ggsurvplot:: Placing risk table inside survival curves

[kassambara]

How to place risk table inside survival curves?

[MarcinKosinski]

Maybe stacked barplot on X axis with additional legend on a right (2 legends :P)?

[kassambara]

Good idea!!

[Sterniii3]

How can I place the risk table inside the plot of the survival curves? Is it possible? If so, I can't find how to do it.
Thanks!

[kassambara]

This is not yet possible. We'll work on it:-)!

[kassambara]

A first attempt of placing risk.table inside survival curves:

library(survival)
library(survminer)

fit<- survfit(Surv(time, status) ~ sex, data = lung)
p<-ggsurvplot(fit, data = lung, risk.table = TRUE, risk.table.col = "strata")

# Create a transparent theme object
transparent_theme <- theme(
  axis.title.x = element_blank(),
  axis.title.y = element_blank(),
  axis.text.x = element_blank(),
  axis.text.y = element_blank(),
  axis.ticks = element_blank(),
  panel.grid = element_blank(),
  axis.line = element_blank(),
  panel.background = element_rect(fill = "transparent",colour = NA),
  plot.background = element_rect(fill = "transparent",colour = NA),
  plot.margin=unit(c(0,0,0,0),"mm"),)

p1 <- p$plot
p2 <- p$table + transparent_theme

# Create the external graphical elements
# called a "grop" in Grid terminology
p2_grob = ggplotGrob(p2)
p1 + annotation_custom(grob = p2_grob, xmin = -50, 
                       ymin = 0, ymax = 0.25)

I'm not sure that this is good idea...

[MarcinKosinski]

It's always just an option : )
Maybe some users will find it useful (for plots with estimates above 50%).

I would go even further and try placing the legend inside the plot oO

[kassambara]

I think that for legend, the job is done using the argument `legend'

ggsurvplot(fit, data = lung, risk.table = TRUE, risk.table.col = "strata", 
          legend = c(0.2, 0.2))

[kassambara]

Optimal code to be added

# Fit survival curves
library(survival)
fit <- survfit( Surv(time, status) ~ rx + adhere, data = colon )

library(survminer)
p <- ggsurvplot(fit, data = lung, risk.table = TRUE, risk.table.col = "strata")

# Create a transparent theme object
transparent_theme <- theme(
  title = element_blank(),
  axis.title.x = element_blank(),
  axis.title.y = element_blank(),
  axis.text.x = element_blank(),
  axis.text.y = element_blank(),
  axis.ticks = element_blank(),
  panel.grid = element_blank(),
  axis.line = element_blank(),
  panel.background = element_rect(fill = "transparent",colour = NA),
  plot.background = element_rect(fill = "transparent",colour = NA),
  plot.margin=unit(c(0,0,0,0),"mm"),
  panel.border = element_blank(),
  legend.position = "none")

p1 <- p$plot
p2 <- p$table + transparent_theme

# Create the external graphical elements
# called a "grop" in Grid terminology
nstrata = 6
ymax <- nstrata*0.05
p2_grob = ggplotGrob(p2)
p1 + annotation_custom(grob = p2_grob, xmin = -max(fit$time)/20, 
                       ymin = -0.05, ymax = ymax)

[kassambara]

option to add table tick labels on the right side

[kassambara]

New argument risk.table.pos in ggsurvplot() for placing risk table inside survival curves. Allowed options are one of c("out", "in") indicating 'outside' or 'inside' the main plot, respectively. Default value is "out".

library(survival)
fit <- survfit( Surv(time, status) ~ rx + adhere, data = colon )

library(survminer)
ggsurvplot(fit, data = colon, 
           legend = "right",
           pval = TRUE, pval.coord = c(500, 0.4),
           risk.table = TRUE, risk.table.y.text = FALSE,
           risk.table.pos = "in")

[awcm0n]

I like the option to put the risk table inside, but how can I get the table title back?