Summary: New machine learning technology that researchers have made free online can be used by sleep experts to study the role of K-complex, a brief but prominent pattern of brain activity that lasts around half a second during sleep. Algorithms and deep learning has enabled Flinders University sleep researchers to dive deep into one of the mysteries of sleep health. They have used machine learning and artificial intelligence to develop a free online tool being used by sleep experts and researchers around the world to work out the role of the so-called K-complex, a prominent, brief up-down-up pattern of brain electro-encephalogram (EEG) electrical activity lasting around half a second during sleep. 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. "We hope this algorithm will help to fast forward new discoveries regarding the mysterious K-complex waveform and its associated health outcomes."

Background: Electroencephalography (EEG) monitors brain activity during sleep and is used to identify sleep disorders. In sleep medicine, clinicians interpret raw EEG signals in so-called sleep stages, which are assigned by experts to every 30s window of signal. For diagnosis, they also rely on shorter prototypical micro-architecture events which exhibit variable durations and shapes, such as spindles, K-complexes or arousals. Annotating such events is traditionally performed by a trained sleep expert, making the process time consuming, tedious and subject to inter-scorer variability. To automate this procedure, various methods have been developed, yet these are event-specific and rely on the extraction of hand-crafted features. New method: We propose a novel deep learning architecure called Dreem One Shot Event Detector (DOSED). DOSED jointly predicts locations, durations and types of events in EEG time series. The proposed approach, applied here on sleep related micro-architecture events, is inspired by object detectors developed for computer vision such as YOLO and SSD. It relies on a convolutional neural network that builds a feature representation from raw EEG signals, as well as two modules performing localization and classification respectively. Results and comparison with other methods: The proposed approach is tested on 4 datasets and 3 types of events (spindles, K-complexes, arousals) and compared to the current state-of-the-art detection algorithms. Conclusions: Results demonstrate the versatility of this new approach and improved performance compared to the current state-of-the-art detection methods.