A research team from the Department of Computer Science at the University of Copenhagen and the Sleep Center at Riggs Hospital in Denmark has partnered to develop an artificial intelligence algorithm that can improve the diagnosis and treatment of sleep disorders.
“The algorithm is very precise, and we have conducted a series of tests, and we have reached a degree of performance that exceeds the results of the best doctors working in this field,” said Matthias Berslev, a member of the study team, which was reported in the scientific journal “Digital Medicine.”
During sleep disorders tests, the patient is usually asked to sleep for a period of seven to eight hours and is subjected to a series of tests to measure his behavior and vital signs during sleep. Doctors divide sleep periods into 30-second time segments, and are categorized according to the different stages of sleep that the patient goes through, including napping, light sleep, deep sleep, and so on.
The study team confirms that the analysis of the results of the tests that require a long time can be carried out within a few seconds using the new system.
And the “Science Daily” website, which specializes in technology, quoted researcher Paul Genome, head of the Sleep Center, as saying that “this project allowed us to prove that all measurements can be carried out completely safely by artificial intelligence,” adding that the adaptation of artificial intelligence in this field helps in “ Providing long hours of work in order to assess the patient’s condition and diagnose his health condition accurately.”
The new system relies on data collected from multiple sources, as the researchers who created the algorithm fed it with data on nearly 20,000 sleep experiments conducted in the United States and several European countries.
