Shining a Light on the Mechanisms of Drug Resistance to Anti‐PD‐1 Therapy in Non‐small Cell Lung Cancer

Immune checkpoint inhibitors (ICIs) are first‐line therapies for advanced Nonsmall cell lung cancer (NSCLC), yet managing ICI resistance remains a critical, unavoidable challenge. This study identified genetic markers of anti‐PD‐1 resistance and developed an exploratory predictive model to differentiate responsive and resistant NSCLC patients. The GSE126044 transcriptomic subseries was used as the discovery cohort and included 16 pretreatment NSCLC biopsies (5 responders and 11 nonresponders). The prespecified eight‐gene score was re‐evaluated using repeated stratified out‐of‐fold prediction and was further assessed in two independent checkpoint‐blockade cohorts. The averaged out‐of‐fold AUC in GSE126044 was 0.982 (95% CI 0.931–1.000), although the eight genes had been selected before cross‐validation. External discrimination was limited in GSE135222 (AUC = 0.636, 95% CI 0.363–0.909) and GSE253564 (AUC = 0.567, 95% CI 0.230–0.903). These findings do not support stable generalization of the score across independent treatment settings. The eight‐gene score should be regarded as an exploratory checkpoint‐blockade response‐associated signature. Its potential clinical value requires validation in larger, prospectively collected cohorts with harmonized treatment and response endpoints.