Researchers at the University of Eastern Finland have developed a deep learning model they claim can identify sleep stages as accurately as a sleep physician. The model uses artificial intelligence and neural network architecture to automatically classify sleep stages based on raw data.
According to a study published in the IEEE Journal of Biomedical and Health Informatics, the model identified sleep stages in healthy patients with an 83.7% accuracy when using a single frontal electroencephalography (EEG) channel, and with an 83.9% accuracy when supplemented with electrooculogram (EOG). In patients with suspected obstructive sleep apnea, the model achieved accuracies of 82.9% (single EEG channel) and 83.8% (EEG and EOG channels).
In a university press release, the researchers said the model’s accuracies are comparable to manual scoring; however, they noted that the accuracy of sleep staging decreased in more severe cases of sleep apnea.
The researchers hope the deep learning model can be used to improve the consistency of sleep staging across providers and systems while also completing the scoring in mere seconds. They also noted the potential cost savings by measuring sleep with fewer channels. Ultimately, the researchers think their methods could improve sleep apnea severity assessment, promote individualized treatment planning, and more reliably predict sleep apnea-related daytime symptoms and comorbidities. The research originated at the Sleep Technology and Analytics Group at the University of Eastern Finland, which was created to examine challenges in sleep diagnostics.
Read more sleep research news from the AASM.