Radiogenomic insights from a Portuguese lung cancer cohort: Foundations for predictive modeling

Abstract

This study aimed to investigate the relationships between radiologic, clinical, and molecular characteristics in patients with lung cancer. A retrospective analysis was conducted using the Lung Cancer Mutation Database (LCMutationDB), which includes integrated clinical and computed tomography (CT) imaging data from 256 patients. The study focused on identifying associations between imaging features, clinical variables, and key oncogenic mutations (EGFR, KRAS). Significant correlations were observed between CT imaging characteristics and molecular alterations. Features such as ground-glass attenuation and pleural involvement were associated with poorer prognosis, while distinct imaging and clinical profiles corresponded to specific mutation subtypes. These findings enhance the current understanding of genotype–phenotype associations in lung cancer and underscore the value of integrating imaging, clinical, and molecular data for patient stratification. The results also provide a foundation for developing artificial intelligence–based diagnostic and prognostic models to improve early detection and personalized treatment strategies in lung cancer care.