In this paper, the results of processing airflow area, oxygen saturation, heart rate variability and Neural Network based real time evaluation for a previously designed portable apnea device have been demonstrated. This results has been presented by a specific interface of "Artificial Neural Networks Based Sleep Apnea Detection and Analysis" and network performances were presented in comparative manner. Apart from having real time apnea detection, desired artificial neural networks can be generated via apnea user interface by using feature extracted signals in accordance with the selected activation function and training with selected target vector. The attributes obtained from each signal were evaluated separately or together and the detection characteristics of the models were examined. The Time Delayed Neural Networks (TDNNs) with hybrid data performs better than the other networks trained with the set obtained from single channel. It is easy to perform and compare networks with extracting new features and training new networks by this dedicated interface.