<![CDATA[Sleep apnea is a sleep disorder that occurs when breathing is repeatedly interrupted during sleep. This condition can lead to various serious health problems if left untreated, such as high blood pressure, poor sleep quality, and difficulty concentrating. Sufferers often do not realize they have sleep apnea because it occurs during sleep. Generally, diagnosis is made through interviews with the patient and their family to identify common symptoms such as snoring, and then confirmed through physical examination and Polysomnography (PSG). Since sleep apnea is related to respiratory activity that correlates with changes in cardiac activity, electrocardiogram (ECG) examination during sleep serves as an alternative diagnostic method. Therefore, this study presents a comparative analysis of deep learning models for detecting sleep apnea from spectrogram-based ECG representations. The raw ECG signals were transformed into spectrograms and then saved as images for classification into normal and abnormal categories. Deep learning (DL) methods were applied for the classification of normal and sleep apnea ECGs. EfficientNet, MobileNetV2, DenseNet, AlexNet, and VGG16 were used to evaluate the performance of the proposed method and identify the best-performing model. The evaluation results show that EfficientNet achieved the highest performance with an accuracy of 91.01%, precision of 90.70%, recall of 95.76%, and an F1-score of 92.61%. EfficientNet outperformed the other evaluated models in this study. By utilizing a spectrogram-based approach combined with a scalable architecture, the method demonstrates competitive accuracy for sleep apnea detection. Exploring other approaches to further improve accuracy remains an interesting direction for future research]]>
