Dr Matteo Cesari
Sleep Disorders Unit, Department of Neurology, Medical University of Innsbruck in Austria
Contributing partner to World Sleep Society
Artificial Intelligence (AI) consists of computer programs that perform decision-making and pattern-recognition tasks previously done by humans. It is changing the field of sleep medicine.
Currently, sleep data recorded in sleep labs with polysomnography sleep studies (the gold standard sleep examination consisting of the simultaneous monitoring of brain waves, eye movement, muscular activity and cardiorespiratory functions) are visually inspected and sleep stages and events are manually scored by experts.
This is a time-consuming process which is also prone to inter-rater variability (when two human scorers do not agree on the identification of a sleep stage or event). Many studies have shown that AI algorithms can perform these tasks faster than humans and sometimes more precisely.
As an example, an AI algorithm has been shown to identify with very high precision sleep stages, sleep apnoeas and periodic limb movement during sleep on over 15,000 polysomnography recordings.
Other AI algorithms have been developed to automatically identify sleep disorders. In a study, it has been shown that patients suffering from REM sleep behaviour disorder (abnormal muscle activity and dream enactment during REM sleep, which is the early stage of neurodegenerative diseases like Parkinson’s) could be automatically identified from polysomnography data with an AI algorithm.
Common types of AI
Recent years have shown an increasing number of sensors and technologies to monitor sleep in home environments, in addition to the AI currently being developed for evaluating data and verifying sleep disorders from polysomnography.
A consultation with a sleep expert is always necessary in case of sleep issues.
Such technologies generally give information on sleep patterns and sleep quality. Several inform on the amount of time spent sleeping and the percentages of deep and light sleep.
However, many of these wearables have not been verified for clinical use. Therefore, attention should be paid in interpreting the outcomes of these AI technologies. A consultation with a sleep expert is always necessary in case of sleep issues.
Implementation of AI in clinical practice
Despite the current advancement of AI, AI algorithms are seldom employed in clinical practice. This is because the field is still growing and there is lack of regulatory frameworks on how to implement and use these algorithms. In the coming years, there is the need to have standard procedures in order to validate AI algorithms for clinical use. AI algorithms for clinical practice should also be transparent on how the data is processed and how the outputs are created.
The goal for the future is to have the best synergy between machines and human. Collaboration between clinicians, researchers and manufacturers is the basis to construct the future of AI in sleep medicine.
*Citations available on healthiersleepmag.com
Matteo Cesari, PhD has been working in the field of sleep research since 2016. Dr Cesari is currently at the Sleep Disorders Unit, Department of Neurology, Medical University of Innsbruck in Austria, where he is part of the sleep research team led by Professor Birgit Högl.
This article as originally published in the Healthier Sleep Magazine – July/August 2021 by the World Sleep Society.
