Real-World Efficacy and Safety of Amivantamab for EGFR-Mutant NSCLC.

INTRODUCTION: Amivantamab-vmjw (amivantamab) is a bispecific EGFR/MET antibody approved for patients with advanced NSCLC with EGFR exon 20 insertion mutations, after prior therapy. Nevertheless, the benefits and safety of amivantamab in other EGFR-mutant lung cancer, with or without osimertinib, and with concurrent radiation therapy, are less known. METHODS: We queried the MD Anderson Lung Cancer GEMINI, Fred Hutchinson Cancer Research Center, University of California Davis Comprehensive Cancer Center, and Stanford Cancer Center's database for patients with EGFR-mutant NSCLC treated with amivantamab, not on a clinical trial. The data analyzed included initial response, duration of treatment, and concomitant radiation safety in overall population and prespecified subgroups. RESULTS: A total of 61 patients received amivantamab. Median age was 65 (31-81) years old; 72.1% were female; and 77% were patients with never smoking history. Median number of prior lines of therapies was four. On the basis of tumor's EGFR mutation, 39 patients were in the classical mutation cohort, 15 patients in the exon 20 cohort, and seven patients in the atypical cohort. There were 37 patients (58.7%) who received amivantamab concomitantly with osimertinib and 25 patients (39.1%) who received concomitant radiation. Furthermore, 54 patients were assessable for response in the overall population; 19 patients (45.2%) had clinical response and disease control rate (DCR) was 64.3%. In the classical mutation cohort of the 33 assessable patients, 12 (36.4%) had clinical response and DCR was 48.5%. In the atypical mutation cohort, six of the seven patients (85.7%) had clinical response and DCR was 100%. Of the 13 assessable patients in the exon 20 cohort, five patients (35.7%) had clinical response and DCR was 64.3%. Adverse events reported with amivantamab use were similar as previously described in product labeling. No additional toxicities were noted when amivantamab was given with radiation with or without osimertinib. CONCLUSIONS: Our real-world multicenter analysis revealed that amivantamab is a potentially effective treatment option for patients with EGFR mutations outside of exon 20 insertion mutations. The combination of osimertinib with amivantamab is safe and feasible. Radiation therapy also seems safe when administered sequentially or concurrently with amivantamab.

Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study.

BACKGROUND: Only around 20-30% of patients with non-small-cell lung cancer (NCSLC) have durable benefit from immune-checkpoint inhibitors. Although tissue-based biomarkers (eg, PD-L1) are limited by suboptimal performance, tissue availability, and tumour heterogeneity, radiographic images might holistically capture the underlying cancer biology. We aimed to investigate the application of deep learning on chest CT scans to derive an imaging signature of response to immune checkpoint inhibitors and evaluate its added value in the clinical context. METHODS: In this retrospective modelling study, 976 patients with metastatic, EGFR/ALK negative NSCLC treated with immune checkpoint inhibitors at MD Anderson and Stanford were enrolled from Jan 1, 2014, to Feb 29, 2020. We built and tested an ensemble deep learning model on pretreatment CTs (Deep-CT) to predict overall survival and progression-free survival after treatment with immune checkpoint inhibitors. We also evaluated the added predictive value of the Deep-CT model in the context of existing clinicopathological and radiological metrics. FINDINGS: Our Deep-CT model demonstrated robust stratification of patient survival of the MD Anderson testing set, which was validated in the external Stanford set. The performance of the Deep-CT model remained significant on subgroup analyses stratified by PD-L1, histology, age, sex, and race. In univariate analysis, Deep-CT outperformed the conventional risk factors, including histology, smoking status, and PD-L1 expression, and remained an independent predictor after multivariate adjustment. Integrating the Deep-CT model with conventional risk factors demonstrated significantly improved prediction performance, with overall survival C-index increases from 0·70 (clinical model) to 0·75 (composite model) during testing. On the other hand, the deep learning risk scores correlated with some radiomics features, but radiomics alone could not reach the performance level of deep learning, indicating that the deep learning model effectively captured additional imaging patterns beyond known radiomics features. INTERPRETATION: This proof-of-concept study shows that automated profiling of radiographic scans through deep learning can provide orthogonal information independent of existing clinicopathological biomarkers, bringing the goal of precision immunotherapy for patients with NSCLC closer. FUNDING: National Institutes of Health, Mark Foundation Damon Runyon Foundation Physician Scientist Award, MD Anderson Strategic Initiative Development Program, MD Anderson Lung Moon Shot Program, Andrea Mugnaini, and Edward L C Smith.