Toward Interpretable Sleep Stage Classification Using Cross-Modal Transformers

TL;DR

This paper introduces a cross-modal transformer for sleep stage classification that improves accuracy, reduces model complexity, and enhances interpretability over existing deep-learning methods, facilitating clinical application.

Contribution

The paper presents a novel cross-modal transformer architecture with interpretability and efficiency advantages for sleep staging, outperforming current state-of-the-art models.

Findings

Outperforms existing sleep staging methods

Reduces model parameters and training time

Provides interpretability through attention modules

Abstract

Accurate sleep stage classification is significant for sleep health assessment. In recent years, several machine-learning based sleep staging algorithms have been developed , and in particular, deep-learning based algorithms have achieved performance on par with human annotation. Despite improved performance, a limitation of most deep-learning based algorithms is their black-box behavior, which have limited their use in clinical settings. Here, we propose a cross-modal transformer, which is a transformer-based method for sleep stage classification. The proposed cross-modal transformer consists of a novel cross-modal transformer encoder architecture along with a multi-scale one-dimensional convolutional neural network for automatic representation learning. Our method outperforms the state-of-the-art methods and eliminates the black-box behavior of deep-learning models by utilizing the interpretability aspect of the attention modules. Furthermore, our method provides considerable reductions in the number of parameters and training time compared to the state-of-the-art methods. Our code is available at https://github.com/Jathurshan0330/Cross-Modal-Transformer. A demo of our work can be found at https://bit.ly/Cross_modal_transformer_demo.