Tree-based model for breast cancer prognostication

Abstract

Purpose: To define prognostic groups for recurrence-free survival in breast cancer, assess relative effects of prognostic factors, and examine the influence of treatment variations on recurrence-free survival in patients with similar prognostic-factor profiles.

Patients and methods: We analyzed 1,055 patients diagnosed with stage I-III breast cancer between 1990 and 1996. Variables studied included socioeconomic factors, tumor characteristics, concurrent medical conditions, and treatment. The primary end point was recurrence-free survival (RFS). Multivariable analyses were performed using recursive partitioning and Cox proportional hazards regression.

Results: The most significant difference in prognosis was between patients with fewer than four and those with at least four positive nodes (P <.0001). Four distinct prognostic groups (5-year RFS, 97%, 78%, 58%, and 27%) were developed, defined by the number of positive nodes, tumor size, progesterone receptor (PR) status, differentiation, race, and marital status. Patients with fewer than four positive nodes and tumor < or = 2 cm, PR positive, and well or moderately differentiated had the best prognosis. RFS in this group was unaffected by type of adjuvant therapy (P =.38). Patients with at least four positive nodes and PR-negative tumors had the worst prognosis, and those treated with tamoxifen plus chemotherapy had the best outcome in this group (P =.0001). Among patients in the two intermediate-risk groups, those treated with tamoxifen or a combination of tamoxifen and chemotherapy had the best outcome.

Conclusion: Lymph node status, PR status, tumor size, differentiation, race, and marital status are valuable for prognostication in breast cancer. The prognostic groups derived can provide guidance for clinical trial design, patient management, and future treatment policy.