OSCR

MAF-SleepNet: A Multimodal Attention-Enhanced Fusion Network for Automatic Multi-Class Sleep Disorder Classification from Polysomnography.

Overview

  1. Department of Biomedical, Vocational School of Technical Sciences, Firat University, 23119 Elazig, Türkiye
  2. School of Mathematics, Physics, and Computing, University of Southern Queensland, Springfield, QLD 4300, Australia
  3. Department of Electrical-Electronics Engineering, Faculty of Engineering, Firat University, 23119 Elazig, Türkiye
  4. School of Business, University of Southern Queensland, Toowoomba, QLD 4350, Australia
Institutions: Fırat University (Türkiye); University of Southern Queensland (Australia)
Journal: Diagnostics (Basel, Switzerland), volume 16, issue 15, article 2317
Dates: received 24 May 2026; accepted 21 July 2026; published online 23 July 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3390/diagnostics16152317 · PMID 42587555 · PMCID PMC13465423 · OpenAlex W7170184884
Open access: gold, a free copy (OpenAlex)
Categories: EEG (modality), sleep disorders (population)
Methods: Spectral & time-frequency, Connectivity, Machine learning, Preprocessing, Statistics, Physiology & signal measures
Keywords: attention mechanism, deep learning, information fusion, multimodal learning, polysomnography, sleep disorder classification
Topic: Obstructive Sleep Apnea Research (Physiology (medical), Medicine), according to OpenAlex
Funding: International Research Fellowship Program (1059B142301242); Firat Üniversitesi (TBMYO.25.09)
Citations: not cited yet (Europe PMC); 87 references in the paper

Abstract

Background/Objectives: Sleep disorders are heterogeneous conditions with diverse neural, muscular, and ocular manifestations, making polysomnography (PSG) the gold standard for accurate diagnosis. Artificial intelligence-based approaches, particularly deep learning (DL) models capable of integrating heterogeneous information, offer a promising solution for reliable decision-making in such clinical scenarios. However, most existing DL studies have focused on a single disorder, relied on limited datasets, or employed epoch-level labeling strategies that overlook the episodic nature of sleep pathophysiology, thereby limiting clinical applicability. To address these gaps, we propose a novel multimodal attention-enhanced fusion network (MAF-SleepNet) for automatic multi-class sleep disorder classification based on the International Classification of Sleep Disorders. Methods: MAF-SleepNet jointly processes electroencephalography (EEG), electrooculography (EOG), and leg electromyography (EMG) signals through modality-specific feature extraction and adaptive attention mechanisms, capturing both intra- and inter-modality dependencies. The model was evaluated on a combined dataset of 141 recordings from three public databases, including five PSG-requiring disorders and a healthy class. Results: Experimental results demonstrated that MAF-SleepNet achieved 86.07 ± 3.66% accuracy and 82.67 ± 4.46% macro-F1 under a strict subject-independent cross-validation, and 98.96 ± 0.66% accuracy and 98.93 ± 0.60% macro-F1 under subject-dependent cross-validation. Conclusions: These results demonstrate that the proposed approach provides a more reliable and clinically meaningful assessment compared to many existing studies that rely on subject-dependent evaluation or epoch-level labeling. The findings highlight the effectiveness of adaptive multimodal fusion for robust and clinically relevant sleep disorder classification. Future work should investigate the integration of respiratory and autonomic modalities and validation on larger multi-center cohorts.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data and to no code of its authors: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

Data Availability Statement

The original contributions presented in this study are included in the article/Supplementary Materials. Further inquiries can be directed to the corresponding author.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 3 authors, 6 keywords, 2 funders, 69 references.

Cite

This paper

Yaman, S., Guler, H., & Hafeez-Baig, A. (2026). MAF-SleepNet: A Multimodal Attention-Enhanced Fusion Network for Automatic Multi-Class Sleep Disorder Classification from Polysomnography. Diagnostics (Basel, Switzerland), 16(15), 2317. https://doi.org/10.3390/diagnostics16152317

