Montage-agnostic federated learning for privacy-preserving Alzheimer’s disease classification from heterogeneous multi-site EEG
- 1Faculty of Medicine, Damascus University
- 2Faculty of Information Technology, Syrian Virtual University
- 3Faculty of Information Technology Engineering, Damascus University
Abstract
Federated learning (FL) lets institutions train shared models without moving raw data, attractive for clinical electroencephalography (EEG), where cohorts are small and privacy-sensitive. Two obstacles persist: clinical sites record EEG with different electrode montages, so input feature spaces differ and standard aggregation fails; and because one recording yields thousands of epochs, splitting epochs rather than subjects leaks subject identity and inflates accuracy. We present MontageFL, a montage-agnostic pipeline that maps any electrode configuration to a fixed 88-dimensional feature vector through region-based aggregation of spectral and covariance features, letting a 19-channel and an 11-channel site train together. Benchmarking centralized, local, FedAvg, and FedProx training for Alzheimer’s disease versus healthy-control classification (Miltiadous et al. dataset; 65 subjects) under strictly subject-level, leakage-free evaluation, subject-level accuracy reached approximately 74% (19-channel) and 89% (11-channel), with no detected difference between federated and local models (FedProx versus local, −1.8 pp; 95% CI [−6.3, +2.7] ), consistent with parity but unable to exclude a modest effect given the small cohort. Evaluated with epoch-level splitting, the same pipeline scored 15–30 points higher, illustrating leakage-driven inflation. Because montage heterogeneity was simulated by channel subsetting within one acquisition system, validation on independent recording hardware remains future work.
Related
- Federated learning for privacy-preserving opportunistic screening of lumbar-spine DXA-defined osteoporotic-level bone mineral density using chest radiographs: A multi-center independent validation study
- Privacy-preserving clustered federated learning via differential privacy and homomorphically encrypted prototypes
- A privacy-preserving multicenter framework for lung nodule segmentation in low-dose CT using an F1-score-weighted federated 3D Transformer-UNet
- Dental arch classification using deep learning and federated learning on DenPAR radiographs
- Multi-Platform Transcriptomic Classification of LUAD Driver Mutation Subtypes via Heterogeneous Ensemble Learning
BibTeX
@article{masry2026montageagnostic,
title = {{Montage-agnostic federated learning for privacy-preserving Alzheimer’s disease classification from heterogeneous multi-site EEG}},
author = {Bahaa Masry and Anas Shahin and George Karraz},
journal = {Scientific Reports},
year = {2026},
month = aug,
doi = {10.1038/s41598-026-65986-4},
url = {https://doi.org/10.1038/s41598-026-65986-4},
note = {CC BY},
}
RIS
TY - JOUR
TI - Montage-agnostic federated learning for privacy-preserving Alzheimer’s disease classification from heterogeneous multi-site EEG
AU - Bahaa Masry
AU - Anas Shahin
AU - George Karraz
PY - 2026
DA - 2026/08/01
JO - Scientific Reports
DO - 10.1038/s41598-026-65986-4
UR - https://doi.org/10.1038/s41598-026-65986-4
AB - Federated learning (FL) lets institutions train shared models without moving raw data, attractive for clinical electroencephalography (EEG), where cohorts are small and privacy-sensitive. Two obstacles persist: clinical sites record EEG with different electrode montages, so input feature spaces differ and standard aggregation fails; and because one recording yields thousands of epochs, splitting epochs rather than subjects leaks subject identity and inflates accuracy. We present MontageFL, a montage-agnostic pipeline that maps any electrode configuration to a fixed 88-dimensional feature vector through region-based aggregation of spectral and covariance features, letting a 19-channel and an 11-channel site train together. Benchmarking centralized, local, FedAvg, and FedProx training for Alzheimer’s disease versus healthy-control classification (Miltiadous et al. dataset; 65 subjects) under strictly subject-level, leakage-free evaluation, subject-level accuracy reached approximately 74% (19-channel) and 89% (11-channel), with no detected difference between federated and local models (FedProx versus local, −1.8 pp; 95% CI [−6.3, +2.7] ), consistent with parity but unable to exclude a modest effect given the small cohort. Evaluated with epoch-level splitting, the same pipeline scored 15–30 points higher, illustrating leakage-driven inflation. Because montage heterogeneity was simulated by channel subsetting within one acquisition system, validation on independent recording hardware remains future work.
SN - 2045-2322
ER -