n2012.Rmd

---
title: "n2012"
output:
  word_document: default
  html_document:
    df_print: paged
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```


```{r}
library(haven);library(tidyverse);library(survey)
```

```{r}
df <- read_csv("H:/cabg_pci/n2012mod.csv")
```

Now, prior to further analysis, remove the variables that are not needed in this study. 
Also:

1. Keep only primary surgery; remove patients with prior CABG 
2. Remove patients with concomitant valve surgery

```{r}

n12 <- df

pricabg <- as.character(c("V4581")) # prior MI 

a <- pricabg

n12$pricabg <- with(n12, ifelse((DX1 %in% a | DX2 %in% a | DX3 %in% a | DX4 %in% a | DX4 %in% a | DX5 %in% a | DX6 %in% a | DX7 %in% a | DX8 %in% a | DX10 %in% a | DX11 %in% a | DX12 %in% a | DX13 %in% a | DX14 %in% a | DX15 %in% a ), "yes","no"))

n12 %>% count(pricabg)
```


Remove patients with prior CABG:

```{r remove prior CABG patients}
df2 <- n12 %>% filter(pricabg == "no")
dim(df2) # df2 contains only patients with primary CABG surgery and no prior CABG surgery.
```

```{r remove patients undergoing concomitant valve surgery}

# valve replacement/ valve repair 



valve <- as.character(c('3511','3512','3513','3514','3521','3522','3523','3524','3526','3525','3527',
'3528'))

a <- valve

df2$valve <- with(df2, ifelse((PR1 %in% a | PR2 %in% a | PR3 %in% a | PR4 %in% a | PR4 %in% a | PR5 %in% a | PR6 %in% a | PR7 %in% a | PR8 %in% a | PR10 %in% a | PR11 %in% a | PR12 %in% a | PR13 %in% a | PR14 %in% a | PR15 %in% a), "yes","no"))

df2 %>% count(valve)

```



```{r remove valve patients too}

df3 <- df2 %>% filter(valve == "no")
dim(df3)
```


1. Keep only patients who underwent CABG; remove patients with underwent PCI:

```{r remove PCI patients}

df4 <- df3 %>% filter(cabg == 1)

```

```{r change name of df to get more variables}

n12 <- df4

```

```{r prior conditions}

priormi <- as.character(c("412")) # prior MI 

a <- priormi

n12$priormi <- with(n12, ifelse((DX1 %in% a | DX2 %in% a | DX3 %in% a | DX4 %in% a | DX4 %in% a | DX5 %in% a | DX6 %in% a | DX7 %in% a | DX8 %in% a | DX10 %in% a | DX11 %in% a | DX12 %in% a | DX13 %in% a | DX14 %in% a | DX15 %in% a ), "yes","no"))

n12 %>% count(priormi)

```

```{r}
 
priorpci <- as.character(c("V4582")) # prior PCI 

a <- priorpci

n12$priorpci <- with(n12, ifelse((DX1 %in% a | DX2 %in% a | DX3 %in% a | DX4 %in% a | DX4 %in% a | DX5 %in% a | DX6 %in% a | DX7 %in% a | DX8 %in% a | DX10 %in% a | DX11 %in% a | DX12 %in% a | DX13 %in% a | DX14 %in% a | DX15 %in% a), "yes","no"))

n12 %>% count(priorpci)

```


```{r}
chf <- as.character('4280','4281','4282','4283','4284','4285','4286','4287','4288') # ICD9 codes for CHF

a <- chf

n12$chf <- with(n12, ifelse((DX1 %in% a | DX2 %in% a | DX3 %in% a | DX4 %in% a | DX4 %in% a | DX5 %in% a | DX6 %in% a | DX7 %in% a | DX8 %in% a | DX10 %in% a | DX11 %in% a | DX12 %in% a | DX13 %in% a | DX14 %in% a | DX15 %in% a), "yes","no"))

n12 %>% count(chf)
```


```{r}

shock <- as.character(c("78551")) # prior CABG 

a <- shock

n12$shock <- with(n12, ifelse((DX1 %in% a | DX2 %in% a | DX3 %in% a | DX4 %in% a | DX4 %in% a | DX5 %in% a | DX6 %in% a | DX7 %in% a | DX8 %in% a | DX10 %in% a | DX11 %in% a | DX12 %in% a | DX13 %in% a | DX14 %in% a | DX15 %in% a ), "yes","no"))

n12 %>% count(shock)
```

```{r}

stemi <- as.character(c("41071")) # prior CABG 

a <- stemi

n12$stemi <- with(n12, ifelse((DX1 %in% a | DX2 %in% a | DX3 %in% a | DX4 %in% a | DX4 %in% a | DX5 %in% a | DX6 %in% a | DX7 %in% a | DX8 %in% a | DX10 %in% a | DX11 %in% a | DX12 %in% a | DX13 %in% a | DX14 %in% a | DX15 %in% a ), "yes","no"))



n12 %>% count(stemi)

