Setting the standard: empirical benchmarks for case-level site-central discordance in radiographic endpoints in oncology clinical trials.

Publication date: Oct 01, 2026

Progression-free survival and objective response rate assessed per Response Evaluation Criteria in Solid Tumors, version 1. 1 (RECIST v1. 1), are based on serial radiographic assessments of tumor burden. We quantified case-level discordance between investigator and blinded independent central review (BICR)-determined progressive disease (PD) and objective response (OR) to provide benchmarks that can help clinical study teams judge whether observed discordance rates are expected or a data quality concern. We performed a pooled analysis of 39 phase 2 and 3 solid-tumor trials of pembrolizumab-based regimens in which radiographic images were reviewed by investigators and BICR and RECIST v1. 1 was used to assess response. Case-level discordance of PD, confirmed OR, and unconfirmed OR were calculated from 2cD72 tables. Case-level discordance was 17. 7% (95% CI 17. 2-18. 2) for PD (n = 20,908), 12. 2% (11. 8-12. 7) for confirmed OR (n = 21,520), and 14. 7% (14. 1-15. 3) for unconfirmed OR (n = 15,209). Discordance varied by cancer type, ranging from 11. 8% (melanoma) to 22. 8% (hepatocellular carcinoma [HCC]) for PD, from 5. 4% (HCC) to 20. 0% (cervical cancer) for confirmed OR, and from 6. 3% (HCC) to 19. 7% (cervical cancer) for unconfirmed OR. Trials with real-time verification of progression showed lower PD discordance than those without (17. 3% [95% CI 16. 7-17. 8] vs 20. 2% [18. 8-21. 7]). PD discordance was similar in double-blind and open-label trials (17. 6% [95% CI 16. 9-18. 3] vs 17. 8% [17. 0-18. 6]). Confirmed OR discordance was more common in double-blind trials (13. 3% [12. 7-13. 9] vs 10. 9% [10. 3-11. 6]). This analysis of trials of pembrolizumab-based regimens addresses a critical gap in oncology trial methodology by establishing empirical benchmarks for site-central discordance of RECIST v1. 1 response assessment, enabling study teams to distinguish expected variability from potential data quality signals. While the underlying sources of discordance characterized here are not specific to immunotherapy, the reported magnitude of discordance should be applied cautiously to trials of non-immunotherapy agents.

Semantics

Original Article