Mini oral 1: NSCLC non-metastatic

Dr Dieter Stevens. thoracic oncologist at Ghent University Hospital discusses a selection of abstracts that were presented during the mini oral session on non-metastatic NSCLC.

Neoadjuvant and perioperative immunotherapy have transformed the treatment of early-stage resectable NSCLC. The CheckMate 77T trial compared neoadjuvant chemotherapy plus nivolumab with chemotherapy plus placebo, followed by surgery and adjuvant nivolumab or placebo. Interim results showed significant improvements in EFS and pCR rates with nivolumab. With a median follow-up of 33 months, updated data confirmed sustained benefits: a two-year EFS rate of 65% for the nivolumab group versus 44% for placebo. Exploratory analyses showed that patients receiving nivolumab had significantly higher ctDNA clearance at the end of neoadjuvant therapy, which was associated with a greater likelihood of achieving pCR after surgery. In contrast, ctDNA recurrence, an early sign of disease progression, was more common in the placebo group, with recurrence rates of 20% compared to 8% in the nivolumab group. Similarly, the AEGEAN trial, which used durvalumab in stage 2A–3B resectable NSCLC, reinforced the link between ctDNA clearance and higher pCR rates. Both trials highlight ctDNA clearance as a promising biomarker with strong negative predictive value. However, practical issues like long turnaround times and test failure rates limit its clinical application. Despite these challenges, ctDNA clearance may guide decisions on adjuvant therapies or more aggressive neoadjuvant treatments in the future.

A pooled analysis of five-year outcomes from two neoadjuvant immunotherapy trials in early-stage, resectable NSCLC (NEOSTAR and CA-209-159) sheds light on its efficacy. In total, 90 patients were treated: 60 with neoadjuvant nivolumab alone, and 30 with a combination of nivolumab and ipilimumab, without chemotherapy. The nivolumab-ipilimumab group had a higher pCR rate (33%) compared to nivolumab alone (8%), but five-year OS rates were similar (70% vs. 67%). Despite these findings, questions remain about which patients should receive neoadjuvant immunotherapy alone or in combination with chemotherapy. Additionally, patients with KRAS co-mutations (STK11, KEAP1) had worse outcomes, suggesting they may need more aggressive treatment.

Two abstracts highlight the role of AI in healthcare, focusing on disease monitoring and risk prediction in oncology. The first presents ARTIMES, an AI model for quantifying tumor volume in pleural mesothelioma. Trained on imaging data from clinical trials, ARTIMES outperformed the modified RECIST, the current standard for evaluating treatment response, in detecting early disease progression and correlating with overall survival. This suggests it may be a more precise tool for tracking mesothelioma progression. The second abstract introduces an AI model that combines radiomics and clinical data to predict pneumonitis in patients undergoing chemoradiotherapy and durvalumab, identifying high-risk patients for timely intervention. These studies underscore the growing role of AI in oncology, with the potential to enhance the precision of disease monitoring and risk prediction, ultimately improving patient outcomes.