```

```{r change df name to get more variables }
df <- n12
```


```{r carotid disease}
carotid.d <- as.character(c("43310")) # carotid artery disease

a <- carotid.d

df$carotid <- with(df, ifelse((DX1 %in% a | DX2 %in% a | DX3 %in% a | DX4 %in% a | DX4 %in% a | DX5 %in% a | DX6 %in% a | DX7 %in% a | DX8 %in% a | DX10 %in% a | DX11 %in% a | DX12 %in% a | DX13 %in% a | DX14 %in% a | DX15 %in% a), "yes","no"))

table(df$carotid)
```

```{r}

pristroke <- as.character(c("V1254","4380")) # prior stroke

a <- pristroke

df$pristroke <- with(df, ifelse((DX1 %in% a | DX2 %in% a | DX3 %in% a | DX4 %in% a | DX4 %in% a | DX5 %in% a | DX6 %in% a | DX7 %in% a | DX8 %in% a | DX10 %in% a | DX11 %in% a | DX12 %in% a | DX13 %in% a | DX14 %in% a | DX15 %in% a ), "yes","no"))


table(df$pristroke)
```

```{r}
priicd <- as.character(c("V4502")) # prior ICD implant 

a <- priicd

df$priicd <- with(df, ifelse((DX1 %in% a | DX2 %in% a | DX3 %in% a | DX4 %in% a | DX4 %in% a | DX5 %in% a | DX6 %in% a | DX7 %in% a | DX8 %in% a | DX10 %in% a | DX11 %in% a | DX12 %in% a | DX13 %in% a | DX14 %in% a | DX15 %in% a ), "yes","no"))

table(df$priicd)
```


```{r}
dementia <- as.character(c("2900","2941","2942","2948","3310","3311","3312","33182")) # dementia 

a <- dementia

df$dementia <- with(df, ifelse((DX1 %in% a | DX2 %in% a | DX3 %in% a | DX4 %in% a | DX4 %in% a | DX5 %in% a | DX6 %in% a | DX7 %in% a | DX8 %in% a | DX10 %in% a | DX11 %in% a | DX12 %in% a | DX13 %in% a | DX14 %in% a | DX15 %in% a ), "yes","no"))

table(df$dementia)

```

```{r get var for n09 and convert them to lower case}

n12 <- df

names(n12)

names(n12) <- tolower(names(n12))

names(n12)
```


```{r getting the severity file and hospital files into the document}

sev <- read_spss("H:/NIS_2012_Severity.sav")

names(sev) <- tolower(names(sev))

names(sev)

sev2 <- sev %>% dplyr::select(hosp_nis, key_nis, cm_aids:cm_wghtloss)

names(sev2)
```

```{r merge with df and sev}

df2 <- left_join(n12, sev2, by = "key_nis")
names(df2)

```

1. Now we need to get the hospital information into the df:

```{r get hospital df}

hosp <- read_spss("H:/NIS_2012_Hospital.sav")

names(hosp) <- tolower(names(hosp))

names(hosp)


```

```{r merge both df together}

df2$hosp_nis <- df2$hosp_nis.x

df2$hosp_nis <- as.numeric(df2$hosp_nis)
hosp$hosp_nis <- as.numeric(hosp$hosp_nis)

df3 <- left_join(df2, hosp, by = "hosp_nis")
dim(df3)

```


```{r save df for now}

write_csv(df3, "H:/bita_nis/df2012.csv")

```

```{r}


m1 <- df3 %>% dplyr::select(age,  died, discwt.x, dispuniform,  drg, dx1, 
dx2, dx3, dx4, dx5, dx6, dx7, dx8, dx9, dx10,
dx11, dx12, dx13, dx14, dx15, female, key_nis, los, nis_stratum.x, 
pay1,   pr1, pr2, 
pr3, pr4, pr5, pr6, pr7, pr8, pr9,pr10, pr11, 
pr12, pr13, pr14, pr15,  race, totchg, 
 year.x,  cabg, 
pci, bita,  pricabg, valve, priormi, priorpci, 
chf, shock, stemi, cm_aids, cm_alcohol, 
cm_anemdef, cm_arth, cm_bldloss, cm_chf, cm_chrnlung, 
cm_coag, cm_depress, cm_dm, cm_dmcx, cm_drug, cm_htn_c, 
cm_hypothy, cm_liver, cm_lymph, cm_lytes, cm_mets, 
cm_neuro, cm_obese, cm_para, cm_perivasc, cm_psych, 
cm_pulmcirc, cm_renlfail, cm_tumor, cm_ulcer, cm_valve, 
cm_wghtloss, hosp_nis,  discwt.y, 
hosp_bedsize, hosp_locteach,  
hosp_region,  nis_stratum.y, year.y)

names(m1)
```


```{r write df to folder}

write_csv(m1, "H:/bita_nis/df/m2012.csv")

```