02_demographic-preprocess.Rmd

---
title: "Demographic Pre-processing"
author: "Meg Hutch"
date: "2022-11-09"
output: html_document
---

Pre-process demographic table for use in downstream demographic figure (Figure 2).

```{r message=FALSE, warning=FALSE}
library(tidyverse)
source("R/demo_tables.R")
source("R/utils.R")
```

## **Import Data from each Healthcare System**

```{r message=FALSE, warning=FALSE}
# read in files from results folder 
# this folder contains all of the local healthcare system level analyses
rdas <- list.files(
  path = "results",
  pattern = ".rda",
  full.names = TRUE
)
for (rda in rdas) {
  load(rda)
}

rm(rdas, rda)

# create a list of participating healthcare systems from our study tracking spreadsheet
site_google_url <- "https://docs.google.com/spreadsheets/d/1epcYNd_0jCUMktOHf8mz5v651zy1JALD6PgzobrGWDY/edit?usp=sharing"

# load site parameters
site_params <- googlesheets4::read_sheet(site_google_url, sheet = 1)
site_avails <- googlesheets4::read_sheet(site_google_url, sheet = 2)

# filter the list of sites who ran the analysis
sorted_sites <- site_avails %>%
  filter(!is.na(date_v4_received)) %>%
  pull(siteid) %>%
  paste("results", sep = "_")

# list sites without race
sites_wo_race <- site_params %>%
  filter(!include_race) %>%
  pull(siteid)

# combine all rda files with 'results' in name
results <- mget(ls(pattern = "results"))
```

### **Abstract adult & pediatric tables from each healthcare system**

```{r}
# load in previously generated patient count table by site
pt_counts <- read.csv('tables/site_pt_counts.csv')

# create list of hospitals for adult and pediatric analyses
adult_sites <- pt_counts %>% 
  filter(population == "Adult") %>% 
  pull(site) 

pediatric_sites <- pt_counts %>% 
  filter(population == "Pediatric") %>% 
  pull(site) 

# create demographics table
demo_table_adult <- create_demo_tableone(sorted_sites = adult_sites, is_pediatric = FALSE)

demo_table_pediatric <- create_demo_tableone(sorted_sites = pediatric_sites, is_pediatric = TRUE)
```

### **Combine adult and pediatric tables**

```{r}
demo_table_combine  <- rbind(demo_table_adult, demo_table_pediatric) %>% 
  select(site, variable, Demo_var, contains('n_var')) %>% 
  pivot_longer(., cols = c(contains('n_var'))) %>% 
  group_by(site, variable, Demo_var, name) %>% 
  mutate(total_variable = sum(value, na.rm = TRUE)) %>% 
  group_by(site, Demo_var, name) %>% 
  mutate(total_demo_var = sum(value, na.rm = TRUE))  %>% 
  ungroup() %>% 
  select(-Demo_var, -value) %>% 
  distinct()

demo_table_site <- demo_table_combine %>% 
  pivot_wider(., id_cols = c("site", "variable"),  
              names_from = "name", 
              values_from = c("total_variable", "total_demo_var")) %>% 
  mutate(NNC_perc = round(total_variable_n_var_None / total_demo_var_n_var_None * 100,1),
         CNS_perc = round(total_variable_n_var_Central / total_demo_var_n_var_Central * 100,1),
         PNS_perc = round(total_variable_n_var_Peripheral / total_demo_var_n_var_Peripheral * 100,1)) %>% 
  rename(NNC_n = 'total_variable_n_var_None',
         CNS_n = 'total_variable_n_var_Central',
         PNS_n = 'total_variable_n_var_Peripheral') %>% 
  select(site, variable, NNC_n, CNS_n, PNS_n, NNC_perc, CNS_perc, PNS_perc) %>% 
  mutate(NNC = paste0(NNC_n, " (", NNC_perc, "%)"),
         CNS = paste0(CNS_n, " (", CNS_perc, "%)"),
         PNS = paste0(PNS_n, " (", PNS_perc, "%)"))
```

**Save patient demographic data**

```{r}
save(demo_table_site, file = 'demographic-figure/demographic-data/demo_table_site.rda')
```