A decision tree to predict four or more positive axillary lymph nodes in breast cancer patients with positive sentinel node biopsy: Determining necessity for regional nodal irradiation in the absence of axillary dissection

Abstract

e11540 Background: Regional nodal irradiation (RNI) is indicated for breast cancer patients with ≥ 4 positive axillary lymph nodes (ALN). The need for RNI is unclear for women with T1–2 tumors and 1–3 positive sentinel lymph nodes (SLN) who don’t undergo axillary lymph node dissection (ALND). In an effort to guide clinician decision-making and potentially spare patients combined toxicities of ALND and radiation, the purpose of this study was to create a decision tree of clinicopathologic variables to predict patients with ≥ 4 positive ALN. Methods: We reviewed the records of 197 women with T1–2 tumors and 1–3 positive SLN. All patients underwent a complete ALND to determine the number of positive ALN. The patients were divided into 2 groups: < 4 or ≥ 4 positive ALN. Ten clinicopathologic predictive variables were identified for analysis: patient age, size of tumor, histological type, tumor grade, number of metastatic SLN, largest SLN metastasis size, detection method, estrogen receptor, Ki67 and lymphovascular invasion (LVI). The analysis used Chi-Square Automatic Interaction Detection (CHAID SPSS), a non-parametric, stepwise “regression tree” analysis, with Bonferroni adjusted p-values to create a decision tree. Results: 141 (72%) patients had < 4 and 56 (28%) had ≥ 4 positive ALN. Three variables were selected into the CHAID tree based upon maximum predictability: LVI, the number of metastatic SLNs, and largest SLN metastasis size. 100% of patients (N=42) had < 4 positive ALN if negative for LVI and had only 1 positive SLN with a metastasis size < 0.2cm (p-value < 0.0432). For patients with LVI (N=77), 13 of 14 (93%) had < 4 positive ALN if the SLN metastasis size was ≤ 0.2cm (p < .0014). The highest prevalence of ≥ 4 positive ALN were patients with LVI and a SLN metastasis size > 0.2cm. Conclusions: The CHAID analysis more accurately predicted patients with < 4 positive ALN compared to those with ≥4. The decision tree provides a new tool for the clinician to determine the necessity for RNI without ALND. No significant financial relationships to disclose.