Real-time, automatic, open-source\ufeff\ufeff sleep stage classification system using single EEG for mice

Taro Tezuka,Masanori Sakaguchi,Iyo Koyanagi,Deependra Kumar,Sima Singh,Toshie Naoi

doi:10.1038/s41598-021-90332-1

Taro Tezuka, Masanori Sakaguchi + Show 4 more

Open Access

https://doi.org/10.1038/s41598-021-90332-1

Copy DOI

Journal: Scientific Reports	Publication Date: May 27, 2021
Citations: 12	License type: open-access

Abstract

We developed a real-time sleep stage classification system with a convolutional neural network using only a one-channel electro-encephalogram source from mice and universally available features in any time-series data: raw signal, spectrum, and zeitgeber time. To accommodate historical information from each subject, we included a long short-term memory recurrent neural network in combination with the universal features. The resulting system (UTSN-L) achieved 90% overall accuracy and 81% multi-class Matthews Correlation Coefficient, with particularly high-quality judgements for rapid eye movement sleep (91% sensitivity and 98% specificity). This system can enable automatic real-time interventions during rapid eye movement sleep, which has been difficult due to its relatively low abundance and short duration. Further, it eliminates the need for ordinal pre-calibration, electromyogram recording, and manual classification and thus is scalable. The code is open-source with a graphical user interface and closed feedback loop capability, making it easily adaptable to a wide variety of end-user needs. By allowing large-scale, automatic, and real-time sleep stage-specific interventions, this system can aid further investigations of the functions of sleep and the development of new therapeutic strategies for sleep-related disorders.

Highlights

We developed a real-time sleep stage classification system with a convolutional neural network using only a one-channel electro-encephalogram source from mice and universally available features in any time-series data: raw signal, spectrum, and zeitgeber time
The output from the convolutional neural network (CNN), Fourier Transformation (FFT), and zeitgeber time (ZT) are concatenated and transformed into a three-dimensional vector corresponding to the probabilities of each sleep stage by a fully connected neural network (FCN) (Fig. 1)
We hypothesized that historical information would be useful for classification, as previously shown[5,7]. We developed another system (UTSN-L) that connects to a LSTM after FCN output from the universal time-series network (UTSN) (Fig. 2), which enables the use of the output layer of the UTSN

Summary

Introduction

We developed a real-time sleep stage classification system with a convolutional neural network using only a one-channel electro-encephalogram source from mice and universally available features in any time-series data: raw signal, spectrum, and zeitgeber time. The resulting system (UTSN-L) achieved 90% overall accuracy and 81% multi-class Matthews Correlation Coefficient, with high-quality judgements for rapid eye movement sleep (91% sensitivity and 98% specificity) This system can enable automatic realtime interventions during rapid eye movement sleep, which has been difficult due to its relatively low abundance and short duration. Patanaik et al developed a real-time human sleep classification system with a convolutional neural network (CNN) using FFT, but not raw, data from two-channel electroencephalogram (EEG) and two-channel electrooculogram[4]. They achieved 81.4% overall accuracy (ACC), 71.8% REM sensitivity, and 83.6% REM specificity. Our method is scalable and harnessed in any closed feedback loop system for real-time intervention in specific sleep stages, with especially high sensitivity and specificity for REM

Methods

Results

Conclusion