An interpretable multimodal deep learning model for physiological stress detection
PLOS One · 29.10.2026 · 21 (10) · e0360314
DOI: 10.1371/journal.pone.0360314 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 29.10.2026. Verfasst von Ahmed Tibermacine und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Mohamed Khider Biskra, Algeria. Hauptthemen laut MEDLINE: Deep Learning, Stress, Physiological. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Stress is a major contributor to physical and mental health disorders, underscoring the need for reliable and interpretable detection systems. We present an interpretable multimodal deep learning framework that integrates electrocardiogram (ECG), electrodermal activity (EDA), and respiration signals using modality-specific neural architectures complemented by feature-based classical models. To ensure robustness and generalizability, the framework was evaluated under both subject-independent and subject-dependent protocols. Results show that multimodal fusion consistently outperformed single modalities, achieving 94.8% accuracy, 93.9% F1-score, and 0.97 AUC under subject-independent validation, compared with 86–91% accuracy for individual signals. In subject-dependent experiments, performance reached 97.2% accuracy and 96.8% F1-score. Comparative analysis with recent state-of-the-art methods demonstrated the competitiveness of our approach, while ablation studies confirmed the contribution of each modality and fusion strategy. Statistical significance testing with ( p < 0.05) further validated the reliability of these gains. Importantly, interpretability analyses using Grad-CAM and attention visualization provided physiological insights, revealing that the model emphasizes clinically meaningful regions such as ECG R-peaks and phasic EDA fluctuations. By uniting high performance, robustness, and interpretability, this work advances stress detection research and offers a physiologically grounded framework for continuous mental health monitoring.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Science, University of Mohamed Khider Biskra, Algeria.
- Department of Computer, Control and Management Engineering, Sapienza University of Rome, Italy.
- Laboratory of Telecommunications and Smart Systems, Faculty of Sciences and Technologies, University of Djelfa, Djelfa, Algeria.
- Department of Artificial Intelligence, ELTE Eotvos Lorand University, Budapest, Hungary.
- Division of Building Technology and Design, Department of Civil and Architectural Engineering, KTH Royal Institute of Technology, Stockholm, Sweden.
ORCID-Profile: M'hamed Mancer, Mustapha Habib
Zitieren
APA
Tibermacine, A., Tibermacine, I. E., Mancer, M., Rabehi, A., Guettala, W., & Habib, M. (2026). An interpretable multimodal deep learning model for physiological stress detection. PLOS One, 21(10), e0360314. https://doi.org/10.1371/journal.pone.0360314
Vancouver
Tibermacine A, Tibermacine IE, Mancer M, Rabehi A, Guettala W, Habib M. An interpretable multimodal deep learning model for physiological stress detection. PLOS One. 2026;21(10):e0360314. doi:10.1371/journal.pone.0360314
BibTeX
@article{Tibermacine2026,
author = {Tibermacine, Ahmed and Tibermacine, Imad Eddine and Mancer, M'hamed and Rabehi, Abdelaziz and Guettala, Walid and Habib, Mustapha},
title = {An interpretable multimodal deep learning model for physiological stress detection},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {10},
pages = {e0360314},
doi = {10.1371/journal.pone.0360314}
}
EUVIMED