According to various embodiments, there is provided a method for detecting a sleep disorder, the method including: processing an audio signal, the audio signal including breathing sounds made by a subject when the subject is asleep identifying intervals of the audio signal where breathing sounds are absent and detecting the sleep disorder based on the identified intervals. Identification of the intervals comprises computing of entropy values of the frequency components of the audio signal. Detection of the sleep disorder comprises computing of feature vectors for the classification of abnormality events.