Discordance in pleural mesothelioma response classification and modelling of impact on clinical trials.

INTRODUCTION: Agreement between radiologists regarding treatment response in Pleural Mesothelioma (PM) is acknowledged to be poor, but downstream effects in clinical trials have not been quantified. METHODS: We performed a mixed methods study, composed of a multicentre, retrospective cohort study and in silico modelling. CT images and data were retrieved from 4 UK centres regarding chemotherapy-treated patients. Expert radiologists classified response using modified Response Evaluation Criteria In Solid Tumours (mRECIST) v1.1, generating discordance rate (%) and agreement. In silico modelling simulated two-arm trials of an active therapy with intended 80% power and confidence intervals for four endpoints (objective response rate (ORR), disease control rate (DCR), progression-free survival (PFS), overall survival (OS)) covering 95% of the true effect. Actual power and endpoint coverage were modelled against mRECIST misclassification rate (a single reporter equivalent of discordance rate). Consecutive simulations varied misclassification rate from 0 to 100% in 1% increments, each repeated 10,000 times. RESULTS: 172 cases were included. Discordance rate was 35% (60/172), kappa = 0.456. In silico modelling demonstrated reduced power and endpoint precision with increasing misclassification. At 17% misclassification, corresponding to the observed 35% discordance, power dropped from 80% to 39% for ORR, 54% for DCR, 64% for PFS and 64% for OS, with endpoint coverage reduced to 85%, 90%, 92% and 92%, respectively. 50/60 (83%) discordances reflected interpretation or measurement differences intrinsic to mRECIST. Discordance was not associated with tumour volume. CONCLUSIONS: Inconsistent response classification is common in PM and substantially reduces statistical power and endpoint precision in clinical trials.