BibTeX

@article{yaman2026maf,
author = {Yaman, Suleyman and Guler, Hasan and Hafeez-Baig, Abdul},
title = {{MAF-SleepNet: A Multimodal Attention-Enhanced Fusion Network for Automatic Multi-Class Sleep Disorder Classification from Polysomnography}},
journal = {Diagnostics (Basel, Switzerland)},
year = {2026},
month = jul,
volume = {16},
number = {15},
pages = {2317},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {2075-4418},
doi = {10.3390/diagnostics16152317},
url = {https://doi.org/10.3390/diagnostics16152317},
pmid = {42587555},
pmcid = {PMC13465423}
}

RIS

TY - JOUR
AU - Yaman, Suleyman
AU - Guler, Hasan
AU - Hafeez-Baig, Abdul
TI - MAF-SleepNet: A Multimodal Attention-Enhanced Fusion Network for Automatic Multi-Class Sleep Disorder Classification from Polysomnography
T2 - Diagnostics (Basel, Switzerland)
J2 - Diagnostics (Basel)
PY - 2026
DA - 2026/07/23
VL - 16
IS - 15
SP - 2317
SN - 2075-4418
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/diagnostics16152317
UR - https://doi.org/10.3390/diagnostics16152317
LA - en
ER -

CSL-JSON

{
"id": "10.3390/diagnostics16152317",
"type": "article-journal",
"title": "MAF-SleepNet: A Multimodal Attention-Enhanced Fusion Network for Automatic Multi-Class Sleep Disorder Classification from Polysomnography",
"container-title": "Diagnostics (Basel, Switzerland)",
"author": [
{
"family": "Yaman",
"given": "Suleyman"
},
{
"family": "Guler",
"given": "Hasan"
},
{
"family": "Hafeez-Baig",
"given": "Abdul"
}
],
"container-title-short": "Diagnostics (Basel)",
"volume": "16",
"issue": "15",
"page": "2317",
"DOI": "10.3390/diagnostics16152317",
"PMID": "42587555",
"PMCID": "PMC13465423",
"ISSN": "2075-4418",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://doi.org/10.3390/diagnostics16152317",
"language": "en",
"issued": {
"date-parts": [
[
2026,
7,
23
]
]
}
}

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.3390/diagnostics12102510
L-Tetrolet Pattern-Based Sleep Stage Classification Model Using Balanced EEG Datasets.
Journal: Diagnostics (Basel, Switzerland)
In common: sleep disorders, EEG, 5 references
[2] doi:10.3390/s23073468
Simultaneous Sleep Stage and Sleep Disorder Detection from Multimodal Sensors Using Deep Learning.
Journal: Sensors (Basel, Switzerland)
In common: sleep disorders, EEG, 4 references
[3] doi:10.1093/sleep/zsaf164 [code]
The Hypno-PC: uncovering sleep dynamics through principal component analysis and hidden Markov modeling of electrophysiological signals.
Journal: Sleep
In common: EEG, 4 references
[4] doi:10.3390/brainsci15090985
NRGAMTE: Neurophysiological Residual Gated Attention Multimodal Transformer Encoder for Sleep Disorder Detection.
Journal: Brain sciences
In common: sleep disorders, 3 references
[5] doi:10.3390/brainsci15070691
A Permutation Entropy Method for Sleep Disorder Screening.
Journal: Brain sciences
In common: sleep disorders, EEG, 3 references
[6] doi:10.1007/s11571-025-10266-6
DMPat-based SOXFE: investigations of the violence detection using EEG signals.
Journal: Cognitive neurodynamics
In common: EEG, author Abdul Hafeez-Baig
[7] doi: [code]
An automated EEG–ECG framework for CAP–HRV analysis: enabling brain–heart coupling studies in sleep disorders
Journal: Frontiers in physiology
In common: sleep disorders, EEG, 3 references
[8] doi:10.1038/s41746-026-03406-7 [code]
AnySleep: a channel-agnostic deep learning system for high-resolution sleep staging in multi-center cohorts.
Journal: NPJ digital medicine
In common: sleep disorders, EEG, 3 references
[9] doi:10.3390/s25072141
On-the-Fly Sleep Scoring Algorithm with Heart Rate, RR Intervals and Accelerometer as Input.
Journal: Sensors (Basel, Switzerland)
In common: EEG, 3 references
[10] doi:10.1186/s12880-025-01721-1
StrokeNeXt: an automated stroke classification model using computed tomography and magnetic resonance images.
Journal: BMC medical imaging
In common: author Abdul Hafeez-Baig

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.