Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph

TL;DR

An innovative end-to-end framework called Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph (EARTH) is introduced, which seamlessly integrates the neural ODE approach with the epidemic mechanism, considering the complex spatial spread process during epidemic evolution.

Abstract

Effective epidemic forecasting is critical for public health strategies and efficient medical resource allocation, especially in the face of rapidly spreading infectious diseases. However, existing deep-learning methods often overlook the dynamic nature of epidemics and fail to account for the specific mechanisms of disease transmission. In response to these challenges, we introduce an innovative end-to-end framework called Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph (EARTH) in this paper. To learn continuous and regional disease transmission patterns, we first propose EANO, which seamlessly integrates the neural ODE approach with the epidemic mechanism, considering the complex spatial spread process during epidemic evolution. Additionally, we introduce GLTG to model global infection trends and leverage these signals to guide local transmission dynamically. To accommodate both the global coherence of epidemic trends and the local nuances of epidemic transmission patterns, we build a cross-attention approach to fuse the most meaningful information for forecasting. Through the smooth synergy of both components, EARTH offers a more robust and flexible approach to understanding and predicting the spread of infectious diseases. Extensive experiments show EARTH superior performance in forecasting real-world epidemics compared to state-of-the-art methods. The code will be available at https://github.com/Emory-Melody/EpiLearn.

Figures (6)

• Figure 1: Problem illustration. Considering both evolution of regional correlation signals and irregular sampling observation intervals facts, we focus on the continuous-time epidemic system. But existing solutions fail to I) learn disease transmission patterns with epidemic mechanism and II) address missing states. Additionally, they omit to III) learn global trends caused by external factors (e.g., lockdowns) while developing dynamic regional transmission.
• Figure 2: Architecture illustration of Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph. EARTH is a general and end-to-end framework that can flexibly capture the time-continuous epidemic mechanism. Best viewed in color.
• Figure 3: Visualization of predicted cases. We randomly pick two regions in the Australia-COVID dataset with horizon 10. It shows that EARTH fits the ground truth well and follows the developing trend of epidemics. Better view in enlarged.
• Figure 4: Learned Regional Graph in GLTG. We visualize top-3 weighted edges for each region in the US-States dataset, excluding states with no available data.
• Figure 5: Analysis on hyper-parameter. Performance with hyper-parameter $N_\mathcal{T}$ and $k$, where red, yellow, and green represent the Australia-COVID, US-States, and US-Region respectively.