 0
## 9 9 10552 2 232 67 183.0 109.0 1 20 30.18 0 0
## 10 10 11252 2 285 46 130.0 84.0 1 23 23.10 0 0
## heartrte glucose educ prevchd prevap prevmi prevstrk prevhyp time period
## 1 80 77 4 0 0 0 0 0 0 1
## 2 69 92 4 0 0 0 0 0 4628 3
## 3 95 76 2 0 0 0 0 0 0 1
## 4 80 86 2 0 0 0 0 0 2156 2
## 5 80 71 2 0 0 0 0 0 4344 3
## 6 75 70 1 0 0 0 0 0 0 1
## 7 75 87 1 0 0 0 0 0 2199 2
## 8 65 103 3 0 0 0 0 1 0 1
## 9 60 89 3 0 0 0 0 1 1977 2
## 10 85 85 3 0 0 0 0 0 0 1
## hdlc ldlc death angina hospmi mi_fchd anychd stroke cvd hyperten timeap
## 1 NA NA 0 0 1 1 1 0 1 0 8766
## 2 31 178 0 0 1 1 1 0 1 0 8766
## 3 NA NA 0 0 0 0 0 0 0 0 8766
## 4 NA NA 0 0 0 0 0 0 0 0 8766
## 5 54 141 0 0 0 0 0 0 0 0 8766
## 6 NA NA 0 0 0 0 0 0 0 0 8766
## 7 NA NA 0 0 0 0 0 0 0 0 8766
## 8 NA NA 1 0 0 0 0 1 1 1 2956
## 9 NA NA 1 0 0 0 0 1 1 1 2956
## 10 NA NA 0 0 0 0 0 0 0 1 8766
## timemi timemifc timechd timestrk timecvd timedth timehyp
## 1 6438 6438 6438 8766 6438 8766 8766
## 2 6438 6438 6438 8766 6438 8766 8766
## 3 8766 8766 8766 8766 8766 8766 8766
## 4 8766 8766 8766 8766 8766 8766 8766
## 5 8766 8766 8766 8766 8766 8766 8766
## 6 8766 8766 8766 8766 8766 8766 8766
## 7 8766 8766 8766 8766 8766 8766 8766
## 8 2956 2956 2956 2089 2089 2956 0
## 9 2956 2956 2956 2089 2089 2956 0
## 10 8766 8766 8766 8766 8766 8766 4285Como primer paso daremos categoria a variables binarias, por ejemplo, para la variable “sex” unicamente arroja valores 2 y 1, las cuales representan femenino y masculino respectivamente, se realizara el mismo ejercicio para las demas variables con la misma situacion de valores binarios:
#Se generan intervalos de la edad, estas se escojieron a partir del
#primer y tecer quartil, teniendo tres intervalos de edades
edad <- cut(FHS$age ,
breaks = c(-Inf, 48, 62, Inf),
labels = c("menos de 48 años", "De 48 a 62 años" , " mas de 62 años"))
sexo <- factor(FHS$sex, levels = c(1,2),
labels = c("Male", "Female"))
educacion <- factor(FHS$educ,
levels =c(1,2,3,4),
labels = c("Some high school", "High school diploma/GED", "Some college, vocational school", "College (BS,BA) degree or more"))
prevelant_stroke <- factor(FHS$prevstrk, levels = c(0,1),
labels = c("Free of disease","Prevelant disease"))
prevelant_hyp <- factor(FHS$prevhyp, levels = c(0,1),
labels = c("Free of disease","Prevelant disease"))
diabetic <- factor(FHS$diabetes, levels = c(0,1),
labels = c("No a diabetic","Diabetic"))
#variables a comparar con los estratos
variable_fchd <- factor(FHS$mi_fchd, levels = c(0,1),
labels = c("Hospitalized MI - Fatal CHD","Angina"))
angina_pecho <- factor(FHS$angina, levels = c(0,1), labels = c("No","Yes") )
#Se colocan las etiquetas para cada variable
label(FHS$age) <- "Age(Years)"
label(sexo) <- "Sex"
label(edad) <- "Age"
label(educacion) <- "education"
label(prevelant_stroke) <- "Prevelant Stroke"
label(prevelant_hyp) <- "Prevelant Hipertensive"
label(diabetic) <- "Diabetes"
label(variable_fchd) <- "Hospitalized MI - Fatal CHD"
label(angina_pecho) <- "Angina"En esta Tabla 1, se comparan los estratos con la variable
my_fchd y la variable angina las cuales
representan las tasas de incidencias de angina de pecho y de la
cardiopatía isquémica fatal hospitalizada
table1(~ sexo + age + edad + educacion + prevelant_hyp + prevelant_stroke + diabetic | variable_fchd*angina_pecho,
data = FHS,
render.continuous = c(.="Mean (SD)", .="Median [Q1, Q3]"),
overall = FALSE,
caption = "Specific Angina and Hospitalized MI-Fatal CHD Incidence Rates")Hospitalized MI - Fatal CHD |
