Exploratory analyses of surrogate endpoints in metastatic non-small cell lung cancer

Introduction Context: Metastatic lung cancer accounts for 40-50% of diagnosed lung cancers, and has a great lethality, with 4% 5-year net survival. Treatment has been recently modified due to the development of immunotherapy. In order to obtain faster results and to overcome the limitations associated with the use of overall survival (OS), the search for surrogate endpoints (SE) has become an area of research. Using the real-life database ESME-AMLC ( NCT03848052 ), we investigated two candidate surrogate endpoints for OS: progression-free survival (PFS) and time to next treatment (TNT) for patients treated with first-line chemotherapy and/or immunotherapy. Methods This is an exploratory analysis assessing investigating surrogate properties for OS of PFS and TNT in patients diagnosed with metastatic non-small cell lung cancer (NSCLC). Using real world data, we estimated the individual-level association between PFS/TNT and OS as well as the center-level association between treatment effect on PFS/TNT and treatment effect on OS. This observational, retrospective and multi-center study uses data from patients treated since 2015 in French cancer care centers for metastatic NSCLC, with first-line chemotherapy and/or immunotherapy. Baseline was the administration of the first treatment. PFS was defined as the time until first progression of disease or death, TNT as the time until initiation of a second line of treatment or death, and OS as the time until death. Associations between OS and surrogate endpoints were estimated at the individual and center level with a meta-analytical approach. A joint frailty model was used with an individual random effect or with copula functions. Estimated parameters were found using penalized likelihood and baseline hazard functions were approximated using splines functions. Effectiveness of models was assessed with predictions using leave-one-out cross validation. Results The study population included 5294 patients: 5055 patients treated with chemotherapy alone, and 239 patients treated with immunotherapy alone or in association with chemotherapy. Median OS was 13 months, and median PFS and TNT were 4 months. These estimates were higher for patients treated with immunotherapy, with 16 months versus 12 months for OS, 5 months versus 4 months for PFS, and 8 months versus 4 months for TNT. With the joint frailty model approach using copula functions, estimated individual-level association was 0.57 (0.54–0.61) between OS and PFS, and 0.57 (0.53–0.60) also between OS and TNT. All estimated coefficients for associations at the center-level were close to 1, with a 95%CI equal to (0.91–1.09) between OS and PFS and equal to (1.00–1.00) between OS and TNT. Conclusion PFS and TNT were moderately correlated with OS at the individual-level. Center-level associations were strong. These results deserve to be confirmed with meta-analyses of clinical trials once published data will become available.