Transparency in Sleep Staging: Deep Learning Method for EEG Sleep Stage Classification with Model Interpretability

This repository contains code, results, and dataset links for our arxiv paper titled Transparency in Sleep Staging: Deep Learning Method for EEG Sleep Stage Classification with Model Interpretability. 📝

Authors: ¹Shivam Kumar Sharma, ¹Suvadeep Maiti, S.Mythirayee, Srijithesh Rajendran, Bapi Raju

¹Equal contribution

More details on the paper can be found here. Raise an issue for any query regarding the code, paper, or for any support.

Table of contents

• Introduction
• Highlights
• Results
• Dataset
• Getting started
• Getting the weights
• License and Citation

Introduction 🔥

Automated Sleep stage classification using raw single channel EEG is a critical tool for sleep quality assessment and disorder diagnosis. However, modelling the complexity and variability inherent in this signal is a challenging task, limiting their practicality and effectiveness in clinical settings. To mitigate these challenges, this study presents an end-to-end deep learning (DL) model which integrates squeeze and excitation blocks within the residual network to extract features and stacked Bi-LSTM to understand complex temporal dependencies. A distinctive aspect of this study is the adaptation of GradCam for sleep staging, marking the first instance of an explainable DL model in this domain with alignment of its decision-making with sleep expert's insights. We evaluated our model on the publically available datasets (SleepEDF-20, SleepEDF-78, and SHHS), achieving Macro-F1 scores of 82.5, 78.9, and 81.9, respectively. Additionally, a novel training efficiency enhancement strategy was implemented by increasing stride size, leading to 8x faster training times with minimal impact on performance. Comparative analyses underscore our model outperforms all existing baselines, indicating its potential for clinical usage.

Highlights ✨

• A supervised model trained on Electroencephalography (EEG) data beating the current SOTA models 💥.
• Complete pre-processing pipeline, augmentation, and training scripts are available for experimentation.
• Pre-trained model weights are provided for reproducibility.

Results 🕺

Linear evaluation results on Sleep-EDF-20, Sleep-EDF-78 and SHHS datasets.

	Accuracy	κ	Macro F1-score
Sleep-EDF-20	87.5	0.82	82.5
Sleep-EDF-78	83.8	0.77	78.9
SHHS	76.75	0.83	81.9

1D-GradCAM visualization of raw EEG epochs along with sleep micro-structures shown in green boxes.

Getting started 🥷

Setting up the environment

TODO

What each file does

TODO

Training the model

TODO

Testing the model

TODO

Logs and checkpoints

• The logs are saved in logs/ directory.
• The model checkpoints are saved in checkpoints/ directory.

Getting the weights 🏋️

TODO

License and Citation 📰

Please cite the following paper if you have used this code:

@misc{sharma2023deep,
      title={A Deep Dive into Sleep: Single-Channel EEG-Based Sleep Stage Classification with Model Interpretability}, 
      author={Shivam Sharma and Suvadeep Maiti and S. Mythirayee and Srijithesh Rajendran and Bapi Raju},
      year={2023},
      eprint={2309.07156},
      archivePrefix={arXiv},
      primaryClass={eess.SP}
}