## Resumo

Obesity is a common problem in nutrition, both in the developed and developing countries. The aim of this study was to classify obesity by artificial neural networks and logistic regression. This cross-sectional study comprised of 414 healthy military personnel in southern Iran. All subjects completed questionnaires on their socio-economic status and their anthropometric measures were measured by a trained nurse. Classification of obesity was done by artificial neural networks and logistic regression. The mean age?SD of participants was 34.4?7.5 years. A total of 187 (45.2%) were obese. In regard to logistic regression and neural networks the respective values were 80.2% and 81.2% when correctly classified, 80.2 and 79.7 for sensitivity and 81.9 and 83.7 for specificity; while the area under Receiver-Operating Characteristic (ROC) curve were 0.888 and 0.884 and the Kappa statistic were 0.600 and 0.629 for logistic regression and neural networks model respectively. We conclude that the neural networks and logistic regression both were good classifier for obesity detection but they were not significantly different in classification.

## Resumo Limpo

obes common problem nutrit develop develop countri aim studi classifi obes artifici neural network logist regress crosssect studi compris healthi militari personnel southern iran subject complet questionnair socioeconom status anthropometr measur measur train nurs classif obes done artifici neural network logist regress mean agesd particip year total obes regard logist regress neural network respect valu correct classifi sensit specif area receiveroper characterist roc curv kappa statist logist regress neural network model respect conclud neural network logist regress good classifi obes detect signific differ classif