When displayed on an EEG screen, it looks a bit like a 'K', says Bastien Lechat, lead author on a new Flinders University paper published in Sleep journal (pre-press).
"We hope this algorithm will help to fast forward new discoveries regarding the mysterious K-complex waveform and its associated health outcomes."
"A lack of K-complexes has been linked to various clinical problems, such as Alzheimer's disease and insomnia, suggesting that K-complexes are an important part of normal sleep and health."
"While the meaning and role of K-complexes is rather unclear, one of the leading theories is that they reflect low-level decision processing to either wake up or stay asleep in response to sensory input during sleep," says Mr Lechat, from the Adelaide Institute for Sleep Health at Flinders University.
K-complexes occur roughly every two minutes during sleep, so are too labour-intensive for routine sleep scoring.
If K-complexes were considered, it would take an expert sleep technician approximately 0.5 to 1.5 hours longer to score one sleep study.
Manual scoring also comes with a lot of variability, with agreement between expert scorers as low as 50%. The deep learning algorithm to automatically score K-complexes during overnight sleep studies is much faster and more reliable than with manual scoring.
The algorithm takes around 3 minutes to score an entire night of sleep and out-performs all currently available automated methods," says co-author Dr Branko Zajamsek.
"In addition to its enhanced detection speed and accuracy, the algorithm also gives a 'confidence' or probability rating, allowing for more useful comparisons between clear versus ambiguous K-complex signals - as defined by human scoring.
"This makes the sleep scoring output comprehensive, yet very easy to understand compared to other automated methods."
Beyond K-complex binary scoring during sleep: Probabilistic classification using deep learning (April 2020) by B Lechat, K Hansen, P Catcheside and B Zajamsek has been published in international journal Sleep.