Federated GNNs for EEG-Based Stroke Assessment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Protani, Andrea, Giusti, Lorenzo, Aillet, Albert Sund, Iacovelli, Chiara, Reale, Giuseppe, Sacco, Simona, Manganotti, Paolo, Marinelli, Lucio, Santos, Diogo Reis, Brutti, Pierpaolo, Caliandro, Pietro, Serio, Luigi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915052420857856
author Protani, Andrea
Giusti, Lorenzo
Aillet, Albert Sund
Iacovelli, Chiara
Reale, Giuseppe
Sacco, Simona
Manganotti, Paolo
Marinelli, Lucio
Santos, Diogo Reis
Brutti, Pierpaolo
Caliandro, Pietro
Serio, Luigi
author_facet Protani, Andrea
Giusti, Lorenzo
Aillet, Albert Sund
Iacovelli, Chiara
Reale, Giuseppe
Sacco, Simona
Manganotti, Paolo
Marinelli, Lucio
Santos, Diogo Reis
Brutti, Pierpaolo
Caliandro, Pietro
Serio, Luigi
contents Machine learning (ML) has the potential to become an essential tool in supporting clinical decision-making processes, offering enhanced diagnostic capabilities and personalized treatment plans. However, outsourcing medical records to train ML models using patient data raises legal, privacy, and security concerns. Federated learning has emerged as a promising paradigm for collaborative ML, meeting healthcare institutions' requirements for robust models without sharing sensitive data and compromising patient privacy. This study proposes a novel method that combines federated learning (FL) and Graph Neural Networks (GNNs) to predict stroke severity using electroencephalography (EEG) signals across multiple medical institutions. Our approach enables multiple hospitals to jointly train a shared GNN model on their local EEG data without exchanging patient information. Specifically, we address a regression problem by predicting the National Institutes of Health Stroke Scale (NIHSS), a key indicator of stroke severity. The proposed model leverages a masked self-attention mechanism to capture salient brain connectivity patterns and employs EdgeSHAP to provide post-hoc explanations of the neurological states after a stroke. We evaluated our method on EEG recordings from four institutions, achieving a mean absolute error (MAE) of 3.23 in predicting NIHSS, close to the average error made by human experts (MAE $\approx$ 3.0). This demonstrates the method's effectiveness in providing accurate and explainable predictions while maintaining data privacy.
format Preprint
id arxiv_https___arxiv_org_abs_2411_02286
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Federated GNNs for EEG-Based Stroke Assessment
Protani, Andrea
Giusti, Lorenzo
Aillet, Albert Sund
Iacovelli, Chiara
Reale, Giuseppe
Sacco, Simona
Manganotti, Paolo
Marinelli, Lucio
Santos, Diogo Reis
Brutti, Pierpaolo
Caliandro, Pietro
Serio, Luigi
Machine Learning
Artificial Intelligence
Signal Processing
Machine learning (ML) has the potential to become an essential tool in supporting clinical decision-making processes, offering enhanced diagnostic capabilities and personalized treatment plans. However, outsourcing medical records to train ML models using patient data raises legal, privacy, and security concerns. Federated learning has emerged as a promising paradigm for collaborative ML, meeting healthcare institutions' requirements for robust models without sharing sensitive data and compromising patient privacy. This study proposes a novel method that combines federated learning (FL) and Graph Neural Networks (GNNs) to predict stroke severity using electroencephalography (EEG) signals across multiple medical institutions. Our approach enables multiple hospitals to jointly train a shared GNN model on their local EEG data without exchanging patient information. Specifically, we address a regression problem by predicting the National Institutes of Health Stroke Scale (NIHSS), a key indicator of stroke severity. The proposed model leverages a masked self-attention mechanism to capture salient brain connectivity patterns and employs EdgeSHAP to provide post-hoc explanations of the neurological states after a stroke. We evaluated our method on EEG recordings from four institutions, achieving a mean absolute error (MAE) of 3.23 in predicting NIHSS, close to the average error made by human experts (MAE $\approx$ 3.0). This demonstrates the method's effectiveness in providing accurate and explainable predictions while maintaining data privacy.
title Federated GNNs for EEG-Based Stroke Assessment
topic Machine Learning
Artificial Intelligence
Signal Processing
url https://arxiv.org/abs/2411.02286