MD Anderson AI Predicts Lung Cancer Immunotherapy Response

Researchers at The University of Texas MD Anderson Cancer Center have developed an artificial intelligence model that analyzes routine pathology slides to predict how patients with metastatic nonsmall cell lung cancer will respond to immunotherapy. The model, known as Pathology-driven Immunotherapy Optimization or PathIO, was presented on April 20 at the American Association for Cancer Research Annual Meeting in San Diego.

PathIO uses deep learning techniques from the field of pathomics, which applies computational methods to digital images of tissue samples. It examines patterns in the tumor microenvironment, such as specific cellular structures called niches, to identify patients at higher or lower risk of poor outcomes from immune checkpoint inhibitors. These drugs, which help the immune system attack cancer cells, have improved survival for some lung cancer patients but benefit only a subset, making reliable prediction a key challenge in oncology.

The study involved 797 patients treated with immune checkpoint inhibitors at MD Anderson. PathIO stratified them into high-risk and low-risk groups, with those in the high-risk category facing more than double the risk of death or...