Multi-Regional Infectious Disease Transmission Forecasting Based on Graph-Structure-Enhanced Large Language Model
Open Access
- 20 July 2026
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 14 (14) , 2642
Abstract
Infectious disease outbreaks strain medical resources and public-health systems, making accurate multi-horizon, multi-regional forecasting essential for early warning and resource allocation. Existing approaches face a trade-off: data-driven deep models can capture nonlinear spatiotemporal patterns but often overlook transmission mechanisms, whereas mechanistic models are interpretable but limited in modeling complex regional dependencies. To address this challenge, we propose Epidemic Spatial–Temporal Large Language Model (EpiSTLLM), which is a graph-structure-enhanced large language model for multi-regional infectious disease forecasting. EpiSTLLM injects regional adjacency information into Transformer-based representation learning to capture cross-regional transmission structure and long-term temporal dependencies. A temporal-gated cross-attention module generates horizon-specific latent transmission and recovery parameters, while a latent-space SIR-inspired propagation mechanism with a residual correction branch enables stable multi-horizon forecasting without requiring fully observed compartmental states. Experiments on the FluView state-level influenza-like illness dataset and NHSN state-level influenza hospitalization dataset show that EpiSTLLM achieves the best or highly competitive performance in most evaluation settings against statistical, deep learning, graph-based, and mechanism-guided baselines across 4-, 8-, and 12-week horizons. For example, EpiSTLLM reduces MAE and RMSE values by and at on FluView, and by and at on NHSN compared with the strongest baselines, respectively.
Keywords
Funding Information
- Basic and Applied Basic Research Foundation of Guangdong Province (2024A1515030128)
- Basic and Applied Basic Research Foundation of Guangdong Province (2023B1515120078)
- Science and Technology Development Fund of Macau SAR (0010/2025/RIC)
- Science and Technology Development Fund of Macau SAR (0002/2024/RDP)
- Shenzhen Science and Technology Program (KJZD20240903104200001)
This publication has 44 references indexed in Scilit:
- EpiGNN: Exploring Spatial Transmission with Graph Neural Network for Regional Epidemic Forecasting2023
- Top-Down and Bottom-Up Lockdown: Evidence from COVID-19 Prevention and Control in ChinaJournal of Chinese Political Science, 2021
- Artificial intelligence for COVID-19: saviour or saboteur?The Lancet Digital Health, 2021
- Structural identifiability and observability of compartmental models of the COVID-19 pandemicAnnual Reviews in Control, 2021
- Improving epidemic surveillance and response: big data is dead, long live big dataThe Lancet Digital Health, 2020
- Nowcasting and forecasting the potential domestic and international spread of the 2019-nCoV outbreak originating in Wuhan, China: a modelling studyThe Lancet, 2020
- A modelling approach for correcting reporting delays in disease surveillance dataStatistics in Medicine, 2019
- Estimates of global seasonal influenza-associated respiratory mortality: a modelling studyThe Lancet, 2018
- Applied Spatial Data Analysis with R2013
- Supervised Sequence Labelling with Recurrent Neural Networks2012