MedGNN: Towards Multi-resolution Spatiotemporal Graph Learning for Medical Time Series Classification

TL;DR

MedGNN introduces a multi-resolution spatiotemporal graph learning framework that effectively models complex dependencies in medical time series, improving classification accuracy by addressing multi-scale, baseline wander, and multi-view challenges.

Contribution

The paper proposes MedGNN, a novel framework combining adaptive graph structures, difference attention, frequency domain analysis, and multi-resolution transformers for enhanced medical time series classification.

Findings

Outperforms existing methods on real-world datasets

Effectively models multi-scale spatial-temporal dependencies

Addresses baseline wander and multi-view characteristics

Abstract

Medical time series has been playing a vital role in real-world healthcare systems as valuable information in monitoring health conditions of patients. Accurate classification for medical time series, e.g., Electrocardiography (ECG) signals, can help for early detection and diagnosis. Traditional methods towards medical time series classification rely on handcrafted feature extraction and statistical methods; with the recent advancement of artificial intelligence, the machine learning and deep learning methods have become more popular. However, existing methods often fail to fully model the complex spatial dynamics under different scales, which ignore the dynamic multi-resolution spatial and temporal joint inter-dependencies. Moreover, they are less likely to consider the special baseline wander problem as well as the multi-view characteristics of medical time series, which largely hinders their prediction performance. To address these limitations, we propose a Multi-resolution Spatiotemporal Graph Learning framework, MedGNN, for medical time series classification. Specifically, we first propose to construct multi-resolution adaptive graph structures to learn dynamic multi-scale embeddings. Then, to address the baseline wander problem, we propose Difference Attention Networks to operate self-attention mechanisms on the finite difference for temporal modeling. Moreover, to learn the multi-view characteristics, we utilize the Frequency Convolution Networks to capture complementary information of medical time series from the frequency domain. In addition, we introduce the Multi-resolution Graph Transformer architecture to model the dynamic dependencies and fuse the information from different resolutions. Finally, we have conducted extensive experiments on multiple medical real-world datasets that demonstrate the superior performance of our method. Our Code is available.