Papers › Toward Interpretable Sleep Stage Classification Using Cross-Modal Transformers

Toward Interpretable Sleep Stage Classification Using Cross-Modal Transformers

15 Aug 2022arXiv:2208.06991archive 2025-07-28

Jathurshan Pradeepkumar, Mithunjha Anandakumar, Vinith Kugathasan, Dhinesh Suntharalingham, Simon L. Kappel, Anjula C. De Silva, Chamira U. S. Edussooriya

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.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

jathurshan0330/cross-modal-transformer officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Automatic Sleep Stage Classification Deep Learning General Classification Multimodal Sleep Stage Detection Representation Learning Sleep Stage Detection Sleep Staging

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Automatic Sleep Stage Classification	Sleep-EDF	Sequence Cross-Modal Transformer-15	Accuracy	84.3	#2 of 4	Archive leaderboard	report
Automatic Sleep Stage Classification	Sleep-EDF	Sequence Cross-Modal Transformer-15	Cohen’s Kappa score	0.785	#2 of 4	Archive leaderboard	report
Automatic Sleep Stage Classification	Sleep-EDF	Sequence Cross-Modal Transformer-15	Number of parameters (M)	4.05	#2 of 4	Archive leaderboard	report
Automatic Sleep Stage Classification	Sleep-EDF	Epoch Cross-Modal Transformer	Accuracy	80.8	#4 of 4	Archive leaderboard	report
Automatic Sleep Stage Classification	Sleep-EDF	Epoch Cross-Modal Transformer	Cohen’s Kappa score	0.736	#4 of 4	Archive leaderboard	report
Automatic Sleep Stage Classification	Sleep-EDF	Epoch Cross-Modal Transformer	Number of parameters (M)	0.32	#4 of 4	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections