Background Uncommon EGFR mutations (ucEGFR mut) account for 10%-15% of epidermal growth factor receptor (EGFR) oncogenic alterations in non-small cell lung cancer (NSCLC) and display heterogeneous sensitivity to EGFR tyrosine kinase inhibitors. Materials and methods Clinical, pathological, and molecular data from patients with advanced NSCLC harboring ucEGFR mut (excluding ex20 insertions) and treated with first-line osimertinib were retrospectively collected from the Italian ATLAS registry. Results From January 2019 to January 2025, 212 patients were included. Median age was 69 years (range 24-90); 61.3% were female and 47.6% had a smoking history. Exon 19 deletions/insertions (ex19 delins) were the most frequent ucEGFR mut (55.7%), followed by L816Q (10.8%), G719X (8.5%), and D761N (7.5%). Tumor protein p53 and phosphatidylinositol-4,5-bisphosphate 3-kinase catalytic subunit alpha (PIK3CA) comutations were present in 43.3% and 10.4% of cases. The overall response rate (ORR) was 66% [95% confidence interval (CI) 58-73], median progression-free survival (mPFS) was 18.3 months (95% CI 14.6-19.7), and median overall survival (mOS) was 34.5 months (95% CI 26.1-42.9). Patients with ex19 delins showed superior outcomes versus other ucEGFR mut: ORR (74.3% versus 55%, P = 0.007), mPFS (25.3 versus 12.6 months, P = 0.001), and mOS (41.7 versus 30.4 months, P = 0.03), as well as different resistance mechanisms. Targetable acquired alterations (mesenchymal–epithelial transition amplification and C797S mutations) were detected predominantly in patients with ex19 delins, leading to the use of second-line molecularly matched therapies mainly in this subgroup. Patients with ex19 delins showed similar survival outcomes (25.3 versus 25.4 months, P = 0.55) and resistance patterns compared with a cohort of patients harboring the common exon 19 deletion (ELREA) extracted from the ATLAS registry. Among ex19 delins, variants starting at codon 746 achieved longer survival compared with those starting at codon 747. Conclusions Osimertinib exhibited meaningful differences in efficacy and resistance mechanisms across distinct ucEGFR mut. Notably, ex19 delins showed comparable survival outcomes and resistance patterns to classical ex19 deletions, albeit with heterogeneous osimertinib sensitivity depending on the deletion–insertion starting codon.
G. Farinea, A. Mogavero, A. Vitale et al.· ESMO Open· 0 citations
Background The AI-HOPE Lung Cancer study is a multicenter initiative designed to integrate artificial intelligence (AI) and real-world data to improve outcome prediction in patients with metastatic non-small-cell lung cancer treated with first-line immunotherapy-based regimens. AI-HOPE aims to leverage machine learning (ML) models to generate individualized predictions of progression-free survival (PFS), overall survival (OS), and treatment-related toxicity in a broad, unselected population. Materials and methods Clinical and imaging data are harmonized and stored within a privacy-compliant infrastructure (San Raffaele Ai CEnter [S-RACE] platform), promoting FAIR (Findable, Accessible, Interoperable and Reusable) data principles and minimizing manual workload. The primary objective is the development of time-to-event models for PFS and OS. Complementary binary classification models will explore early progression, long-term survival, and clinically relevant toxicities. Results The study includes retrospective (from 2017) and prospective (until 2027) phases across 21 European centers. So far, 920 patients have been recruited for the study, of whom 621 have baseline imaging scans available for centralized analysis. In the AI-HOPE study, a flexible methodological approach integrates multiple ML models tailored to specific clinical questions, complemented by explainable AI tools. Multimodal models combining clinical variables with computed tomography and [18F]2-fluoro-2-deoxy-d-glucose–positron emission tomography imaging features (when available) are supported through the S-RACE platform, which provides a partially automated imaging analysis workflow. Conclusions By combining structured clinical variables and multimodal imaging data, the AI-HOPE Lung Cancer study aims to support refined risk stratification and treatment personalization, ultimately facilitating the responsible integration of AI into routine thoracic oncology practice.
F. Ogliari, M. Ferrara, J. Huijs et al.· ESMO real world data and dig...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.