Artificial intelligence–driven biomarkers for predicting lung cancer diagnosis, treatment, and prognosis: a narrative review

Abstract

Lung cancer remains the leading cause of cancer-related mortality worldwide, with late-stage diagnosis and heterogeneous treatment responses contributing to poor survival outcomes. Recent advances in artificial intelligence (AI) have profoundly transformed the discovery, validation, and clinical application of lung cancer biomarkers, spanning early diagnosis, treatment stratification, and prognostic assessment. This review comprehensively summarizes major categories of lung cancer biomarkers—genomic, imaging, immunological, and emerging types—and highlights their roles in predicting the diagnosis, treatment, and prognosis of lung cancer. Furthermore, AI enables the integration of multimodal data from diverse sources, enhancing the accuracy and robustness of biomarker identification. The current applications of AI in lung cancer nursing practice are also critically examined, and key challenges and future directions for AI-driven biomarker prediction are outlined, with particular emphasis on data integration, model interpretability, and real-world clinical implementation.