Researchers developed an Immune Response-related Risk Score (IRRS) using machine learning and 13 immune-related genes that outperformed existing tools in predicting colorectal cancer prognosis and immunotherapy response.
The IRRS achieved the highest prognostic accuracy with an area under the curve of 0.861, successfully stratifying patients into high-risk and low-risk groups across multiple independent datasets.
Low-risk patients showed better overall survival, higher immune activity, increased immune cell infiltration, and elevated expression of immune checkpoint molecules including PDCD1, CD274, and CTLA4.
The multi-omics approach identified key genes like CTLA4, PDCD1, and CD274 that provide insights into tumor immunogenicity and represent potential therapeutic targets for colorectal cancer treatment.