Abstract: Objective To investigate the value of fluorodeoxyglucose F18 positron emission tomography-computed tomography （18F-FDG PET-CT） in predicting the presence of epidermal growth factor receptor （EGFR） mutations in unresectable lung adeocarcinoma. Methods From April 2012 to May 2016， 151 patients with stage ⅢB or Ⅳ lung adeocarcinoma who underwent 18F-FDG PET-CT and EGFR mutation analysis were enrolled in this study. Receiver-operating characteristic （ROC） curve was used to test the cut-off of maximum standard uptake value（SUVmax）. Logistic regression model was employed to analyze the independent predictive factors for EGFR mutatuin. Results ROC curve showed that the cut-off of SUVmax was 10.28. Among 151 lung adeocarcinoma patients，68（45.0％） were identified with EGFR mutation. Univariate analysis showed that gender，smoking status，CEA and SUVmaxwere all associated with EGFR mutation （P＜0.05）. And no significant differences were found regarding partical CT characteristics of lesions including cavitation，air bronchogram， attenuation，lobulation and pleural-indentation （P＞0.05）. Logistic multivariate analysis showed that smoking status and SUVmax were the independent factors for predicting EGFR mutation （P＜0.05）. Conclusion SUVmax of 18F-FDG PET／CT is an independent factor for predicting EGFR mutation in patients with unresectable lung adeocarcinoma， and it has certainly reference value for predicting EGFR mutation.