Sleep apnea is a prevalent sleep disorder that profoundly impacts individuals’ health, disrupting normal sleep patterns and contributing to various health complications, including cardiovascular diseases and cognitive impairment. Early and accurate detection of sleep apnea is critical for mitigating its effects. This comprehensive review explores recent developments in automated sleep apnea detection, focusing on the utilization of biomedical signals and advanced signal preprocessing techniques, as well as different algorithms of machine learning and deep learning for sleep apnea detection. We provide an in-depth analysis of existing research studies, emphasizing the integration of diverse signals, such as heart rate variability, SpO \(_2\) , and electrocardiogram, aimed at enhancing the accuracy of apnea detection systems. In addition, the review addresses advanced signal preprocessing methodologies, including the application of wavelet transform and adaptive filtering, and highlights key features extracted for the detection of sleep apnea.