Enhancing Generalization in Arrhythmia Classification with Attention Mechanisms

This research investigates the influence of dataset characteristics on the performance and generalization capabilities of deep learning models, on ECG data. The study evaluates multiple subsets of the TNMG dataset with varying levels of curated characteristics to assess their impact on model performance. Additionally, an attention mechanism is introduced to enhance model accuracy and generalization. The experimental results reveal that models trained on balanced subsets and incorporating the attention mechanism consistently outperform those trained on unbalanced data or without attention, emphasizing the critical importance of dataset balance and attention mechanism for achieving improved model performance. Surprisingly, the largest ECG dataset, TNMG, proved less effective in generalization than smaller, curated subsets. The study demonstrates that a well-balanced and thoughtfully curated dataset, combined with the attention mechanism, can lead to competitive model performance, even with a significantly smaller size. This research on ECG data underscores the critical importance of dataset curation, balance, and attention mechanisms in biomedical machine learning. It highlights that well-balanced, thoughtfully curated datasets with attention mechanisms can outperform larger, unbalanced datasets, challenging conventional notions and offering potential advancements in medical data analysis and patient care.