Advanced sleep spindle identification with neural networks
This work addresses the issue of intra- and inter-rater variability in sleep spindle annotations for research and diagnostic purposes, representing an incremental improvement in automated detection methods.
The paper tackled the problem of unreliable manual sleep spindle identification in EEG recordings by developing a U-Net-type deep neural network model, which exceeded state-of-the-art detector performance and most expert raters in the MODA dataset, with improved accuracy across all ages including older individuals.
Sleep spindles are neurophysiological phenomena that appear to be linked to memory formation and other functions of the central nervous system, and that can be observed in electroencephalographic recordings (EEG) during sleep. Manually identified spindle annotations in EEG recordings suffer from substantial intra- and inter-rater variability, even if raters have been highly trained, which reduces the reliability of spindle measures as a research and diagnostic tool. The Massive Online Data Annotation (MODA) project has recently addressed this problem by forming a consensus from multiple such rating experts, thus providing a corpus of spindle annotations of enhanced quality. Based on this dataset, we present a U-Net-type deep neural network model to automatically detect sleep spindles. Our model's performance exceeds that of the state-of-the-art detector and of most experts in the MODA dataset. We observed improved detection accuracy in subjects of all ages, including older individuals whose spindles are particularly challenging to detect reliably. Our results underline the potential of automated methods to do repetitive cumbersome tasks with super-human performance.