Reducing Intraspecies and Interspecies Covariate Shift in Traumatic Brain Injury EEG of Humans and Mice Using Transfer Euclidean Alignment

TL;DR

This paper introduces Transfer Euclidean Alignment, a transfer learning method that significantly improves EEG-based traumatic brain injury classification across different datasets and species, addressing variability and data scarcity issues.

Contribution

The paper proposes Transfer Euclidean Alignment, a novel transfer learning technique that enhances model robustness across diverse EEG datasets from humans and mice.

Findings

Average accuracy increase of 14.42% within species

Average accuracy increase of 5.53% across species

Demonstrates effectiveness of transfer learning in biomedical EEG classification

Abstract

While analytics of sleep electroencephalography (EEG) holds certain advantages over other methods in clinical applications, high variability across subjects poses a significant challenge when it comes to deploying machine learning models for classification tasks in the real world. In such instances, machine learning models that exhibit exceptional performance on a specific dataset may not necessarily demonstrate similar proficiency when applied to a distinct dataset for the same task. The scarcity of high-quality biomedical data further compounds this challenge, making it difficult to evaluate the model's generality comprehensively. In this paper, we introduce Transfer Euclidean Alignment - a transfer learning technique to tackle the problem of the dearth of human biomedical data for training deep learning models. We tested the robustness of this transfer learning technique on various rule-based classical machine learning models as well as the EEGNet-based deep learning model by evaluating on different datasets, including human and mouse data in a binary classification task of detecting individuals with versus without traumatic brain injury (TBI). By demonstrating notable improvements with an average increase of 14.42% for intraspecies datasets and 5.53% for interspecies datasets, our findings underscore the importance of the use of transfer learning to improve the performance of machine learning and deep learning models when using diverse datasets for training.