Epidemic-guided deep learning for spatiotemporal forecasting of Tuberculosis outbreak

2025-02-15

AI Summary

Accurately forecasting spatiotemporal tuberculosis (TB) outbreaks remains challenging due to complex disease dynamics and surveillance noise. Method: We propose an interpretable early-warning framework integrating mechanistic modeling with deep learning. We introduce a novel “epidemic-guided modeling paradigm” that embeds a networked SIR model with saturated incidence and graph Laplacian diffusion into dual-path neural architectures—EGDL-Parallel and EGDL-Series—and estimate parameters via Bayesian MCMC. We theoretically establish global system stability and quantify prediction uncertainty using conformal prediction. Results: Evaluated on real TB incidence data from Japan’s 47 prefectures, our method significantly mitigates overfitting and surveillance noise, achieving high accuracy in short- to medium-term forecasts. It enhances both the reliability and interpretability of public health intervention decisions, offering a principled, data-informed approach to TB outbreak preparedness.

Technology Category

Reasoning under Uncertainty: Relational Probabilistic ModelsMachine Learning: Graph-based Machine LearningPlanning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsUser Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalizationSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Tuberculosis (TB) remains a formidable global health challenge, driven by complex spatiotemporal transmission dynamics and influenced by factors such as population mobility and behavioral changes. We propose an Epidemic-Guided Deep Learning (EGDL) approach that fuses mechanistic epidemiological principles with advanced deep learning techniques to enhance early warning systems and intervention strategies for TB outbreaks. Our framework is built upon a networked Susceptible-Infectious-Recovered (SIR) model augmented with a saturated incidence rate and graph Laplacian diffusion, capturing both long-term transmission dynamics and region-specific population mobility patterns. Compartmental model parameters are rigorously estimated using Bayesian inference via the Markov Chain Monte Carlo (MCMC) approach. Theoretical analysis leveraging the comparison principle and Green's formula establishes global stability properties of the disease-free and endemic equilibria. Building on these epidemiological insights, we design two forecasting architectures, EGDL-Parallel and EGDL-Series, that integrate the mechanistic outputs of the networked SIR model within deep neural networks. This integration mitigates the overfitting risks commonly encountered in data-driven methods and filters out noise inherent in surveillance data, resulting in reliable forecasts of real-world epidemic trends. Experiments conducted on TB incidence data from 47 prefectures in Japan demonstrate that our approach delivers robust and accurate predictions across multiple time horizons (short to medium-term forecasts). Additionally, incorporating uncertainty quantification through conformal prediction enhances the model's practical utility for guiding targeted public health interventions.

Problem

• Tuberculosis outbreak forecasting
• Spatiotemporal transmission dynamics
• Enhanced early warning systems

Innovation

• Epidemic-Guided Deep Learning
• Networked SIR model
• Bayesian inference MCMC