Finding Neural Biomarkers for Motor Learning and Rehabilitation Using an Explainable Graph Neural Network

作     者：Han, J. Embs, A. Nardi, F. Haar, S. Faisal, A. A. 

作者机构：Imperial Coll London Dept Comp Brain & Behav Lab London SW7 2AZ England Imperial Coll London UKRI Ctr Doctoral Training AI Healthcare Dept Comp London SW7 2AZ England Imperial Coll London Dept Brain Sci London W12 0BZ England Imperial Coll London UK Dementia Res Inst Care Res & Technol Ctr London W12 0BZ England Imperial Coll London Dept Bioengn London SW7 2AZ England Univ Bayreuth Chair Digital Hlth & Data Sci D-95447 Bayreuth Germany 

出 版 物：《IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING》 (IEEE Trans. Neural Syst. Rehabil. Eng.)

年 卷 期：2025年第33卷

页      面：554-565页

核心收录：

学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 1002[医学-临床医学] 0808[工学-电气工程] 08[工学] 

基　　金：U.K. Research and Innovation (UKRI) Centre for Doctoral Training in Artificial Intelligence (AI) for Healthcare [EP/S023283/1] Edmond and Lily Safra Fellowship Program UK Dementia Research Institute Care Research and Technology Centre UKRI Turing AI Fellowship [EP/V025449/1] 

主　　题：Motors Electroencephalography Biomarkers Brain modeling Feature extraction Biological system modeling Graph neural networks Deep learning Data models Recurrent neural networks Brain-computer interface EEG human motor learning graph neural network explainable AI XAI 

摘      要：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.