Kaplan-Meier curves and log-rank test
Describes the probability of staying event-free over time in each group, and compares groups with the log-rank test.
Clinical example
Time from surgery to relapse in two adjuvant treatment arms, where some patients are still relapse-free at the end of follow-up.
When to use it
- The outcome is the time until an event, and some patients have not had the event by the end of follow-up.
- You compare two or more groups.
- You don't need to adjust for other variables.
Assumptions to check
Non-informative censoring
Patients who are censored, for example lost to follow-up, should have the same future risk as patients who remain under observation.
What to report
- Kaplan-Meier curves with the number at risk under the plot
- Median time to event per group with 95% CI
- Median follow-up, estimated with the reverse Kaplan-Meier method
- The log-rank p-value
Common mistakes
Don't turn time-to-event into yes/no
Counting who had the event by the end ignores when it happened and how long each patient was followed.
Report follow-up properly
Report median follow-up, ideally with the reverse Kaplan-Meier method, and the number at risk under the curves.
Alternatives
| If your situation is… | Use |
|---|---|
| You need to adjust for other variables | Cox proportional hazards regression |
| A competing event is common | Competing risks: cumulative incidence and Fine-Gray |
In your software
# R
library(survival)
fit <- survfit(Surv(time_months, relapse) ~ arm, data = trial)
survdiff(Surv(time_months, relapse) ~ arm, data = trial)
KM time_months BY arm
/STATUS=relapse(1)
/PRINT TABLE MEAN
/PLOT SURVIVAL
/TEST LOGRANK.