AI Tool Successfully Predicts Immunotherapy Outcomes in Lung Cancer Patients
A new study published in Nature Medicine reveals that artificial intelligence (AI) tools can accurately predict treatment and survival outcomes for patients with advanced non-small cell lung cancer (NSCLC) undergoing immunotherapy. The I3LUNG project, an international trial, developed these AI-based predictive models to personalize therapeutic approaches for individuals. Immunotherapy, while transformative for some lung cancer patients, often faces resistance, and current predictive biomarkers like PD-L1 expression have limitations. Dr. Marina Garassino, professor of medicine at UChicago Medicine and senior author, emphasized the need for smarter tools. The research team enrolled 2,396 NSCLC patients from six international centers, including the United States, integrating diverse data such as clinical, imaging, pathology, and genomic information. The AI models consistently outperformed standard clinical biomarkers, with one model achieving an AUC score of 0.88 when incorporating clinical, blood, imaging, a...