In this work Artificial Neural Networks (ANNs) were developed and applied in order to forecast the discomfort levels due to the combination of high temperature and air humidity, during the hot season of the year, in eight different regions within the Greater Athens Area (GAA), Greece. For the selection of ANNs-forecasting models best type and architecture the Multiple Criteria Analysis (MCA) technique was applied. Three different types of ANNs were developed and tested with the MCA method. Concretely, the Multilayer Perceptron (MLP), the Generalized Feed Forward Networks (GFFN) and the Time-Lag Recurrent Networks (TLRN) were developed and tested. Results showed that the best ANNs type performance was achieved by using the GFNN model for the prediction of discomfort levels due to high temperature and air humidity within GAA. For the evaluation of the constructed ANNs appropriate statistical indices were used. The analysis proved that the forecasting ability of the developed ANNs models is very satisfactory, at a significant statistical level of p<0.01