Artificial intelligence applied to sleep medicine

Artificial intelligence (AI) is based on the development of technological systems capable of performing tasks that require human intelligence. Machine learning has been of growing interest in sleep medicine, with convolutional neural networks and recurrent neural networks being the most widely used algorithms. New diagnostic methods have been developed, such as customized non-contact pressure-sensitive devices, single-channel electrocardiogram, signal detection systems for triaxial thoracic and abdominal accelerometers, oximetry and electrocardiogram, pulse oximetry oxygen saturation measurement systems with smartphones, systems based on the detection of daytime tracheal noises, and prediction systems based on age, sex, and body mass index. AI has also made advances in the analysis of clusters of patients with sleep-disordered breathing, as well as in the detection of signals from polysomnographic recordings for automatic correction.