Lung cancer is the leading cause of cancer-related deaths worldwide, and almost accounts for 20% of these deaths, however, the cure rate is less than 10% . Non-small cell lung cancer (NSCLC) accounts for approximately 85% of all cases of lung cancer , but fewer than 15% of individuals diagnosed with NSCLC can survive for more than 5 years, which poses a great threat to the patient’s life and health . Recently, the incidence of lung cancer keeps dynamically growing, but more than 75% of patients at diagnosis has appeared local development or metastasis, missing the best period of surgery. Moreover, despite surgical treatment is the optimal choice for early-stage NSCLC patients, 30%-40% of patients with NSCLC develop tumor recurrence in a short time. Therefore, improving the prognosis of patients with lung cancer and predicting the long-term survival of patients is of particular importance . At present, tumor and node metastasis (TNM) staging system, clinicopathological characteristics, visceral pleural invasion and marginal status are used to predict the disease progression and overall survival of NSCLC patients. There is no index which is stable, effective, reliable and less harmful to assess prognosis, predict recurrence risk and overall survival.