Recursive partitioning analysis of lymph node ratio in breast cancer patients.

Lymph node ratio (LNR) is a powerful prognostic factor for breast cancer. We conducted a recursive partitioning analysis (RPA) of the LNR to identify the prognostic risk groups in breast cancer patients. Records of newly diagnosed breast cancer patients between 2002 and 2006 were searched in the Taiwan Cancer Database. The end of follow-up was December 31, 2009. We excluded patients with distant metastases, inflammatory breast cancer, survival <1 month, no mastectomy, or missing lymph node status. Primary outcome was 5-year overall survival (OS). For univariate significant predictors, RPA were used to determine the risk groups. Among the 11,349 eligible patients, we identified 4 prognostic factors (including LNR) for survival, resulting in 8 terminal nodes. The LNR cutoffs were 0.038, 0.259, and 0.738, which divided LNR into 4 categories: very low (LNR ≤ 0.038), low (0.038 < LNR ≤ 0.259), moderate (0.259 < LNR ≤ 0.738), and high (0.738 < LNR). Then, 4 risk groups were determined as follows: Class 1 (very low risk, 8,265 patients), Class 2 (low risk, 1,901 patients), Class 3 (moderate risk, 274 patients), and Class 4 (high risk, 900 patients). The 5-year OS for Class 1, 2, 3, and 4 were 93.2%, 83.1%, 72.3%, and 56.9%, respectively (P< 0.001). The hazard ratio of death was 2.70, 4.52, and 8.59 (95% confidence interval 2.32-3.13, 3.49-5.86, and 7.48-9.88, respectively) times for Class 2, 3, and 4 compared with Class 1 (P < 0.001). In conclusion, we identified the optimal cutoff LNR values based on RPA and determined the related risk groups, which successfully predict 5-year OS in breast cancer patients.