An AI-enabled Agent-Based Model and Its Application in Measles Outbreak Simulation for New Zealand
This work addresses the need for more efficient and automated ABMs in public health, specifically for simulating measles outbreaks to inform policy decisions, though it appears incremental as it combines existing AI techniques with traditional ABMs.
The authors tackled the problem of enhancing Agent-Based Models (ABMs) for infectious disease simulation by developing a tensorized and differentiable model using Graph Neural Networks and LSTMs, applied to the 2019 measles outbreak in New Zealand, demonstrating accurate simulation of outbreak dynamics, particularly during peak periods.
Agent Based Models (ABMs) have emerged as a powerful tool for investigating complex social interactions, particularly in the context of public health and infectious disease investigation. In an effort to enhance the conventional ABM, enabling automated model calibration and reducing the computational resources needed for scaling up the model, we have developed a tensorized and differentiable agent-based model by coupling Graph Neural Network (GNN) and Long Short-Term Memory (LSTM) network. The model was employed to investigate the 2019 measles outbreak occurred in New Zealand, demonstrating a promising ability to accurately simulate the outbreak dynamics, particularly during the peak period of repeated cases. This paper shows that by leveraging the latest Artificial Intelligence (AI) technology and the capabilities of traditional ABMs, we gain deeper insights into the dynamics of infectious disease outbreaks. This, in turn, helps us make more informed decision when developing effective strategies that strike a balance between managing outbreaks and minimizing disruptions to everyday life.