Channel-Imposed Fusion: A Simple yet Effective Method for Medical Time Series Classification

2025-05-31

AI Summary

To address the poor interpretability and high computational complexity of Transformer-based models in classifying medical time-series signals (e.g., EEG/ECG), this paper proposes a Channel-Imposed Fusion (CIF) mechanism integrated with a lightweight Temporal Convolutional Network (TCN) to form an interpretable classification framework. CIF explicitly models inter-channel dependencies via cross-channel feature alignment and weighted aggregation, enhancing signal-to-noise ratio and suppressing redundancy; TCN ensures architectural transparency and efficient inference. This work is the first to embed channel-level interpretability directly into the temporal modeling backbone. Evaluated on multiple public EEG/ECG benchmarks, the method surpasses state-of-the-art approaches, achieving significant improvements in accuracy and F1-score. Moreover, it enables intuitive visualization of per-channel contribution, thereby balancing high performance with clinical trustworthiness.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Transparent, Interpretable, Explainable ML
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Security and Privacy: Data transparency and provenance

Abstract

The automatic classification of medical time series signals, such as electroencephalogram (EEG) and electrocardiogram (ECG), plays a pivotal role in clinical decision support and early detection of diseases. Although Transformer based models have achieved notable performance by implicitly modeling temporal dependencies through self-attention mechanisms, their inherently complex architectures and opaque reasoning processes undermine their trustworthiness in high stakes clinical settings. In response to these limitations, this study shifts focus toward a modeling paradigm that emphasizes structural transparency, aligning more closely with the intrinsic characteristics of medical data. We propose a novel method, Channel Imposed Fusion (CIF), which enhances the signal-to-noise ratio through cross-channel information fusion, effectively reduces redundancy, and improves classification performance. Furthermore, we integrate CIF with the Temporal Convolutional Network (TCN), known for its structural simplicity and controllable receptive field, to construct an efficient and explicit classification framework. Experimental results on multiple publicly available EEG and ECG datasets demonstrate that the proposed method not only outperforms existing state-of-the-art (SOTA) approaches in terms of various classification metrics, but also significantly enhances the transparency of the classification process, offering a novel perspective for medical time series classification.

Problem

• Improving medical time series classification transparency
• Enhancing signal-to-noise ratio via cross-channel fusion
• Combining CIF with TCN for efficient classification

Innovation

• Channel-Imposed Fusion for cross-channel information
• Integration with Temporal Convolutional Network
• Enhances signal-to-noise ratio and transparency