Overtreatment in Hormone Receptor Positive, HER2-, Axillary Node Negative, Non-Metastatic Early Breast Cancer

Abstract

HR+ HER2- T1 N0 M0 breast cancer has very low 5-year postoperative risk of relapse (<5%) with current SoC treat- ment regimens: endocrine monotherapy or chemoendocrine com- bination therapy. Minimally aggressive treatment is ideal. Absent gene-profiling, histopathological features of the tumor are examined to predict risk of relapse. This paper establishes statistical evidence for use of an empirical prognostic index as a risk-based clinical decision aid where gene profiles are unavailable. Methods: A retrospective cohort (n=965) observed for 5 years was propensity score (PS) matched to correct baseline risk differences between chemoendocrine therapy and endocrine monotherapy treatment groups. PS were generated from logistic regression of pertinent histopathological covariates available to a clinician at the time of diagnosis onto treatment designation. Comparator groups were fur- ther equilibrated using Synthetic Minority Over-Sampling (SMOTE). Estimated treatment effects were assessed after propensity score- matching (PSM) and after SMOTE-normalized re-sampling. Results: Propensity score-matched groups (n=262) showed no difference in relapse rates between groups. Significant differences in histopatho- logical covariates remained between groups after PSM. SMOTE further minimized inter-group differences. Corresponding propen- sity score quartiles of the SMOTE groups (n=1000) were tested for proportional differences in relapse. No proportional differences in relapses were observed between groups in Q1-Q3. Proportionally, significantly more relapses occurred in the Q4 endocrine therapy group than in the Q4 chemoendocrine group. Conclusion: After matching, the PSM sample failed to produce generalizable results due to significant group imbalance for multiple predictor variables, whereas SMOTE re-sampling provided adequately risk-matched groups (standardized differences<0.2) for treatment effect anal- ysis. Individuals with HR+ HER2- T1 N0 M0 breast cancer are over-treated if they have PS<0.75, and are prescribed chemoen- docrine therapy, as no additional benefit was observed from this more aggressive treatment regimen. Conversely, individuals are under-treated, and at a significantly higher risk of relapse, if they have PS>0.75 and are not prescribed chemotherapy