The invention discloses an early NSCLC prognosis prediction system, which comprises a main effect identification module, an interaction identification module, a survival time prediction module and a high-dimensional population discrimination module, and can improve the model prediction precision from the perspective of cross-omics by establishing a sample database and molecular biomarkers-methylation and gene expression. Different from a traditional biomarker, the system is stable and minimally invasive, the sensitivity and specificity of prognosis prediction are greatly improved, the main effect, GxE and GxG interaction effects are integrated, an early-stage NSCLC survival prediction model which is high in prediction precision and has strict multi-stage independent crowd verification is constructed, the defect that an existing model is poor in prediction effect is overcome, and a high-risk crowd discrimination module is combined. People with different risks are discriminated, diseaseprognosis is evaluated scientifically and accurately, and clinicians are helped to make clinical decisions or guide adjuvant therapy, early intervention and early benefit.