Method for constructing lung cancer risk prediction model based on peripheral blood markers

The invention discloses a method for constructing a lung cancer risk prediction model based on peripheral blood markers. The method comprises the following steps: 1) collecting leukocyte, neutrophil absolute value, hemoglobin, lymphocyte absolute value and platelet count in peripheral blood routine examination, albumin, prealbumin, globulin and alkaline phosphatase in liver function, sodium, chlorine and iron in electrolyte, fibrinogen and D-dimer in coagulogram, CA125, CEA and cyfra21-1 in tumor markers, and CA125, CEA and cyfra21-1 in tumor markers; 27 indexes, namely, SCC, NSE, ProGRP, CD3 +, CD4 +, CD8 +, B and NK lymphocytes in the immune function, total lymphocyte count and age, are included; and 2) modeling peripheral blood test indexes of the lung cancer patient and the lung benign disease patient (G1) based on machine learning. The model has very high sensitivity and specificity; the model integrates an inflammation index, a nutrition index, a blood coagulation index, a tumor marker and an immune fun