AI Pathology Model Outperforms PD-L1 in Predicting NSCLC Immunotherapy Response

Key Details

• 1Path-IO uses routine pathological slides to identify features predicting immunotherapy response in NSCLC patients.
• 2In validation on over 1,000 patients across multiple institutions and countries, Path-IO significantly outperformed PD-L1 testing, the current standard biomarker.
• 3The AI model stratified patients into high- and low-risk groups, with high-risk patients experiencing double the probability of death or progression.
• 4Unlike 'black box' models, Path-IO leverages established tissue features for explainable, clinically translatable decision-making.
• 5Researchers are integrating radiomics and clinical data to further improve Path-IO's prediction accuracy and plan to include CT, genomics, and other multimodal data in the future.
• 6Prospective clinical validation is the next planned step, and the model may evolve into a digital twin framework for comprehensive clinical decision support.