Adding colors to cumulative incidence function and plot (ggcuminc) made by tidycmprsk

Question

So using the example dataset trial, I want to create a cumulative incidence function of two competing events and give them each a color. The example is not great since you might not need colors for it but in my dataset the two outcomes have a distinct CIF and coloring is useful.

#Load data
data("trial", package = "tidycmprsk")

#make plot
cuminc(Surv(ttdeath, death_cr) ~ 1, trial) %>%
  ggcuminc(outcome = c("death from cancer", "death other causes")) +
  add_confidence_interval() +
  add_risktable() +
  scale_ggsurvfit()

Output

Question

How to get two different colors for death from cancer and death from other causes? Tried to use this guide but couldn't find the answer.

Answer 1

Since this package is using ggplot, you could use ggplot_build to modify the layers of the plot and give them colors. You could add these by modifying both layers based on their group number like this:

library(tidycmprsk)
library(ggsurvfit)
library(dplyr)
data("trial", package = "tidycmprsk")

#make plot
p <- cuminc(Surv(ttdeath, death_cr) ~ 1, trial) %>%
  ggcuminc(outcome = c("death from cancer", "death other causes")) +
  add_confidence_interval() +
  add_risktable() +
  scale_ggsurvfit() 

q <- ggplot_build(p)

q$data[[1]] <- q$data[[1]] %>%
  mutate(colour = ifelse(group == 1, "red", "blue"))
q$data[[2]] <- q$data[[2]] %>%
  mutate(colour = ifelse(group == 1, "red", "blue"),
         fill = ifelse(group == 1, "red", "blue"))

q <- ggplot_gtable(q)
plot(q)

^{Created on 2023-11-06 with reprex v2.0.2}