RESUMO
OBJECTIVE：To establ ish artificial neural netw orks（ANN）model to predict the interferon in the treatment of chronic hepatitis B （CHB），and to provide evidence for selecting suitable CHB therapy plan in clinic. METHODS ：The clinical data of 92 CHB patients treated by interferon ，from Guangzhou Eighth People ’s Hospital were retrospectively analyzed from Jul. 2011 to Dec. 2019. The basic information ，biochemical indexes ，blood routine indexes and virological markers of patients were collected. According to the effect of interferon ，the patients were divided into response group （73 cases）and non-response group （19 cases）. Minitab 18.0 software was used for multivariate Logistic regression analysis to screen the factors influencing the efficacy of interferon. Neurosolutions 5.0 software was used to randomly select 30％ of patients with CHB （27 cases）as the test group to establish and verify the ANN model. RESULTS ：The mean platelet volume ，platelet distribution width ，direct bilirubin ， hepatitis B e antigen and hepatitis B virus DNA more than 4×107 IU/mL had significant effect on interferon response （P＜0.05）. The accuracy ，specificity and area under characteristic curve of ANN test group were significantly higher than those of Logistic regression（P＜0.05）. CONCLUSIONS ：ANN model is accurate in predicting the efficacy of interferon in the treatment of CHB.