Machine learning-based establishment and validation of age-related patterns for predicting prognosis in non-small cell lung cancer within the context of the tumor microenvironment.

Lung cancer (LC) is a leading cause of cancer-related mortality worldwide, with non-small cell lung cancer (NSCLC) accounting for over 80% of cases. The impact of aging on clinical outcomes in NSCLC remains poorly understood, particularly with respect to the immune response. In this study, we explored the effects of aging on NSCLC using 307 genes associated with human aging from the Human Ageing Genomic Resources. We identified 53 aging-associated genes that significantly correlate with overall survival of NSCLC patients, including the clinically validated gene BUB1B. Furthermore, we developed an aging-associated enrichment score to categorize patients based on their aging subtypes and evaluated their prognostic and therapeutic response values in LC. Our analyses yielded two aging-associated subtypes with unique profiles in the tumor microenvironment, demonstrating varying responses to immunotherapy. Consensus clustering based on transcriptome profiles provided insights into the effects of aging on NSCLC and highlighted the potential of personalized therapeutic approaches tailored to aging subtypes. Our findings provide a new target and theoretical support for personalized therapeutic approaches in patients with NSCLC, offering insights into the potential impact of aging on cancer outcomes.