Clustering Cancer Data by Areas between Survival Curves

We propose a hierarchical clustering method for prognostic clustering of cancer patients. Dissimilarity between two subsets of patients is defined as the area between two corresponding Kaplan-Meier curves. The proposed method is applied to the breast cancer data from the Surveillance, Epidemiology, and End Results (SEER) Program of the National Cancer Institute and compared with the linkage approach. The proposed method is convenient to use and can generate dendrograms compatible with those from the linkage approach.