Toward Interpretable Sleep Stage Classification Using Cross-Modal Transformers

• Main Authors: Jathurshan Pradeepkumar (Author), Mithunjha Anandakumar (Author), Vinith Kugathasan (Author), Dhinesh Suntharalingham (Author), Simon L. Kappel (Author), Anjula C. De Silva (Author), Chamira U. S. Edussooriya (Author)
• Format: Book
• Published: IEEE, 2024-01-01T00:00:00Z.
• Subjects: article
• Online Access: Connect to this object online.
• Notes: 1534-4320; 1558-0210; 10.1109/TNSRE.2024.3438610
• Keywords: Automatic sleep stage classification; interpretable deep learning; transformers; deep neural networks; Medical technology; R855-855.5; Therapeutics. Pharmacology; RM1-950
• Source: IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol 32, Pp 2893-2904 (2024)

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 cross-modal transformer encoder architecture along with a multi-scale one-dimensional convolutional neural network for automatic representation learning. The performance of our method is on-par with 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 <uri>https://github.com/Jathurshan0330/Cross-Modal-Transformer</uri>. A demo of our work can be found at <uri>https://bit.ly/Cross_modal_transformer_demo</uri>.