Lung cancer and interstitial lung diseases (ILDs), particularly idiopathic pulmonary fibrosis (IPF), are major contributors to respiratory morbidity and mortality globally. While traditionally studied as distinct conditions, increasing clinical evidence suggests that they may share common etiological pathways and risk factors, including genetic susceptibility, smoking, environmental exposures, and aging. Furthermore, patients with ILD are at a significantly higher risk of developing lung cancer, and the coexistence of these diseases presents unique diagnostic and therapeutic challenges. Despite these observations, current understanding of the mechanisms driving their comorbidity remains limited, and there is a lack of predictive models to identify high-risk individuals or guide integrated management strategies. To address these gaps, we propose to use the extensive data resources of the UK Biobank to investigate the shared and disease-specific genetic, environmental, and clinical determinants of lung cancer and ILDs. Our study will pursue three primary objectives: (1) to identify and compare key risk factors, such as genomic variants, lifestyle variables, air pollution exposure, and clinical history, associated with each disease and their overlap; (2) to analyze temporal associations between ILD and lung cancer diagnoses, and evaluate how ILD subtypes and progression influence lung cancer incidence and patient outcomes; and (3) to develop multivariable risk prediction models for comorbid disease using regression and machine learning techniques, with the goal of enabling more accurate risk stratification and earlier intervention. By integrating diverse data types in a population-based cohort, this study aims to provide new insights into the etiology, progression, and interaction of lung cancer and ILDs, ultimately supporting the development of evidence-based prevention and personalized treatment strategies.
