CoChat

Integrating EEG and Machine Learning to Analyze Brain Changes during the Rehabilitation of Broca’s Aphasia

Open access
Močilnik, Vanesa, Rutar Gorišek, Veronika, Sajovic, Jakob, Pretnar Oblak, Janja, Drevenšek, Gorazd, Rogelj, Peter · 2024 · Sensors

The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.

Abstract

The fusion of electroencephalography (EEG) with machine learning is transforming rehabilitation. Our study introduces a neural network model proficient in distinguishing pre- and post-rehabilitation states in patients with Broca’s aphasia, based on brain connectivity metrics derived from EEG recordings during verbal and spatial working memory tasks. The Granger causality (GC), phase-locking value (PLV), weighted phase-lag index (wPLI), mutual information (MI), and complex Pearson correlation coefficient (CPCC) across the delta, theta, and low- and high-gamma bands were used (excluding GC, which spanned the entire frequency spectrum). Across eight participants, employing leave-one-out validation for each, we evaluated the intersubject prediction accuracy across all connectivity methods and frequency bands. GC, MI theta, and PLV low-gamma emerged as the top performers, achieving 89.4%, 85.8%, and 82.7% accuracy in classifying verbal working memory task data. Intriguingly, measures designed to eliminate volume conduction exhibited the poorest performance in predicting rehabilitation-induced brain changes. This observation, coupled with variations in model performance across frequency bands, implies that different connectivity measures capture distinct brain processes involved in rehabilitation. The results of this paper contribute to current knowledge by presenting a clear strategy of utilizing limited data to achieve valid and meaningful results of machine learning on post-stroke rehabilitation EEG data, and they show that the differences in classification accuracy likely reflect distinct brain processes underlying rehabilitation after stroke.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/s24020329

Cites

37 of 37 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Lesion density maps for our subjects. A more intense yellow color denotes the more frequent occurrence of a lesion in that area. The brightest yellow shows that 6 or more subjects had a lesion there. L and R letters denote the left and right side of the head, respectively, to avoid confusion with MRI image display conventions.
Figure 1 Lesion density maps for our subjects. A more intense yellow color denotes the more frequent occurrence of a lesion in that area. The brightest yellow shows that 6 or more subjects had a lesion there. L and R letters denote the left and right side of the head, respectively, to avoid confusion with MRI image display conventions.CC BY · PubMed Central
Figure 2 The 10% most significant changes in Granger causality (GC) before and after rehabilitation for Broca’s aphasia, during a verbal working memory task. The size of the node indicates a stronger correlation with other nodes, whereas the color of the lines connecting the electrodes can be ignored—the color hues are used for visualization purposes only.
Figure 2 The 10% most significant changes in Granger causality (GC) before and after rehabilitation for Broca’s aphasia, during a verbal working memory task. The size of the node indicates a stronger correlation with other nodes, whereas the color of the lines connecting the electrodes can be ignored—the color hues are used for visualization purposes only.CC BY · PubMed Central
Figure 3 Machine learning model layers.
Figure 3 Machine learning model layers.CC BY · PubMed Central
Figure 4 Accuracies and their distributions for classification of EEG to distinguish the state before and after the rehabilitation for the verbal memory task. Each column in the same color represents a connectivity measure, computed for frequency bands shown in rows. Dots on the graph represent individual data points, i.e., accuracies obtained in the leave-one-out cases.
Figure 4 Accuracies and their distributions for classification of EEG to distinguish the state before and after the rehabilitation for the verbal memory task. Each column in the same color represents a connectivity measure, computed for frequency bands shown in rows. Dots on the graph represent individual data points, i.e., accuracies obtained in the leave-one-out cases.CC BY · PubMed Central
Figure 5 Accuracies and their distributions for classification of EEG to distinguish the state before and after the rehabilitation for the spatial memory task. Each column in the same color represents a connectivity measure, computed for frequency bands shown in rows. Dots on the graph represent individual data points, i.e., accuracies obtained in the leave-one-out cases.
Figure 5 Accuracies and their distributions for classification of EEG to distinguish the state before and after the rehabilitation for the spatial memory task. Each column in the same color represents a connectivity measure, computed for frequency bands shown in rows. Dots on the graph represent individual data points, i.e., accuracies obtained in the leave-one-out cases.CC BY · PubMed Central
Figure 6 Average ROC curves for the best-performing methods when using verbal working memory data on the left and spatial working memory data on the right. Every line of a certain color represents a method–frequency combination being classified in the post-rehabilitation class.
Figure 6 Average ROC curves for the best-performing methods when using verbal working memory data on the left and spatial working memory data on the right. Every line of a certain color represents a method–frequency combination being classified in the post-rehabilitation class.CC BY · PubMed Central
Figure 7 Mean confusion matrices for the best-performing methods, using verbal working memory data on the left and spatial working memory data on the right.
Figure 7 Mean confusion matrices for the best-performing methods, using verbal working memory data on the left and spatial working memory data on the right.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

4 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 1

  1. Touretzky, D., Mozer, M., and Hasselmo, M. (1995). Advances in Neural Information Processing Systems, MIT Press.

Cited by

See all 8

Metadata

Authors
Močilnik, V., Rutar Gorišek, V., Sajovic, J., Pretnar Oblak, J., Drevenšek, G., & Rogelj, P.
Affiliations
  • University of Ljubljana (SI)
  • University Medical Centre Ljubljana, 1000 Ljubljana, Slovenia
  • Faculty of Medicine, University of Ljubljana, 1000 Ljubljana, Slovenia
  • University of Primorska (SI)
Corresponding author
Sajovic, Jakob
Venue
Sensors
Publisher
MDPI AG
Published
2024-01-05
Volume
24
Issue
2
Pages
329
ISSN
1424-8220 (ISSN-L)
OpenAlex
W4390608048
Cited by
8
References
37
Citations by year
2026: 3 · 2025: 3 · 2024: 2
FWCI
1.94
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Javna Agencija za Raziskovalno Dejavnost RS (P3-0293, P5-0110, P3-0338)
Topics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
  • Health Sciences › Medicine › Rehabilitation › Stroke Rehabilitation and Recovery
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Functional Brain Connectivity Studies
Keywords
Broca's aphasia, stroke rehabilitation, EEG, brain connectivity, Granger causality, phase locking value, weighted phase lag index, mutual information, working memory, volume conduction, gamma band, neural network classification
MeSH terms
Machine Learning, Aphasia, Brain, Electroencephalography, Humans, Memory, Short-Term

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.