Good and adequate sleep is very important to stay healthy. Due to today’s fast-paced life, many people are struggling with sleep disorders. This is affecting their health. Scientists have got a big success in this episode. In fact, scientists have developed artificial intelligence (AI) algorithms to improve the detection and treatment of sleep disorders. Researchers from the University of Copenhagen’s Department of Computer Science, in collaboration with the Dennis Center for Sleep Medicine, conducted a study in this regard.
Sleep disorders include insomnia, sleep apnea (interruptions in breathing while sleeping), and narcolepsy (sleep disorders involving the nerves). Most of the people suffering from these diseases do not even know about their disease. Therefore, proper treatment is also not possible.
Mathias Perslev, the lead author of a recent research article published in the NPJ Digital Medicine journal, pointed out that the algorithm is very accurate. We did many tests to see how effective it is. Currently, a variety of tools are used to diagnose sleep disorders. Experts in these diseases review the data collected by examining them for seven-eight hours overnight.
Doctors classify sleep stages by dividing seven to eight hours of sleep into 30-second intervals. E.g. REM (rapid eye movement) sleep, light sleep, deep sleep, etc. However, this investigation takes a long time, while the algorithm developed by the scientists can do this work in a few seconds.
It will help
Paul Jannum, Professor of Neurology at the Dennis Center for Sleep Medicine, said that this project has proved that this sleep assessment can be done very safely through machine learning and will be very useful. While this will save time, more and more patients will also be able to get an accurate examination.
Algorithm prepared like this
It takes one and a half to three hours for doctors to perform a polysomnography test (PSG) for sleep disorders. To overcome these problems, researchers have collected data of about 20 thousand sleep nights from various sources and used it in the algorithm. Researchers said that we collected data from different groups of patients from sleep clinics located in different regions of the world. The biggest thing about this is that this algorithm works in all situations, whereas this type of generalization is a big challenge in medical data analysis.
Efforts to get approval for clinical use
Researchers hope that this algorithm will be of great help to doctors and researchers in knowing sleep disorders. Mathias Perslev says that for this algorithm, only some data has to be collected with the help of normal clinical equipment. Therefore, the use of this software can also be area-specific. Researchers are currently trying to get approval for clinical use of this software and algorithm. Explain that an algorithm is a pattern of data, which presents the data related to the desired case.