Sleep apnea is a severe sleep disorder that happens when breathing stops and starts during slumber. If it goes untreated, it can cause serious health problems. In recent years, Sleep Apnea (SA) has been diagnosed using either Electrocardiogram (ECG) signals that refer the heart health or Electroencephalogram (EEG) signals that refer to brain health. This research aims to build an Artificial Neural Network (ANN) classification model to determine sleep disorders using ECG and EEG signals. Features Delta sub-band waves are extracted and processed using a multilayer perceptron (MLP) with two different topologies; hidden layers are the same. The results show that using ECG and EEG signals to classify sleep apnea achieves high accuracy of 99.97% compared to other recent related work. We anticipate our assay to be a starting point for reliable wearable diagnostic devices to control equipment that can help patients with sleep apnea avoid respiratory distress episodes.