Amplifying Pathological Detection in EEG Signaling Pathways through Cross-Dataset Transfer Learning

TL;DR

This paper demonstrates how transfer learning across EEG datasets can improve pathological detection, especially with limited labeled data, highlighting the importance of model scaling and addressing distribution shifts.

Contribution

It explores the effectiveness of cross-dataset transfer learning in EEG pathology classification, emphasizing model scaling and strategies to mitigate negative transfer.

Findings

Transfer learning improves target model performance with limited labeled data.

Larger models outperform smaller ones in transfer learning scenarios.

Careful evaluation is needed to prevent negative transfer effects.

Abstract

Pathology diagnosis based on EEG signals and decoding brain activity holds immense importance in understanding neurological disorders. With the advancement of artificial intelligence methods and machine learning techniques, the potential for accurate data-driven diagnoses and effective treatments has grown significantly. However, applying machine learning algorithms to real-world datasets presents diverse challenges at multiple levels. The scarcity of labelled data, especially in low regime scenarios with limited availability of real patient cohorts due to high costs of recruitment, underscores the vital deployment of scaling and transfer learning techniques. In this study, we explore a real-world pathology classification task to highlight the effectiveness of data and model scaling and cross-dataset knowledge transfer. As such, we observe varying performance improvements through data scaling, indicating the need for careful evaluation and labelling. Additionally, we identify the challenges of possible negative transfer and emphasize the significance of some key components to overcome distribution shifts and potential spurious correlations and achieve positive transfer. We see improvement in the performance of the target model on the target (NMT) datasets by using the knowledge from the source dataset (TUAB) when a low amount of labelled data was available. Our findings indicate a small and generic model (e.g. ShallowNet) performs well on a single dataset, however, a larger model (e.g. TCN) performs better on transfer and learning from a larger and diverse dataset.