What Cause Heart Disease

library(SASxport)
library(naniar)
library(ggplot2)
library(gapminder)
library(tidyverse)

## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --

## v tibble  3.1.6     v dplyr   1.0.8
## v tidyr   1.2.0     v stringr 1.4.0
## v readr   2.1.2     v forcats 0.5.1
## v purrr   0.3.4

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(GGally)

## Registered S3 method overwritten by 'GGally':
##   method from   
##   +.gg   ggplot2

library(stringr)

Read Data

https://www.cdc.gov/brfss/annual_data/annual_data.htm

BRFSS2020 = read.xport("LLCP2020.XPT")
BRFSS2020

https://www.cdc.gov/brfss/annual_data/2020/pdf/2020-calculated-variables-version4-508.pdf

This dataset contains hundreds of variables

colnames(BRFSS2020)

##   [1] "X.STATE"   "FMONTH"    "IDATE"     "IMONTH"    "IDAY"      "IYEAR"    
##   [7] "DISPCODE"  "SEQNO"     "X.PSU"     "CTELENM1"  "PVTRESD1"  "COLGHOUS" 
##  [13] "STATERE1"  "CELPHONE"  "LADULT1"   "COLGSEX"   "NUMADULT"  "LANDSEX"  
##  [19] "NUMMEN"    "NUMWOMEN"  "RESPSLCT"  "SAFETIME"  "CTELNUM1"  "CELLFON5" 
##  [25] "CADULT1"   "CELLSEX"   "PVTRESD3"  "CCLGHOUS"  "CSTATE1"   "LANDLINE" 
##  [31] "HHADULT"   "SEXVAR"    "GENHLTH"   "PHYSHLTH"  "MENTHLTH"  "POORHLTH" 
##  [37] "HLTHPLN1"  "PERSDOC2"  "MEDCOST"   "CHECKUP1"  "EXERANY2"  "SLEPTIM1" 
##  [43] "CVDINFR4"  "CVDCRHD4"  "CVDSTRK3"  "ASTHMA3"   "ASTHNOW"   "CHCSCNCR" 
##  [49] "CHCOCNCR"  "CHCCOPD2"  "HAVARTH4"  "ADDEPEV3"  "CHCKDNY2"  "DIABETE4" 
##  [55] "DIABAGE3"  "LASTDEN4"  "RMVTETH4"  "MARITAL"   "EDUCA"     "RENTHOM1" 
##  [61] "NUMHHOL3"  "NUMPHON3"  "CPDEMO1B"  "VETERAN3"  "EMPLOY1"   "CHILDREN" 
##  [67] "INCOME2"   "PREGNANT"  "WEIGHT2"   "HEIGHT3"   "DEAF"      "BLIND"    
##  [73] "DECIDE"    "DIFFWALK"  "DIFFDRES"  "DIFFALON"  "SMOKE100"  "SMOKDAY2" 
##  [79] "STOPSMK2"  "LASTSMK2"  "USENOW3"   "ALCDAY5"   "AVEDRNK3"  "DRNK3GE5" 
##  [85] "MAXDRNKS"  "FLUSHOT7"  "FLSHTMY3"  "SHINGLE2"  "PNEUVAC4"  "FALL12MN" 
##  [91] "FALLINJ4"  "SEATBELT"  "DRNKDRI2"  "HADMAM"    "HOWLONG"   "HADPAP2"  
##  [97] "LASTPAP2"  "HPVTEST"   "HPLSTTST"  "HADHYST2"  "PCPSAAD3"  "PCPSADI1" 
## [103] "PCPSARE1"  "PSATEST1"  "PSATIME"   "PCPSARS1"  "COLNSCPY"  "COLNTEST" 
## [109] "SIGMSCPY"  "SIGMTEST"  "BLDSTOL1"  "LSTBLDS4"  "STOOLDNA"  "SDNATEST" 
## [115] "VIRCOLON"  "VCLNTEST"  "HIVTST7"   "HIVTSTD3"  "HIVRISK5"  "PDIABTST" 
## [121] "PREDIAB1"  "INSULIN1"  "BLDSUGAR"  "FEETCHK3"  "DOCTDIAB"  "CHKHEMO3" 
## [127] "FEETCHK"   "EYEEXAM1"  "DIABEYE"   "DIABEDU"   "TOLDCFS"   "HAVECFS"  
## [133] "WORKCFS"   "TOLDHEPC"  "TRETHEPC"  "PRIRHEPC"  "HAVEHEPC"  "HAVEHEPB" 
## [139] "MEDSHEPB"  "HLTHCVR1"  "CIMEMLOS"  "CDHOUSE"   "CDASSIST"  "CDHELP"   
## [145] "CDSOCIAL"  "CDDISCUS"  "CAREGIV1"  "CRGVREL4"  "CRGVLNG1"  "CRGVHRS1" 
## [151] "CRGVPRB3"  "CRGVALZD"  "CRGVPER1"  "CRGVHOU1"  "CRGVEXPT"  "ECIGARET" 
## [157] "ECIGNOW"   "MARIJAN1"  "USEMRJN2"  "RSNMRJN1"  "LCSFIRST"  "LCSLAST"  
## [163] "LCSNUMCG"  "LCSCTSCN"  "CNCRDIFF"  "CNCRAGE"   "CNCRTYP1"  "CSRVTRT3" 
## [169] "CSRVDOC1"  "CSRVSUM"   "CSRVRTRN"  "CSRVINST"  "CSRVINSR"  "CSRVDEIN" 
## [175] "CSRVCLIN"  "CSRVPAIN"  "CSRVCTL2"  "PCPSADE1"  "PCDMDEC1"  "HPVADVC4" 
## [181] "HPVADSHT"  "TETANUS1"  "IMFVPLA1"  "BIRTHSEX"  "SOMALE"    "SOFEMALE" 
## [187] "TRNSGNDR"  "ACEDEPRS"  "ACEDRINK"  "ACEDRUGS"  "ACEPRISN"  "ACEDIVRC" 
## [193] "ACEPUNCH"  "ACEHURT1"  "ACESWEAR"  "ACETOUCH"  "ACETTHEM"  "ACEHVSEX" 
## [199] "RCSGENDR"  "RCSRLTN2"  "CASTHDX2"  "CASTHNO2"  "QSTVER"    "QSTLANG"  
## [205] "X.METSTAT" "X.URBSTAT" "MSCODE"    "X.STSTR"   "X.STRWT"   "X.RAWRAKE"
## [211] "X.WT2RAKE" "X.IMPRACE" "X.CHISPNC" "X.CRACE1"  "X.CPRACE"  "X.CLLCPWT"
## [217] "X.DUALUSE" "X.DUALCOR" "X.LLCPWT2" "X.LLCPWT"  "X.RFHLTH"  "X.PHYS14D"
## [223] "X.MENT14D" "X.HCVU651" "X.TOTINDA" "X.MICHD"   "X.LTASTH1" "X.CASTHM1"
## [229] "X.ASTHMS1" "X.DRDXAR2" "X.EXTETH3" "X.ALTETH3" "X.DENVST3" "X.PRACE1" 
## [235] "X.MRACE1"  "X.HISPANC" "X.RACE"    "X.RACEG21" "X.RACEGR3" "X.RACEPRV"
## [241] "X.SEX"     "X.AGEG5YR" "X.AGE65YR" "X.AGE80"   "X.AGE.G"   "HTIN4"    
## [247] "HTM4"      "WTKG3"     "X.BMI5"    "X.BMI5CAT" "X.RFBMI5"  "X.CHLDCNT"
## [253] "X.EDUCAG"  "X.INCOMG"  "X.SMOKER3" "X.RFSMOK3" "DRNKANY5"  "DROCDY3." 
## [259] "X.RFBING5" "X.DRNKWK1" "X.RFDRHV7" "X.FLSHOT7" "X.PNEUMO3" "X.RFSEAT2"
## [265] "X.RFSEAT3" "X.DRNKDRV" "X.RFMAM22" "X.MAM5023" "X.RFPAP35" "X.RFPSA23"
## [271] "X.CLNSCPY" "X.SGMSCPY" "X.SGMS10Y" "X.RFBLDS4" "X.STOLDNA" "X.VIRCOLN"
## [277] "X.SBONTIM" "X.CRCREC1" "X.AIDTST4"

