AI Generalisation Gap In Comorbid Sleep Disorder Staging

Saswata Bose; Suvadeep Maiti; Shivam Kumar Sharma; Mythirayee S; Tapabrata Chakraborti; Srijitesh Rajendran; Raju S. Bapi

cs.LGMar 24, 2026

AI Generalisation Gap In Comorbid Sleep Disorder Staging

Authors: Saswata Bose, Suvadeep Maiti, Shivam Kumar Sharma, Mythirayee S, Tapabrata Chakraborti, Srijitesh Rajendran, Raju S. Bapi

Organizations: International Institute of Information Technology (IIIT-H), Hyderabad, India · Queen Square Institute of Neurology, University College London, United Kingdom · National Institute of Mental Health and Neuroscience (NIMHANS), Bangalore, India · Alan Turing Institute, London and University College London, United Kingdom

Abstract

Accurate sleep staging is essential for diagnosing OSA and hypopnea in stroke patients. Although PSG is reliable, it is costly, labor-intensive, and manually scored. While deep learning enables automated EEG-based sleep staging in healthy subjects, our analysis shows poor generalization to clinical populations with disrupted sleep. Using Grad-CAM interpretations, we systematically demonstrate this limitation. We introduce iSLEEPS, a newly clinically annotated ischemic stroke dataset (to be publicly released), and evaluate a SE-ResNet plus bidirectional LSTM model for single-channel EEG sleep staging. As expected, cross-domain performance between healthy and diseased subjects is poor. Attention visualizations, supported by clinical expert feedback, show the model focuses on physiologically uninformative EEG regions in patient data. Statistical and computational analyses further confirm significant sleep architecture differences between healthy and ischemic stroke cohorts, highlighting the need for subject-aware or disease-specific models with clinical validation before deployment. A summary of the paper and the code is available at https://himalayansaswatabose.github.io/iSLEEPS_Explainability.github.io/

Figures & tables

Figure 1: Deep Model Architecture, with the $n$ th epoch being input to the model, having a window size of $w$ and a stride length of $s$ .

Datasets	Model	Overall Results
Datasets	Model	ACC	MF1	$\kappa$
SleepEDF-20 (Healthy Cohort)	NAS [ 4 ]	82.7	75.9	0.76
	DeepSleepNet [ 10 ]	82.0	76.9	0.76
	XSleepNet2 [ 7 ]	83.9	78.7	0.77
	SleepContextNet [ 13 ]	84.8	79.8	0.79
	SEResnet-Transformer [ 5 ]	79.3	74.7	0.72

Table 1: Results comparison with different models, trained and tested on SleepEDF-20, SleepEDF-78, SHHS and iSLEEPS dataset, respectively. Performance of our model is shown in bold. The performance has been measured using Accuracy (ACC), Macro F1 Score (MF1) and Kappa Score (

\kappa

), which shows that the model predictions align substantially with respect to random chance.

Dataset	W	N1	N2	N3	REM
SleepEDF-20	92.0	56.9	89.9	87.9	85.9
SleepEDF-78	92.1	50.1	85.2	82.1	82.1
SHHS	89.1	54.4	89.2	87.9	88.9
iSLEEPS	79.9	32.9	80.9	74.2	70.6

Table 2: Sleep stage classification (using single-channel raw EEG input) class-wise performance (F1 Score) of our model on the healthy subject datasets: SleepEDF-20, SleepEDF-78, and SHHS; and the patient dataset, iSLEEPS.

Panel of Figure 2 — Figure 2: Medically Annotated Epochs from iSLEEPS showing well-focussed and ill-focussed sleep-relevant artefacts based on the model trained on SHHS and tested on iSLEEPS. The title also includes the probability of the predicted class provided by the model in brackets.

Figure 3: GradCAM visualization of raw EEG epoch of sleep stage N2 (correctly predicted by the model) and boxes in green indicating K-complex and spindles, extracted from the model trained and tested on iSLEEPS.

Panel of Figure 4 — Figure 4: Transition graph of the dataset (excluding insignificant transitions and self transitions) elucidating the probabilities of transition from one state to the other for the corresponding dataset. The nodes represent corresponding sleep stages

Figure 5: Distribution of the Average Run Length in the Datasets. The Violin Chart clearly highlights that the iSLEEPS dataset has a much wider range for the feature while SleepEDF-78 is more constrained within a smaller range of values.

