Finding Neural Biomarkers for Motor Learning and Rehabilitation Using an Explainable Graph Neural Network
Human motor learning is a neural process essential for acquiring new motor skills and adapting existing ones, which is fundamental to everyday activities. Neurological disorders such as Parkinson’s Disease (PD) and stroke can significantly affect human motor functions. Identifying neural...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10843258/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583207127613440 |
|---|---|
| author | J. Han A. Embs F. Nardi S. Haar A. A. Faisal |
| author_facet | J. Han A. Embs F. Nardi S. Haar A. A. Faisal |
| author_sort | J. Han |
| collection | DOAJ |
| description | Human motor learning is a neural process essential for acquiring new motor skills and adapting existing ones, which is fundamental to everyday activities. Neurological disorders such as Parkinson’s Disease (PD) and stroke can significantly affect human motor functions. Identifying neural biomarkers for human motor learning is essential for advancing therapeutic strategies for such disorders. However, identifying specific neural biomarkers associated with motor learning has been challenging due to the complex nature of brain activity and the limitations of traditional data analysis techniques. In response to these challenges, we developed a novel Spatial Graph Neural Network (SGNN) model to predict motor learning outcomes from electroencephalogram (EEG) data using the spatial-temporal dynamics of brain activity. We used it to analyse EEG data collected during a visuomotor rotation (VMR) task designed to elicit distinct types of learning: error-based and reward-based. By doing so, we establish a controlled environment that allows for precisely investigating neural signatures associated with these learning processes. To understand the features learned by the SGNN, we used a set of spatial, spectral, and temporal explainability methods to identify the brain regions and temporal dynamics crucial for learning. These approaches offer comprehensive insights into the neural biomarkers, aligning with current literature and ablation studies, and pave the way for applying this methodology to find biomarkers from various brain signals and tasks. |
| format | Article |
| id | doaj-art-103444885154452ca3c51c4bd0e727e4 |
| institution | Kabale University |
| issn | 1534-4320 1558-0210 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj-art-103444885154452ca3c51c4bd0e727e42025-01-29T00:00:02ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102025-01-013355456510.1109/TNSRE.2025.353011010843258Finding Neural Biomarkers for Motor Learning and Rehabilitation Using an Explainable Graph Neural NetworkJ. Han0https://orcid.org/0000-0003-0156-5065A. Embs1F. Nardi2https://orcid.org/0000-0001-6159-0831S. Haar3https://orcid.org/0000-0003-2213-6585A. A. Faisal4https://orcid.org/0000-0003-0813-7207Department of Computing, Brain and Behavior Laboratory, Imperial College London, London, U.K.Department of Computing, Brain and Behavior Laboratory, Imperial College London, London, U.K.Department of Computing, UKRI Centre for Doctoral Training in AI for Healthcare and the Brain and Behavior Laboratory, Imperial College London, London, U.K.Department of Brain Sciences, UK Dementia Research Institute Care Research and Technology Centre, Imperial College London, London, U.K.Department of Bioengineering, Brain and Behavior Laboratory, Imperial College London, London, U.K.Human motor learning is a neural process essential for acquiring new motor skills and adapting existing ones, which is fundamental to everyday activities. Neurological disorders such as Parkinson’s Disease (PD) and stroke can significantly affect human motor functions. Identifying neural biomarkers for human motor learning is essential for advancing therapeutic strategies for such disorders. However, identifying specific neural biomarkers associated with motor learning has been challenging due to the complex nature of brain activity and the limitations of traditional data analysis techniques. In response to these challenges, we developed a novel Spatial Graph Neural Network (SGNN) model to predict motor learning outcomes from electroencephalogram (EEG) data using the spatial-temporal dynamics of brain activity. We used it to analyse EEG data collected during a visuomotor rotation (VMR) task designed to elicit distinct types of learning: error-based and reward-based. By doing so, we establish a controlled environment that allows for precisely investigating neural signatures associated with these learning processes. To understand the features learned by the SGNN, we used a set of spatial, spectral, and temporal explainability methods to identify the brain regions and temporal dynamics crucial for learning. These approaches offer comprehensive insights into the neural biomarkers, aligning with current literature and ablation studies, and pave the way for applying this methodology to find biomarkers from various brain signals and tasks.https://ieeexplore.ieee.org/document/10843258/Brain-computer interfaceEEGhuman motor learninggraph neural networkexplainable AIXAI |
| spellingShingle | J. Han A. Embs F. Nardi S. Haar A. A. Faisal Finding Neural Biomarkers for Motor Learning and Rehabilitation Using an Explainable Graph Neural Network IEEE Transactions on Neural Systems and Rehabilitation Engineering Brain-computer interface EEG human motor learning graph neural network explainable AI XAI |
| title | Finding Neural Biomarkers for Motor Learning and Rehabilitation Using an Explainable Graph Neural Network |
| title_full | Finding Neural Biomarkers for Motor Learning and Rehabilitation Using an Explainable Graph Neural Network |
| title_fullStr | Finding Neural Biomarkers for Motor Learning and Rehabilitation Using an Explainable Graph Neural Network |
| title_full_unstemmed | Finding Neural Biomarkers for Motor Learning and Rehabilitation Using an Explainable Graph Neural Network |
| title_short | Finding Neural Biomarkers for Motor Learning and Rehabilitation Using an Explainable Graph Neural Network |
| title_sort | finding neural biomarkers for motor learning and rehabilitation using an explainable graph neural network |
| topic | Brain-computer interface EEG human motor learning graph neural network explainable AI XAI |
| url | https://ieeexplore.ieee.org/document/10843258/ |
| work_keys_str_mv | AT jhan findingneuralbiomarkersformotorlearningandrehabilitationusinganexplainablegraphneuralnetwork AT aembs findingneuralbiomarkersformotorlearningandrehabilitationusinganexplainablegraphneuralnetwork AT fnardi findingneuralbiomarkersformotorlearningandrehabilitationusinganexplainablegraphneuralnetwork AT shaar findingneuralbiomarkersformotorlearningandrehabilitationusinganexplainablegraphneuralnetwork AT aafaisal findingneuralbiomarkersformotorlearningandrehabilitationusinganexplainablegraphneuralnetwork |