Abstract Purpose: Individualized selection of patients with early-stage hormone receptor–positive (HR+) breast cancer for extended endocrine therapy (EET) is required to balance modest gains in outcome with toxicities of prolonged use. This study examined the Breast Cancer Index [BCI; HOXB13/IL17BR ratio (H/I)] as a predictive biomarker of EET benefit in patients from the Investigation on the Duration of Extended Adjuvant Letrozole trial. Experimental Design: BCI was tested in primary tumor specimens from 908 patients randomized to receive 2.5 versus 5 years of extended letrozole. The primary endpoint was recurrence-free interval. Cox models and likelihood ratios tested the interaction between EET and BCI (H/I). Results: BCI (H/I)-high significantly predicted benefit from extended letrozole in the overall cohort [HR 0.42; 95% confidence interval (CI), 0.21–0.84; P = 0.011] and any aromatase inhibitor subset [HR 0.34; 95% CI, 0.16–0.73; P = 0.004), whereas BCI (H/I)-low patients did not derive significant benefit (HR 0.95; 95% CI, 0.58–1.56; P = 0.84 and HR 0.90; 95% CI, 0.53–1.55; P = 0.71, respectively) treatment to biomarker interaction was significant (P = 0.045, P = 0.025, respectively). BCI identified approximately 50% of patients with clinically high-risk disease that did not benefit, and with clinically low-risk disease that derived significant benefit, from an additional 2.5 years of EET. Conclusions: BCI (H/I) predicted preferential benefit from 5 versus 2.5 years of EET and identified patients with improved outcomes from completing 10 years of adjuvant endocrine therapy. Findings expand the clinical utility of BCI (H/I) to a broader range of patients and beyond prognostic risk factors as a predictive endocrine response biomarker for early-stage HR+ breast cancer.