Choose 12 variables

BRFSS2020 = BRFSS2020 %>%
  select(SEQNO,IDATE,X.SEX,X.AGEG5YR,X.RACE,HTM4,WTKG3,X.BMI5CAT,X.SMOKER3,DROCDY3.,X.TOTINDA,X.MICHD)%>%
  rename(Date = IDATE,
         Sex = X.SEX,
         Age.CAT = X.AGEG5YR,
         Height.M = HTM4,
         Weitht.KG = WTKG3,
         BMI.CAT = X.BMI5CAT,
         Race.CAT = X.RACE,
         Smoker = X.SMOKER3,
         Drinking = DROCDY3.,
         Exercise = X.TOTINDA,
         CornoaryHeartD = X.MICHD)
BRFSS2020

Variables

https://www.cdc.gov/brfss/annual_data/2020/pdf/2020-calculated-variables-version4-508.pdf

Age:

• _AGEG5YR Calculated variable for fourteen-level age category. _AGEG5YR is derived from AGE.

• 1 Age 18 to 24 Respondents with reported age between 18 and 24 years (18 <= AGE <= 24)

• 2 Age 25 to 29 Respondents with reported age between 25 and 29 years (25 <= AGE <= 29)

• 3 Age 30 to 34 Respondents with reported age between 30 and 34 years (30 <= AGE <= 34)

• 4 Age 35 to 39 Respondents with reported age between 35 and 39 years (35 <= AGE <= 39)

• 5 Age 40 to 44 Respondents with reported age between 40 and 44 years (40 <= AGE <= 44)

• 6 Age 45 to 49 Respondents with reported age between 45 and 49 years (45 <= AGE <= 49)

• 7 Age 50 to 54 Respondents with reported age between 50 and 54 years (50 <= AGE <= 54)

• 8 Age 55 to 59 Respondents with reported age between 55 and 59 years (55 <= AGE <= 59)

• 9 Age 60 to 64 Respondents with reported age between 60 and 64 years (60 <= AGE <= 64)

• 10 Age 65 to 69 Respondents with reported age between 65 and 69 years (65 <= AGE <= 69)

• 11 Age 70 to 74 Respondents with reported age between 70 and 74 years (70 <= AGE <= 74)

• 12 Age 75 to 79 Respondents with reported age between 75 and 79 years (75 <= AGE <= 79)

• 13 Age 80 or older Respondents with reported age between 80 and 99 years (80 <= AGE <= 99)

• 14 Don’t know/ Refused/ Missing Respondents who reported they didn´t know, were not sure, refused to report or had missing responses for their age. (AGE=7, 9, missing)

Sex:

• 1 Male Male respondent (BIRTHSEX=1 or BIRTHSEX notin (1,2) and SEXVAR=1)

• 2 Female Female respondent (BIRTHSEX=2 or BIRTHSEX notin (1,2) and SEXVAR=2)

Race:

• 1 White only, nonHispanic Respondents who reported they are white and not of Hispanic origin.

• 2 Black only, nonHispanic Respondents who reported they are black and not of Hispanic origin. (_MRACE1=2 and _HISPANC=2)

• 3 American Indian or Alaskan Native only, Non-Hispanic Respondents who reported they are American Indian or Alaska Native and not of Hispanic origin. (_MRACE1=3 and _HISPANC=2)

• 4 Asian only, nonHispanic Respondents who reported they are Asian and not of Hispanic origin. (_MRACE1=4 and _HISPANC=2)

• 5 Native Hawaiian or other Pacific Islander only, Non-Hispanic Respondents who reported they are Native Hawaiian or Pacific Islander and not of Hispanic origin. (_MRACE1=5 and _HISPANC=2)

