Survival analysis in ggplot in R

Question

I coded the following (I used data=lung)

library(ggsurvfit)
library(ggplot2)

p <- survfit2(Surv(time, status)~sex, data=lung) 
ggsurvfit(p,
          type = "survival"
          ) 
          add_censor_mark() %>%
          add_confidence_interval() %>%
          add_risktable()

I have two problems:

R says there is an error: Error in match.arg(type) : 'arg' must be NULL or a character vector However I copied the code exactly as in the examples https://www.danieldsjoberg.com/ggsurvfit/reference/ggsurvfit.html

In the plot the confidence intervals and risk table are not shown. When I use the same dataset and variables but with another code and another package, the confidence intervals are displayed but the image appears to be distorted and the risk table is not shown and it is overlapping...

sfit <- survfit(Surv(day, death)~male, data=db)
 sfit
 summary(sfit)

 library(survminer)
 ggsurvplot(sfit)

 ggsurvplot(sfit, conf.int=TRUE, pval=TRUE, risk.table=TRUE, 
            legend.labs=c("Male", "Female"), legend.title="Sex",  
            palette=c("dodgerblue2", "orchid2"), 
            title="Kaplan-Meier Curve for Lung Cancer Survival", 
            risk.table.height=.15)

I would like to use the first code since as far as I know it can be more customizable, however other options are well accepted as well..

You used the wrong syntax for your first code. There is a missing `+` and intsead of the pipe `%>%` you have ot use a `+` too, i.e. do `ggsurvfit(...) + add_xxx() + add_yyy() + ...` — stefan, Mar 04 '23 at 20:33

score 2 · Accepted Answer · answered Mar 04 '23 at 20:34

2

You haven't copied the examples correctly. You need to use a + to add the components to the plot. You are using %>%, which doesn't make sense in this context.

library(survival)
library(ggplot2)
library(ggsurvfit)

p <- survfit2(Surv(time, status)~sex, data=lung) 

ggsurvfit(p, type = "survival") +
  add_censor_mark() +
  add_confidence_interval() +
  add_risktable()

^{Created on 2023-03-04 with reprex v2.0.2}

answered Mar 04 '23 at 20:34

Allan Cameron

147,086
7
49
87

Thank you! Do you know how I can change the dimensions ("zoom") of the plot? Because when I create a plot with too many variables it gets crop and I would like it to be reduced in dimensions so everything can fit – user19745561 Mar 04 '23 at 21:02
@user19745561 you can simply make the plotting window larger, which increases the space without increasing the text size etc – Allan Cameron Mar 04 '23 at 21:05

Survival analysis in ggplot in R

1 Answers1