AI Model Enhances Prediction of Lung Cancer Immunotherapy Outcomes
A new AI model, presented at the American Association for Cancer Research (AACR) Annual Meeting, has shown promise in predicting outcomes and responses to immunotherapy in patients with metastatic non-small cell lung cancer (NSCLC). Developed by researchers at The University of Texas MD Anderson Cancer Center, the model, known as Pathology-driven Immunotherapy Optimization (Path-IO), uses deep learning to analyze digital pathology images. It stratifies patients into higher and lower risk groups, potentially improving patient selection for immunotherapy. The model was validated across international cohorts and a Phase III clinical trial, outperforming the current standard-of-care biomarker, PD-L1, in predicting patient outcomes. 