Sleep Stage Classification

Sleep stage classification assigns sleep epochs to physiological stages from signals such as EEG, helping quantify sleep architecture and support clinical monitoring.

See all 40 papers

MM-Net: A Multimodal Multi-Task Network for Sleep Staging and Sleep Apnea Assessment After Ischemic Stroke
Oct 27, 2026Md Wahiduzzaman Suva, Esm E Moula Chowdhury Abha, Md Imtiaj Alam Sajin +2Sleep Stage Classification Multimodal Learning
Department of Computer Science and Engineering, American International University-Bangladesh, Dhaka, 1229, Bangladesh · AI and Big Data Department, Woosong University, Daejeon, Republic of Korea
AnySleep: a channel-agnostic deep learning system for high-resolution sleep staging in multi-center cohorts
Dec 16, 2025Niklas Grieger, Jannik Raskob, Siamak Mehrkanoon +1Electroencephalography Sleep Stage Classification
Department of Medical Engineering and Technomathematics, FH Aachen University of Applied Sciences, 52428 Jülich, Germany · Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands · Institute for Data-Driven Technologies, FH Aachen University of Applied Sciences, 52428 Jülich, Germany
DualStabSleepNet: A Dual-Domain Diffusion Stabilization Network for Robust Sleep Staging
Aug 17, 2026Chongjian Wang, Chen Liu, Junjie Gao +3Diffusion-Based Denoising Sleep Stage Classification
School of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao, 266590, Shandong, China · School of Artificial Intelligence, Shandong Women’s University, Jinan, 250352, Shandong, China · School of Computer Science and Engineering, South China University of Technology, Guangzhou, 510641, Guangdong, China

Oct 27, 2026J/K move · Enter open · S save

MM-Net: A Multimodal Multi-Task Network for Sleep Staging and Sleep Apnea Assessment After Ischemic Stroke

Md Wahiduzzaman Suva, Esm E Moula Chowdhury Abha, Md Imtiaj Alam Sajin, Md Iftekharul Mobin+1

Department of Computer Science and Engineering, American International University-Bangladesh, Dhaka, 1229, Bangladesh · AI and Big Data Department, Woosong University, Daejeon, Republic of Korea

Sleep Stage Classification Multimodal Learning Electroencephalography Multimodal Fusion

Open paper AskPDF arXiv

Automated polysomnography after ischemic stroke is challenging because of altered sleep-related neural activity and concurrent respiratory disturbances. Existing stroke-specific approaches mainly address sleep-stage classification, leaving joint analysis of sleep architecture and respiratory events underexplored. Moreover, adapting pretrained EEG encoders introduces a representation inconsistency when downstream models are trained on embeddings from previously seen patients but evaluated on unseen individuals. We propose MM-Net, a multimodal multi-task framework that resolves this inconsistency through cross-fitting and ridge-based embedding alignment. Sleep-adapted EEG-EOG representations and engineered neural descriptors are fused with learned cardiorespiratory features through cross-attention and shared temporal modeling for simultaneous sleep staging and respiratory-event detection. On iSLEEPS (99 patients with subacute ischemic stroke), ten-fold patient-independent evaluation achieved 76.3% staging accuracy (Cohen's

κ

= 0.656) and 0.825 respiratory-event AUC, outperforming the evaluated baselines under matched protocols. The sleep-adapted encoder improved the downstream model when its embeddings were aligned, raising staging accuracy by 1.4 percentage points over the frozen encoder (

p

= 0.020) versus 0.2 points without alignment. MM-Net also achieved 86.4% staging accuracy on Sleep-EDF, above every single-EEG architecture reimplemented on the same recordings, and 80.3% staging accuracy with 0.889 respiratory AUC on ISRUC-I, exceeding its retrained staging baselines. Without retraining, the iSLEEPS-trained model retained respiratory AUCs of 0.833 on ISRUC-I and 0.841 on UCD. These findings support representation-consistent neural adaptation and joint physiological modeling across stroke, healthy-sleep, and sleep-disorder cohorts.

Abstract

Sleep Stage Classification

Explore similar work

MM-Net: A Multimodal Multi-Task Network for Sleep Staging and Sleep Apnea Assessment After Ischemic Stroke

AnySleep: a channel-agnostic deep learning system for high-resolution sleep staging in multi-center cohorts

DualStabSleepNet: A Dual-Domain Diffusion Stabilization Network for Robust Sleep Staging