EARTH: Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph

Guancheng Wan, Zewen Liu, Xiaojun Shan, Max SY Lau, B. Aditya Prakash, Wei Jin

TL;DR: The paper presents EARTH, a framework combining neural ODEs with epidemic mechanisms to improve forecasting by capturing continuous disease transmission dynamics and integrating global trends guided graphs.

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 is available at https://github.com/GuanchengWan/EARTH.

Lay Summary:

Predicting how diseases like COVID-19 or the flu will spread is crucial for protecting public health. Current computer models often struggle because they don't fully capture the constantly changing nature of epidemics or the specific ways diseases transmit between areas, especially when data is patchy or arrives irregularly. They also often overlook how big-picture trends, like national health policies, influence local outbreaks.

We've developed a new AI framework called EARTH to tackle these challenges. EARTH learns how diseases spread over time by combining established knowledge of epidemic progression (like how people become susceptible, infected, and then recover) with a flexible, data-driven approach. Uniquely, it also analyzes overall infection trends across wider regions and uses this global view to understand and dynamically adjust for local transmission patterns. By intelligently blending these global insights with specific local details, EARTH makes more accurate predictions.

Tested on real-world COVID-19 and flu data, EARTH has shown significantly better forecasting performance than existing leading methods. This provides a more robust tool to help public health experts understand disease dynamics and make timely decisions.

Primary Area: Applications->Health / Medicine

Keywords: Graph Learning, Epidemiology, Public Health

Submission Number: 4893