A Kaplan-Meier curve is a statistical graph used to estimate the survival function over time, often in medical research. It shows the proportion of subjects surviving or remaining event-free over a period, while accounting for censored data (such as participants lost to follow-up or who haven’t yet experienced the event). Research papers often abbreviate the Kaplan-Meier curve as KM curve.
Kaplan-Meier curves are frequently used alongside statistical tests like the log-rank test to compare survival between groups. They are also closely related to the hazard ratio (HR), which compares the relative risk of the event occurring at any point in time between two groups. A hazard ratio is the ratio of the two groups’ hazard rates, which are reflected by the slopes of the KM curves—the steeper the slope, the higher the event rate. In essence, the HR provides a single number that summarizes the magnitude of the difference between two Kaplan-Meier curves across the entire follow-up period.
For example, in a clinical trial comparing two cancer treatments, researchers might use Kaplan-Meier curves to plot the percentage of patients surviving over time. By visually comparing the curves, they can assess differences in outcomes. If one curve drops steeply while the other declines more gradually, it suggests that patients in the steeper group are experiencing events (such as death or relapse) more quickly, indicating a higher risk.
