```{r setup, echo= FALSE, message=FALSE,warning= FALSE}
# Strings ain't factors
options(stringsAsFactors = FALSE)
# Load the required libraries
library(knitr)
library(dplyr)
library(ggplot2)
library(RColorBrewer)
# Set the default ggplot theme
theme_set(theme_bw())
# Set default chunk options
opts_chunk$set(echo = FALSE,
results = 'asis',
message = FALSE,
warning = FALSE,
error = TRUE)
# Read in the table
tbstats_raw <- read.delim("cdc_otis_extract.txt")
tbstats <- tbstats_raw %>%
filter(Notes == "") %>%
mutate(per.complete = as.numeric(gsub(x = Percent.of.Completion.of.Therapy.Within.One.Year.Among.Those.Eligible,
pattern = "%|Not Applicable",
replacement = ""))) %>%
select(-matches("Notes"), -ends_with(".Code"))
```
# Reported Active Tuberculosis Cases in the United States: 1993-2013
## Reported Active TB Cases in the United States, 1993-2013
```{r nation}
tbstats %>%
group_by(Year) %>%
summarise(n_cases = sum(Count)) %>%
ggplot(aes(x = Year, y = n_cases)) +
geom_line(size = 2) +
labs(x = "Year Reported",
y = "Number of Cases",
title = "Reported Active TB Cases in the United States") +
expand_limits(y = 0)
```
## Reported Active TB Cases by State
```{r cases}
top_five <-
tbstats %>%
filter(Year == 1993) %>%
arrange(desc(Count)) %>%
slice(1:5) %>%
select(State)
tbstats$top_five_state <- factor(tbstats$State, levels = c(top_five$State, "Other"))
tbstats$top_five_state[is.na(tbstats$top_five_state)] <- "Other"
tbstats %>%
group_by(Year, State) %>%
summarise(n_cases = sum(Count),
top_five_state = unique(top_five_state)) %>%
ggplot(aes(x = Year, y = n_cases, group = State)) +
geom_line(aes(color = top_five_state, size = top_five_state)) +
scale_size_manual(values = c(rep(2, 5), 0.5)) +
scale_color_manual(values = c(brewer.pal(n = 5, "Paired"), "grey")) +
labs(x = "Year Reported",
y = "Number of Cases",
color = "State",
title = "Reported Active TB Cases in the United States") +
expand_limits(y = 0)
```
## Treatment Completion Within One Year for Eligible US TB Cases
```{r tx_completion}
tbstats %>%
group_by(Year) %>%
summarise(tx_completion = weighted.mean(per.complete, w = Count)) %>%
ggplot(aes(x = Year, y = tx_completion)) +
geom_line(size = 2) +
expand_limits(y = 0) +
labs(x = "Year Reported",
y = "Percent of Cases Completed",
title = "Completion of Treatment within One Year for Eligible Cases")
```
Data downloaded from the [CDC WONDER query tool](http://wonder.cdc.gov/tb.html).