Forecasting Coccidioidomycosis (Valley Fever) in Arizona: A Graph Neural Network Approach

2025-07-14

AI Summary

This study addresses the challenge of predicting coccidioidomycosis (valley fever) incidence in Arizona, USA, by proposing the first graph neural network (GNN)-based forecasting framework for this disease. Methodologically, it integrates multi-source environmental data—including soil properties, meteorological variables, agricultural indicators, and air quality metrics—to construct a dynamic graph structure grounded in variable correlations, explicitly modeling spatial dependencies among environmental factors as well as temporal lags and nonlinear time-series relationships. Its key contribution lies in pioneering the application of GNNs to ecological epidemiological modeling of valley fever, substantially improving both predictive accuracy and mechanistic interpretability. Experimental results demonstrate that the model faithfully reproduces historical epidemic trends and identifies temperature, soil moisture, and PM₁₀ as critical drivers. The framework delivers actionable decision support for early risk warning and optimized allocation of public health resources in high-risk regions.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Coccidioidomycosis, commonly known as Valley Fever, remains a significant public health concern in endemic regions of the southwestern United States. This study develops the first graph neural network (GNN) model for forecasting Valley Fever incidence in Arizona. The model integrates surveillance case data with environmental predictors using graph structures, including soil conditions, atmospheric variables, agricultural indicators, and air quality metrics. Our approach explores correlation-based relationships among variables influencing disease transmission. The model captures critical delays in disease progression through lagged effects, enhancing its capacity to reflect complex temporal dependencies in disease ecology. Results demonstrate that the GNN architecture effectively models Valley Fever trends and provides insights into key environmental drivers of disease incidence. These findings can inform early warning systems and guide resource allocation for disease prevention efforts in high-risk areas.

Problem

• Forecasting Valley Fever incidence in Arizona using GNN
• Integrating environmental predictors with case data via graphs
• Modeling disease ecology with lagged effects and temporal dependencies

Innovation

• Uses Graph Neural Network for Valley Fever forecasting
• Integrates environmental predictors with case data
• Captures temporal dependencies via lagged effects