Side-aware Meta-Learning for Cross-Dataset Listener Diagnosis with Subjective Tinnitus

TL;DR

This paper introduces a side-aware meta-learning approach for cross-dataset tinnitus diagnosis using EEG data, enabling effective classification across diverse patient demographics and data collection methods without large datasets.

Contribution

It proposes a novel side-aware meta-learning framework with subject-specific training for improved cross-dataset tinnitus diagnosis.

Findings

Achieved 73.8% accuracy in cross-dataset classification

Demonstrated the effectiveness of side information in model performance

Showed meta-learning reduces dependence on large datasets

Abstract

With the development of digital technology, machine learning has paved the way for the next generation of tinnitus diagnoses. Although machine learning has been widely applied in EEG-based tinnitus analysis, most current models are dataset-specific. Each dataset may be limited to a specific range of symptoms, overall disease severity, and demographic attributes; further, dataset formats may differ, impacting model performance. This paper proposes a side-aware meta-learning for cross-dataset tinnitus diagnosis, which can effectively classify tinnitus in subjects of divergent ages and genders from different data collection processes. Owing to the superiority of meta-learning, our method does not rely on large-scale datasets like conventional deep learning models. Moreover, we design a subject-specific training process to assist the model in fitting the data pattern of different patients or healthy people. Our method achieves a high accuracy of 73.8\% in the cross-dataset classification. We conduct an extensive analysis to show the effectiveness of side information of ears in enhancing model performance and side-aware meta-learning in improving the quality of the learned features.