• 6 Other race only, nonHispanic Respondents who reported they are of some other race group not listed in the question responses and are not of Hispanic origin. (_MRACE1=6 and _HISPANC=2)

• 7 Multiracial, nonHispanic Respondents who reported they are of more than one race group and are not of Hispanic origin. (_MRACE1=7 and _HISPANC=2)

• 8 Hispanic Respondents who reported they are of Hispanic origin. ( _HISPANC=1)

• 9 Don’t know/ Not sure/ Refused Respondents who reported they did not know or refused to give their race and are not of Hispanic origin or did not know, or refused to answer if they are of Hispanic origin.

BMI.CAT:

• 1 Underweight Respondents classified as underweight based on body mass index. (_BMI5 < 18.50)

• 2 Normal Weight Respondents classified as normal weight based on body mass index. (18.50 <= _BMI5 < 25.00)

• 3 Overweight Respondents classified as overweight based on body mass index. (25.00 <= _BMI5 < 30.00)

• 4 Obese Respondents classified as obese based on body mass index. (30.00 <= _BMI5 < 99.99)

Smoker:

• 1 Current smoker - now smokes every day Respondents who reported having smoked at least 100 cigarettes in their lifetime and now smoke every day. (SMOKE100=1 and SMOKDAY2=1)

• 2 Current smoker - now smokes some days Respondents who reported having smoked at least 100 cigarettes in their lifetime and now smoke some days. (SMOKE100=1 and SMOKDAY2=2)

• 3 Former smoker Respondents who reported having smoked at least 100 cigarettes in their lifetime and currently do not smoke. (SMOKE100=1 and SMOKDAY2=3)

• 4 Never smoked Respondents who reported they had not smoked at least 100 cigarettes in their lifetime. (SMOKE100=2

• 9 Don’t know/ Refused/ Missing Respondents who reported they didn’t know if they had smoked 100 cigarettes in their lifetime, those who refused to answer if they had smoked 100 cigarettes in their lifetime, those who didn’t know if they now smoked every day, some days or not at all, those who refused to answer if they now smoked every day, some days or not at all, or those with missing responses. (SMOKE100=7, 9, missing; or SMOKDAY2=7, 9, missing)

Drinking:

• 0 No Drink-Occasions per day Respondents reported no occasions per day that they consumed alcohol. (ALCDAY5=888)

• 1 - 899 Drink-Occasions per day Respondents reported number of occasions per day that they consumed alcohol. (ALCDAY5 not equal to 777, 888, 999, or missing) 900 Don’t know/ Not Sure Or Refused/ Missing Respondents who reported they did not know how many days they had at least one drink of alcohol, those who refused to answer how many days they had at least one drink of alcohol, those with missing responses. (ALCDAY5=777, 999, or missing

Exercise:

• 1 Had physical activity or exercise Respondents who reported doing any physical activity or exercise. (EXERANY2=1)

• 2 No physical activity or exercise in last 30 days Respondents who reported doing no physical activity or exercise. (EXERANY2=2)

• 9 Don’t know/ Refused/ Missing Respondents who reported they didn’t know or refused to answer, and those with missing responses for the physical activity/exercise question. (EXERANY2=7, 9, missing) SAS Code: IF EXERANY2 IN (1) THEN _TOTINDA=1; ELSE IF EXERANY2 IN (2) THEN _TOTINDA=2; ELSE IF EXERANY2 IN (.,7,9) THEN _TOTINDA=9;

CornoaryHeartD:

• 1 Reported having MI or CHD Respondents who reported having had MI or CHD (CVDINFR4=1 OR CVDCRHD4=1)

• 2 Did not report having MI or CHD Respondents who reported not having had MI and CHD (CVDINFR4=2 AND CVDCRHD4=2)

. Not asked or Missing Respondents who reported they didn´t know, refused or had a missing value for the MI or CHD questions (CVDINFR4=7, 9 OR MISSING OR CVDCRHD4=7, 9, OR MISSING)

