TransformEEG: Towards Improving Model Generalizability in Deep Learning-based EEG Parkinson's Disease Detection

2025-07-10

AI Summary

To address substantial inter-subject variability and poor generalizability of existing deep learning models in electroencephalography (EEG)-based Parkinson’s disease (PD) detection, this paper proposes a novel hybrid convolutional–Transformer architecture. The core innovation is a channel-specific depthwise tokenizer that generates highly discriminative feature tokens, thereby enhancing cross-channel feature fusion within the Transformer’s self-attention mechanism. Additionally, EEG-specific data augmentation and threshold calibration strategies are integrated to optimize spatiotemporal feature modeling. Evaluated on four public EEG datasets, the model achieves a median balanced accuracy of 80.10% with a narrow interquartile range of 5.74%, significantly outperforming state-of-the-art methods. These results demonstrate superior robustness and strong potential for clinical deployment in PD screening.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Electroencephalography (EEG) is establishing itself as an important, low-cost, noninvasive diagnostic tool for the early detection of Parkinson's Disease (PD). In this context, EEG-based Deep Learning (DL) models have shown promising results due to their ability to discover highly nonlinear patterns within the signal. However, current state-of-the-art DL models suffer from poor generalizability caused by high inter-subject variability. This high variability underscores the need for enhancing model generalizability by developing new architectures better tailored to EEG data. This paper introduces TransformEEG, a hybrid Convolutional-Transformer designed for Parkinson's disease detection using EEG data. Unlike transformer models based on the EEGNet structure, TransformEEG incorporates a depthwise convolutional tokenizer. This tokenizer is specialized in generating tokens composed by channel-specific features, which enables more effective feature mixing within the self-attention layers of the transformer encoder. To evaluate the proposed model, four public datasets comprising 290 subjects (140 PD patients, 150 healthy controls) were harmonized and aggregated. A 10-outer, 10-inner Nested-Leave-N-Subjects-Out (N-LNSO) cross-validation was performed to provide an unbiased comparison against seven other consolidated EEG deep learning models. TransformEEG achieved the highest balanced accuracy's median (78.45%) as well as the lowest interquartile range (6.37%) across all the N-LNSO partitions. When combined with data augmentation and threshold correction, median accuracy increased to 80.10%, with an interquartile range of 5.74%. In conclusion, TransformEEG produces more consistent and less skewed results. It demonstrates a substantial reduction in variability and more reliable PD detection using EEG data compared to the other investigated models.

Problem

• Improving EEG-based Parkinson's detection model generalizability
• Addressing high inter-subject variability in EEG data
• Enhancing feature mixing in transformer architectures for EEG

Innovation

• Hybrid Convolutional-Transformer for EEG analysis
• Depthwise convolutional tokenizer for channel-specific features
• Nested cross-validation for unbiased model comparison