SOMNUM is a sleep disorders analysis software, developed using explainable medical AI (XAI) technology and integrates the latest AI research trends with diagnostic algorithms based on multi-channel sleep biosignal data
South Korea-based AI-powered sleep disorder diagnosis software company HoneyNaps has received the US Food and Drug Administration (FDA) approval for its SOMNUM algorithm.
SOMNUM is a sleep disease analysis software that integrates the latest AI research trends with diagnostic algorithms based on multi-channel sleep biosignal data, rather than video images.
The electroencephalograms, electrooculograms, electromyograms, electrocardiograms, respiratory airflow and effort, oxygen saturation, posture and snoring include sleep biosignals.
The sleep biosignals are continuously monitored during sleep to determine the sleep status and diagnose any sleep disorder through polysomnography.
HoneyNaps developed SOMNUM using explainable medical AI (XAI) technology.
HoneyNaps general representative director Tae Kyoung Ha said: “The FDA has recently strengthened its review of AI-based medical devices, and we passed the review in three years by conducting clinical trials with 400 subjects, including US citizens directly, rather than through an agency, from the validation stage.
“This is an opportunity for us to further enhance our technology, such as adding diagnostic functions for cardiovascular and neuromuscular diseases, and to accelerate our expansion into the global market.”
According to the company, a skilled healthcare professional would require three to four hours to complete the process of measuring the sleep biosignals.
The AI-based reading systems are being highly researched to mitigate the problem of staffing and time issues associated with sleep biosignals monitoring.
The complex and heterogeneous nature of biosignals makes it very difficult to improve the AI systems to a level that they provide the same output as a human.
HoneyNaps said that its SOMNUM solution leverages deep learning-based AI to perform real-time analysis of vast volumes of multi-channel series biosignals.
The software works beyond conventional video image reading systems for biosignals, setting a new standard for accuracy and transparency in the field of sleep disorder diagnosis.
Furthermore, various studies using SOMNUM have been presented at international conferences held by the World Sleep Society (WSS), and a study was published in an SCIE journal.
Soonchunhyang University Bucheon Hospital Centre for Sleep Medicine head Ji Ho Choi said: “Like the AlphaGo case, which defeated humanity, this FDA approval is a very important event and a turning point in the field of sleep medicine in Korea.
“In the future, AI reading technology for biosignals is expected to play a very important role, similar to AI autonomous driving technology in cars.
“Furthermore, with the continuous improvement of biosignals AI reading technology, it will be possible to detect or predict some cardiovascular, neurological, and muscular diseases beyond the diagnosis of sleep disorders.”