Introduction: Nowadays, the artificial neural networks have received much attention in predicting the effects of multiple variables and complex relationships in aparticular variables. In this study, we have focused on the use of artificial neural network versus logisticre gression to predict post-traumatic mental disorders.Materials & methods: In a prospective cohort study, we covered 100 traumapatients admitted to the trauma center of Shahid Beheshti Hospital of Kashan duringa six month period. The patients were then randomly divided into two training (n=50)and experimental (n=50) groups.14variablesincluding age, sex, occupation, education level, marital status, socioeconomic status, history of mentalil lnessin the immediate family, history of being hospitalized in neurosurgeryunit, historyof trauma, history of underlyingdisease, history of psychological drug use, history of anesthesia, history of alcohol use, and history of substance abuse were totallyinvestigated.300artificial neuralnet work sandlogistic regressions were studied in the first group and then the predicted values were compared in the second group using the two models. The ROC curve and classification accuracy toolwere applied to estimate the predictive power of mental disorder.Findings: The results showed that the accurate index for predicting the disorderwas90.65% for the neural network model, while it was 75.96% for the logisticre gression model.Discussion & conclusions: The artificial neural network models appeared to be more powerful in predictingmental disorder versus the logistic regression model.