W. Duch et al. (Eds.): ICANN 2005, LNCS 3696, pp. 653 – 658, 2005. © Springer-Verlag Berlin Heidelberg 2005 Neural Network Use for the Identification of Factors Related to Common Mental Disorders T.B. Ludermir 2 , C.R.S. Lopes 1,2 , A.B. Ludermir 2 , and M.C.P. de Souto 2 1 State University of Bahia (UESB) – 45.216-510 – Jequié – BA – Brasil 2 Federal University of Pernambuco C.P 7851 – 50.732-970 – Recife – PE - Brazil tbl@cin.ufpe.br Abstract. This paper shows that MLP trained with the optimizing Simulated Annealing algorithm, may be used for identification of the factors related to Common Mental Disorders (CMDs). The average percentage of correct classi- fication of individuals with positive diagnostic for the CMDs was of 90.6% in the experiments related in the paper. 1 Introduction CMDs, and among them the anxiety and depression have been pointed out as the common causes of morbidity in developed countries as much as in the developing ones, as the example of Brazil. These mental disorders represent a high social and economic charge because they are disabled, they constitute important cause of lost of workdays and they take a substantial use of health care services [3]. The use of techniques that may lead to an identification of the factors that present the larger possibility of being related to these CMDs it is relevant to assist within the decision taking process around the planning and intervention of public health care. Artificial Neural Networks (ANNs) have been largely used in the health care field and they are known because they generally obtain a good precision result [2,4,6]. With this research we intend, mainly, to experimentally show that a MLP trained with Simulated Annealing (SA) algorithm is able to identify the factors related to the CMDs. The results obtained with MLP were compared with the ones presented by Ludermir [3]. She applied the logistics regression method, using the same data basis to analyze the independence of each variable association with the CMDs. On the statistic analysis for the identification of the factors related to the CMDs, it was esti- mated the simple and adjusted odds-ratios, whose statistic significance was evaluated by the χ 2 test, considering the 95% confidence interval and values of p (≤0.05). 2 Simulated Annealing The SA algorithm [1] consists of a sequence of iterations. Each iteration consists of randomly changing the current solution to create a new solution in the neighborhood of the current solution. The neighborhood is defined by the choice of the generation mechanism. Once a new solution is created, the corresponding change in the cost function is computed to decide whether the new solution can be accepted as the cur-