Decentralized EEG-based detection of major depressive disorder via transformer architectures and split learning
These findings demonstrate that distributed deep learning pipelines can deliver precise MDD detection from EEG data without compromising data security. Proposed framework keeps data on local nodes and only exchanges intermediate representations. This approach meets institutional privacy requirements while providing robust classification outcomes.
Authors
- Muhammad Shahbaz Khan (ORCID: https://orcid.org/0000-0002-7166-6681)
- Nada Alasbali (ORCID: https://orcid.org/0000-0003-2541-7876)
- Muhammad Umair (ORCID: https://orcid.org/0000-0003-3971-2067)
- Oumaima Saidani (ORCID: https://orcid.org/0000-0001-9520-3174)
- Muhammad Fainan Hanif (ORCID: https://orcid.org/0000-0002-0273-8258)
- Jawad Ahmad
- Aizaz Ahmad Khattak
Institutions
- Princess Nourah bint Abdulrahman University (SA)
- Prince Mohammad bin Fahd University (SA)
- Multimedia University (MY)
- Edinburgh Napier University (GB)
- Örebro University (SE)
- King Khalid University (SA)
Publication Details
- Journal
- Frontiers in Computational Neuroscience
- Published
- 2025-04-16
- DOI
- https://doi.org/10.3389/fncom.2025.1569828
- Citations
- 6
- Primary Topic
- EEG and Brain-Computer Interfaces
- Type
- article
- Field-Weighted Citation Impact
- 8.59
Funders
- Princess Nourah Bint Abdulrahman University
- King Khalid University