Angina |
|||
|---|---|---|---|---|
| No (N=8777) |
Yes (N=1062) |
No (N=948) |
Yes (N=840) |
|
| Sex | ||||
| Male | 3440 (39.2%) | 398 (37.5%) | 602 (63.5%) | 582 (69.3%) |
| Female | 5337 (60.8%) | 664 (62.5%) | 346 (36.5%) | 258 (30.7%) |
| Age(Years) | ||||
| Mean (SD) | 54.0 (9.47) | 57.1 (9.48) | 57.4 (9.47) | 57.2 (9.41) |
| Median [Q1, Q3] | 53.0 [47.0, 61.0] | 58.0 [50.0, 64.0] | 57.0 [50.0, 64.0] | 57.0 [50.0, 64.0] |
| Age | ||||
| menos de 48 años | 2736 (31.2%) | 204 (19.2%) | 188 (19.8%) | 168 (20.0%) |
| De 48 a 62 años | 4241 (48.3%) | 528 (49.7%) | 459 (48.4%) | 403 (48.0%) |
| mas de 62 años | 1800 (20.5%) | 330 (31.1%) | 301 (31.8%) | 269 (32.0%) |
| education | ||||
| Some high school | 3372 (38.4%) | 506 (47.6%) | 443 (46.7%) | 369 (43.9%) |
| High school diploma/GED | 2692 (30.7%) | 254 (23.9%) | 278 (29.3%) | 186 (22.1%) |
| Some college, vocational school | 1508 (17.2%) | 140 (13.2%) | 106 (11.2%) | 131 (15.6%) |
| College (BS,BA) degree or more | 987 (11.2%) | 128 (12.1%) | 99 (10.4%) | 133 (15.8%) |
| Missing | 218 (2.5%) | 34 (3.2%) | 22 (2.3%) | 21 (2.5%) |
| Prevelant Hipertensive | ||||
| Free of disease | 5128 (58.4%) | 466 (43.9%) | 372 (39.2%) | 317 (37.7%) |
| Prevelant disease | 3649 (41.6%) | 596 (56.1%) | 576 (60.8%) | 523 (62.3%) |
| Prevelant Stroke | ||||
| Free of disease | 8690 (99.0%) | 1045 (98.4%) | 919 (96.9%) | 821 (97.7%) |
| Prevelant disease | 87 (1.0%) | 17 (1.6%) | 29 (3.1%) | 19 (2.3%) |
| Diabetes | ||||
| No a diabetic | 8501 (96.9%) | 998 (94.0%) | 845 (89.1%) | 753 (89.6%) |
| Diabetic | 276 (3.1%) | 64 (6.0%) | 103 (10.9%) | 87 (10.4%) |
Para finalizar se realizara una ultima comparacion con los accidentes cerebrovasculares y enfermedades cardiovaculares (mortales y no mortales).
strk <- factor(FHS$stroke, levels = c(0,1),
labels = c("CVD", "Stroke"))
carvd <- factor(FHS$cvd, levels = c(0,1), labels = c("event did not occur", "event did occur"))
label(strk) <- "Stroke"
label(carvd) <- "CVD"
table1(~ sexo + age + edad + educacion + prevelant_hyp + diabetic | strk*carvd,
data = FHS,
render.continuous = c(.="Mean (SD)", .="Median [Q1, Q3]"),
overall = FALSE,
caption = "Specific Stroke and Cardiovascular Disease (Fatal and Non-Fatal) Incidence Rates")CVD |
Stroke |
||
|---|---|---|---|
| event did not occur (N=8728) |
event did occur (N=1838) |
event did occur (N=1061) |
|
| Sex | |||
| Male | 3333 (38.2%) | 1201 (65.3%) | 488 (46.0%) |
| Female | 5395 (61.8%) | 637 (34.7%) | 573 (54.0%) |
| Age(Years) | |||
| Mean (SD) | 53.6 (9.35) | 57.1 (9.40) | 60.4 (8.90) |
| Median [Q1, Q3] | 53.0 [47.0, 60.0] | 57.0 [50.0, 64.0] | 61.0 [55.0, 67.0] |
| Age | |||
| menos de 48 años | 2801 (32.1%) | 376 (20.5%) | 119 (11.2%) |
| De 48 a 62 años | 4264 (48.9%) | 897 (48.8%) | 470 (44.3%) |
| mas de 62 años | 1663 (19.1%) | 565 (30.7%) | 472 (44.5%) |
| education | |||
| Some high school | 3311 (37.9%) | 835 (45.4%) | 544 (51.3%) |
| High school diploma/GED | 2636 (30.2%) | 513 (27.9%) | 261 (24.6%) |
| Some college, vocational school | 1537 (17.6%) | 215 (11.7%) | 133 (12.5%) |
| College (BS,BA) degree or more | 1025 (11.7%) | 225 (12.2%) | 97 (9.1%) |
| Missing | 219 (2.5%) | 50 (2.7%) | 26 (2.5%) |
| Prevelant Hipertensive | |||
| Free of disease | 5235 (60.0%) | 760 (41.3%) | 288 (27.1%) |
| Prevelant disease | 3493 (40.0%) | 1078 (58.7%) | 773 (72.9%) |
| Diabetes | |||
| No a diabetic | 8494 (97.3%) | 1670 (90.9%) | 933 (87.9%) |
| Diabetic | 234 (2.7%) | 168 (9.1%) | 128 (12.1%) |