S808
Clinical - Lung
ESTRO 2026
Digital Poster Highlight 3076
Progression patterns in patients with synchronous oligometastatic NSCLC after systemic and LRT: results from a multicentric retrospective study Valentina Bartolomeo 1,2 , Mandy Jongbloed 3 , Jarno W.J. Huijs 2,3 , Andrea Riccardo Filippi 4,2 , Ben E.E.M. van den Borne 5 , Cordula Pitz 6 , Hester Gietema 7 , Magdolen Youssef-El Soud 8 , Michelle Steens 8 , Safiye Dursun 3 , Wouter H. van Geffenk 9 , Peter de Boer 10 , Dirk K.M. de Ruysscher 2 , Lizza E.L. Hendriks 3 1 Department of Radiation Oncology, Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy. 2 Department of Radiation Oncology (Maastro Clinic), Maastricht University Medical Center, GROW – Research Institute for Oncology and Reproduction, Maastricht, Netherlands. 3 Department of Pulmonary Diseases, GROW – Research Institute for Oncology and Reproduction, Maastricht University Medical Center, Maastricht, Netherlands. 4 Department of Oncology, University of Milan, Milan, Italy. 5 Department of Pulmonary Diseases, Catharina Hospital, Eindhoven, Netherlands. 6 Department of Pulmonary Diseases, Laurentius hospital, Roermond, Netherlands. 7 Department of Radiology and Nuclear Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University Medical Centre, Maastricht, Netherlands. 8 Department of Pulmonary Diseases, Maxima Medical Center, Eindhoven, Netherlands. 9 Department of Pulmonology, Medisch Centrum Leeuwarden, Leeuwarden, Netherlands. 10 Radiotherapeutisch Instituut Friesland, Leeuwarden, Leeuwarden, Netherlands Purpose/Objective: Oligoprogressive disease (OPD) is characterized by progression limited to a few disease sites1,2. While evidence is growing regarding OPD occurrence during systemic therapy for metastatic non-small cell lung cancer (NSCLC), data are limited on progression patterns following systemic treatment combined with local radical treatment (LRT) in patients with synchronous oligometastatic disease (sOMD). Our study aimed to evaluate progression patterns, incidence and predictors in this setting of patients. Material/Methods: A retrospective multicenter analysis was conducted including 199 patients with sOMD NSCLC who received systemic therapy with LRT. Selection flowchart is depicted in Figure 1. Progression pattern, patient and tumor characteristics, and treatment modalities were recorded. Progression-free survival (PFS) and overall survival (OS) were analyzed, comparing patients with OPD to those with widespread progressive disease.
Conclusion: This study developed a deep learning model based on TCGA gene expression data to predict distant metastasis in LUAD, demonstrating high accuracy and AUC. The model holds substantial potential as a clinical risk assessment tool for early detection of high- risk metastatic patients. By integrating molecular features with clinical data, this tool could support personalized treatment strategies, guide decision- making in clinical practice, and assist in the management and follow-up of LUAD patients with metastatic potential. References: 1. Yagin B, Hilal Yagin F, Colak C, et al. Cancer Metastasis Prediction and Genomic Biomarker Identification through Machine Learning and eXplainable Artificial Intelligence in Breast Cancer Research. Diagnostics. 2023; 13(21):3314. 2. Sartori F, Codicè F, Caranzano I, et al. A Comprehensive Review of Deep Learning Applications with Multi-Omics Data in Cancer Research. Genes. 2025; 16(6):648.3. Zhang, X., Xiao, K., Wen, Y. et al. Multi-omics with dynamic network biomarker algorithm prefigures organ- specific metastasis of lung adenocarcinoma. Nat Commun15, 9855 (2024). Keywords: distant metastasis of LUAD, deep learning
Made with FlippingBook - Share PDF online