Filter out missing data

BRFSS2020 = BRFSS2020 %>%
  drop_na() %>%
  filter(Age.CAT !=14, # 14 = Don't know, Refused,Missing
         Smoker != 9, # 9 = Don't know, Refused, Missing
         Drinking != 900, # 900 = Don't know, Refused, Missing
         Exercise != 9) # 9 = Don't know, Refused, Missing

Change values of valuables that match with they are meanings

BRFSS2020 = BRFSS2020 %>%
  mutate(Exercise = case_when(Exercise == 2 ~ 1,
                              TRUE ~ 2),  # change to opposite sequence in Exercise.
         Smoker = case_when(Smoker == 1 ~ 4,
                            Smoker == 2 ~ 3,
                            Smoker == 3 ~ 2,
                             TRUE ~ 1),     # change to opposite sequence in Smoker
         CornoaryHeartD = case_when(CornoaryHeartD == 2 ~ 1,
                                    TRUE ~ 2)) # change to opposite sequence in CornoaryHeartD
BRFSS2020

Smoker:

• 4 Current smoker - now smokes every day Respondents who reported having smoked at least 100 cigarettes in their lifetime and now smoke every day. (SMOKE100=1 and SMOKDAY2=1)

• 3 Current smoker - now smokes some days Respondents who reported having smoked at least 100 cigarettes in their lifetime and now smoke some days. (SMOKE100=1 and SMOKDAY2=2)

• 2 Former smoker Respondents who reported having smoked at least 100 cigarettes in their lifetime and currently do not smoke. (SMOKE100=1 and SMOKDAY2=3)

• 1 Never smoked Respondents who reported they had not smoked at least 100 cigarettes in their lifetime.

summary(BRFSS2020)

##         SEQNO              Date             Sex           Age.CAT      
##  2020000297:    52   03172020:  1747   Min.   :1.000   Min.   : 1.000  
##  2020000946:    52   03122020:  1735   1st Qu.:1.000   1st Qu.: 5.000  
##  2020001059:    52   03162020:  1720   Median :2.000   Median : 8.000  
##  2020001159:    52   03112020:  1696   Mean   :1.525   Mean   : 7.563  
##  2020001679:    52   03182020:  1666   3rd Qu.:2.000   3rd Qu.:10.000  
##  2020000070:    51   11172020:  1639   Max.   :2.000   Max.   :13.000  
##  (Other)   :339022   (Other) :329130                                   
##     Race.CAT        Height.M       Weitht.KG        BMI.CAT          Smoker    
##  Min.   :1.000   Min.   : 91.0   Min.   : 2495   Min.   :1.000   Min.   :1.00  
##  1st Qu.:1.000   1st Qu.:163.0   1st Qu.: 6804   1st Qu.:2.000   1st Qu.:1.00  
##  Median :1.000   Median :170.0   Median : 7938   Median :3.000   Median :1.00  
##  Mean   :2.088   Mean   :170.3   Mean   : 8248   Mean   :2.985   Mean   :1.66  
##  3rd Qu.:1.000   3rd Qu.:178.0   3rd Qu.: 9299   3rd Qu.:4.000   3rd Qu.:2.00  
##  Max.   :9.000   Max.   :234.0   Max.   :29030   Max.   :4.000   Max.   :4.00  
##                                                                                
##     Drinking         Exercise     CornoaryHeartD 
##  Min.   :  0.00   Min.   :1.000   Min.   :1.000  
##  1st Qu.:  0.00   1st Qu.:2.000   1st Qu.:1.000  
##  Median :  3.00   Median :2.000   Median :1.000  
##  Mean   : 17.87   Mean   :1.768   Mean   :1.089  
##  3rd Qu.: 23.00   3rd Qu.:2.000   3rd Qu.:1.000  
##  Max.   :100.00   Max.   :2.000   Max.   :2.000  
## 

Plot data

ggplot(BRFSS2020) +
  aes(x = CornoaryHeartD, y = Smoker,fill = factor(BMI.CAT)) +
  geom_col(position = "fill")