From the Research
Several AI systems, including Dreem, Sleep Profiler, Muse S, Neuroon, and Kokoon, have been developed for real-time detection of sleep disorders using wearable EEG, with Dreem being particularly notable for its seven EEG sensors and ability to detect sleep stages with clinical-grade accuracy. These systems combine lightweight EEG headbands with machine learning algorithms to monitor brain activity during sleep and identify patterns associated with disorders like sleep apnea, insomnia, and narcolepsy. According to a recent scoping review published in the Journal of Medical Internet Research 1, wearable artificial intelligence (AI)-powered solutions offer accessible, scalable, and continuous monitoring, improving the identification and treatment of sleep problems. The review highlights the use of various AI methodologies, including convolutional neural networks, random forest, and support vector machines, for the detection and analysis of sleep disorders.
Some of the key features of these AI systems include:
- Lightweight EEG headbands with multiple sensors (e.g., Dreem's seven EEG sensors)
- Machine learning algorithms for real-time processing of brain wave data
- Ability to detect sleep stages with clinical-grade accuracy
- Interventions like audio stimulation to improve deep sleep
- FDA-cleared in-home sleep testing (e.g., Sleep Profiler's three EEG channels)
The advantage of these wearable systems is their ability to monitor sleep continuously in the home environment over multiple nights, providing more representative data than traditional in-lab polysomnography, though they typically have fewer measurement channels than clinical systems. As noted in a systematic review of sensing technologies for wearable sleep staging published in Sensors 2, EEG-based systems are the most accurate, with EEG being the only sensing modality capable of identifying all the stages of sleep.
Overall, the development of AI systems for real-time detection of sleep disorders using wearable EEG has the potential to improve the diagnosis and treatment of sleep disorders, and the use of these systems should be considered as a valuable tool in the management of sleep disorders, particularly in patients with comorbid insomnia and sleep apnea.