A novel deep learning approach for privacy-preserving encoded EEG-based brain-computer interfaces with clinical LLM applications.

Overview

Authors: Taslima Khanam¹, Siuly Siuly¹, Kate Wang², Hua Wang¹

ORCID iDs: Taslima Khanam

Institute for Sustainable Industries & Liveable Cities, Victoria University, Melbourne, VIC Australia
Royal Melbourne Institute of Technology (RMIT), Melbourne, VIC Australia

Institutions: Victoria University (Australia); RMIT University (Australia)

Journal: Health information science and systems, volume 14, issue 1, article 73

Dates: received 24 May 2025; accepted 19 June 2026; published online 8 July 2026

Type: Research article · Language: English

License: CC BY

Identifiers: DOI 10.1007/s13755-026-00470-x · PMID 42428243 · PMCID PMC13346371 · OpenAlex W7167737035

Open access: hybrid, a free copy (OpenAlex)

Status: data only (how the code is found and verified)

Categories: EEG (modality), clinical / translational (subfield)

Methods: Spectral & time-frequency, Statistics, Connectivity, Machine learning

Keywords: Electroencephalogram, Brain-computer interfaces, Deep denoising structure-preserving neural encoding network, Neural network, Large language models

Topic: EEG and Brain-Computer Interfaces (Cognitive Neuroscience, Neuroscience), according to OpenAlex

Funding: Victoria University

Citations: not cited yet (Europe PMC); 27 references in the paper

Abstract

Purpose: The rise of large language models (LLMs) such as GPT-4 and DeepSeek has transformed healthcare information processing by enabling natural language-based clinical reasoning. However, the integration of LLMs with privacy-sensitive biomedical signals, particularly electroencephalogram (EEG) data used in brain-computer interface (BCI) systems, remains underexplored. EEG signals, especially during motor imagery (MI) tasks, are critical for assistive neurotechnologies but pose significant privacy risks due to their capacity to reveal cognitive and medical information. Traditional encryption techniques often distort signal structure or require decryption with additional noise, compromising classification performance and real-time usability.

Methods: To address this gap, we propose a deep denoising structure-preserving neural encoding network (DSNet) that enables accurate classification of privacy-preserving encoded EEG representations without requiring decryption. EEG features were extracted using common spatial pattern (CSP) and transformed into privacy-preserving encoded representations while preserving their statistical structure. Here, encoding refers to a non-reversible neural transformation designed for privacy preservation rather than a formal cryptographic guarantee. Two deep learning architectures, a feedforward neural network (NN) and a recurrent neural network (RNN), were evaluated for classification in the encoded feature space. Furthermore, we integrated an LLM (GPT-4) to generate clinical-style summaries based on model outputs, enhancing interpretability for clinician review and potential clinical support use.

Results and conclusion: Using publicly available datasets, DSNet-NN achieved over 87% accuracy for every subject, outperforming both the RNN variant and baseline models. It also demonstrated resilience to simulated privacy attacks. LLM-generated reports provided clinician-friendly interpretations of MI predictions, supporting potential real-world applicability. This study introduces an AI framework that bridges privacy-preserving EEG decoding with LLM-based clinical reasoning, offering a practical solution for privacy-preserving neurorehabilitation and digital health systems.

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

bbci.de/competition/iv, at bbci.de; found in “Data Availability”
bnci-horizon-2020.eu/database/data-sets, at bnci-horizon-2020.eu; found in “Data Availability”

Data Availability

The datasets used in this study are publicly available. It can be accessed at: https://www.bbci.de/competition/iv/#dataset2a and https://bnci-horizon-2020.eu/database/data-sets

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 2, 28 September 2026

Funding: added Victoria University

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 4 authors, 5 keywords, 6 references.

Cite

This paper

Khanam, T., Siuly, S., Wang, K., & Wang, H. (2026). A novel deep learning approach for privacy-preserving encoded EEG-based brain-computer interfaces with clinical LLM applications. Health information science and systems, 14(1), 73. https://doi.org/10.1007/s13755-026-00470-x

BibTeX

@article{khanam2026novel, author = {Khanam, Taslima and Siuly, Siuly and Wang, Kate and Wang, Hua}, title = {{A novel deep learning approach for privacy-preserving encoded EEG-based brain-computer interfaces with clinical LLM applications}}, journal = {Health information science and systems}, year = {2026}, month = jul, volume = {14}, number = {1}, pages = {73}, publisher = {Springer}, issn = {2047-2501}, doi = {10.1007/s13755-026-00470-x}, url = {https://doi.org/10.1007/s13755-026-00470-x}, pmid = {42428243}, pmcid = {PMC13346371} }

RIS

TY - JOUR AU - Khanam, Taslima AU - Siuly, Siuly AU - Wang, Kate AU - Wang, Hua TI - A novel deep learning approach for privacy-preserving encoded EEG-based brain-computer interfaces with clinical LLM applications T2 - Health information science and systems J2 - Health Inf Sci Syst PY - 2026 DA - 2026/07/08 VL - 14 IS - 1 SP - 73 SN - 2047-2501 PB - Springer DO - 10.1007/s13755-026-00470-x UR - https://doi.org/10.1007/s13755-026-00470-x LA - en ER -

CSL-JSON

{ "id": "10.1007/s13755-026-00470-x", "type": "article-journal", "title": "A novel deep learning approach for privacy-preserving encoded EEG-based brain-computer interfaces with clinical LLM applications", "container-title": "Health information science and systems", "author": [ { "family": "Khanam", "given": "Taslima" }, { "family": "Siuly", "given": "Siuly" }, { "family": "Wang", "given": "Kate" }, { "family": "Wang", "given": "Hua" } ], "container-title-short": "Health Inf Sci Syst", "volume": "14", "issue": "1", "page": "73", "DOI": "10.1007/s13755-026-00470-x", "PMID": "42428243", "PMCID": "PMC13346371", "ISSN": "2047-2501", "publisher": "Springer", "URL": "https://doi.org/10.1007/s13755-026-00470-x", "language": "en", "issued": { "date-parts": [ [ 2026, 7, 8 ] ] } }

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.