Integrative Modeling of Tumor Burden and Metastatic Pattern for Guiding Anti-PD-L1 Treatment of Non–Small Cell Lung Cancer: Results From Two Randomized Studies

Background: Clinical benefits of immune-checkpoint blockade (ICB) versus standard chemotherapy have been established in unselected non-small cell lung cancer (NSCLC). However, the response to ICB therapy among patients is still heterogeneous in clinical practice. Methods: We retrospectively assessed the impact of baseline sum of the longest diameters (SLD), number of metastatic sites and specific organ metastases on the efficacy of atezolizumab versus docetaxel in the pooled population from OAK and POPLAR studies. An assistant decision model based on the machine-learning method, incorporating these indicators, termed DSO (Diameter-Site-Organ), was developed and validated in OAK and POPLAR cohorts. Findings: Higher SLD (> 38mm) and more metastatic sites (≥ 2) were characterized with pronounced OS benefits from atezolizumab versus docetaxel. Specifically, brain and adrenal gland metastases were identified as favorable predictors of atezolizumab treatment. The DSO model for guiding second-line treatment was developed based on SLD and metastatic sites and organs in the discovery cohort. Remarkably, a general pattern of enhanced efficacy of atezolizumab versus docetaxel was observed along with the increase of the DSO score. For patients with DSO score > 0, atezolizumab yielded a prolonged OS than docetaxel (hazard ratio [HR] 0.67, 95% CI 0.54-0.84; P = 0.0003), whereas OS was generally similar between two treatments in patients with DSO score ≤ 0 (HR 1.46, 95% CI 0.89-2.39; P = 0.1346). Equivalent findings were seen in the internal and external validation cohorts. Interpretation: Our study for the first time revealed that patients with higher tumor burden were more suitable for ICB compared with standard chemotherapy. More importantly, the integrative DSO decision model might provide promising medication guidance for second-line ICB treatment in unselected NSCLC patients. Funding: This study was supported by the National Natural Science Foundation for YoungScientists of China (Grant No. 81802863 and 81902353), the Natural Science Foundation of Guangdong Province (Grant No. 2018030310285), and the Outstanding Youths Development Scheme of Nanfang Hospital, Southern Medical University (Grant No. 2017J003). Conflict of Interest: The authors have no actual or potential conflicts of interest to declare. Ethical Approval: The study was approved by theInstitutional Ethical Review Boards of Nanfang Hospital. All patients enrolled in OAK and POPLAR provided signed informed consent in accordance with the protocols of the corresponding studies.