Neoadjuvant or concurrent atezolizumab with chemoradiation for locally advanced cervical cancer: a randomized phase I trial

Abstract

Combined immune checkpoint blockade (ICB) and chemoradiation (CRT) is approved in patients with locally advanced cervical cancer (LACC) but optimal sequencing of CRT and ICB is unknown. NRG-GY017 (NCT03738228) was a randomized phase I trial of atezolizumab (anti-PD-L1) neoadjuvant and concurrent with CRT (Arm A) vs. concurrent with CRT (Arm B) in patients with high-risk node-positive LACC. The primary endpoint was the fraction of expanded tumor-associated T-cell receptor (TCR) clones in blood at day 21 as a surrogate measure of anti-tumor immune response. Secondary objectives were safety and feasibility, 2-year disease-free survival (DFS), and predictive value of PD-L1 expression. Forty patients were randomized, 36 received treatment, and 25 were evaluable for the primary endpoint. After cycle 1, there was peripheral expansion of higher proportion of tumor-associated TCR clones in Arm A than in Arm B (p = 0.0025) that remained higher at day 21, meeting the pre-specified endpoint on two-sample T-test (p = 0.052), but not on sensitivity analysis by Wilcoxon test (p = 0.13). At the median follow up of 25.8 months, 2-year DFS was 76% in Arm A and 56% in Arm B (p = 0.28). There were no new safety signals. In conclusion, neoadjuvant ICB prior to CRT was safe and was associated with immunologically and clinically favorable outcomes, warranting larger confirmatory studies.

Fig. 1. Consort diagram and study schema.

A Consort diagram of the randomized trial participants and treatment disposition. B Study schema with the Arm A and Arm B treatment, imaging, and biospecimen collection timepoints. Created in BioRender. Zamarin, D. (2022) BioRender.com/g30o610.

Fig. 2. Clinical outcomes.

A Kaplan–Meier curve for disease-free survival by treatment. B Treatment effect in day-28 tumor tissue, 2-sided by Fisher exact test.

Fig. 3. Evolution of T cell repertoire parameters over the course of treatment.

A Schematic of definitions of TCR repertoires in tumors (right) and peripheral blood (left), image created with BioRender. B Scatter plot from a representative patient demonstrating expansion and contraction from baseline to post-treatment. Each clone was tested for significant expansion using a binomial test after correcting for the control false discovery rate (FDR) at 0.01. C Total TCR clonal expansion at day 21. D Total TCR clonal expansion at completion of cycle 1. E Fraction of TCR clones that expanded at the end of cycle 1 of therapy and were found to be tumor-associated. F Fraction of TCR clones that expanded at day 21 and were found to be tumor-associated. C–E Comparisons were performed using a two-sided Wilcoxon matched-pairs signed rank test. F Two-sided unpaired Students T tests were used for comparisons at a 10% significance level, pre-specified for the primary endpoint. G Change in tumor-associated TCR clonal percentages from cycle 1 to cycle 2 of therapy in Arm A (C–D) Arm A n = 17, Arm B n = 13. E–F Arm A n = 14, Arm B n = 11. G Arm A n = 13. Each data point represents an individual patient with an individual measurement for the specified time point. There were no adjustments for multiple comparisons. Source data are provided as a Source Data file. Image in 3 A created in BioRender. Zamarin, D. (2024) BioRender.com/u23c225.