Advancing Real-time Infectious Disease Forecasting Using Large Language Models

Forecasting the short-term spread of an ongoing disease outbreak poses a challenge due to the complexity of contributing factors, some of which can be characterized through interlinked, multi-modality variables, and the intersection of public policy and human behavior. Our work introduces PandemicLLM, a framework with multi-modal Large Language Models (LLMs) that reformulates real-time forecasting of disease spread as a text reasoning problem, with the ability to incorporate real-time, complex, non-numerical information. This approach, through an AI-human cooperative prompt design and time series representation learning, encodes multi-modal data for LLMs. The model is applied to the COVID-19 pandemic, and trained to utilize textual public health policies, genomic surveillance, spatial, and epidemiological time series data, and is tested across all 50 states of the U.S. for a duration of 19 months. PandemicLLM opens avenues for incorporating various pandemic-related data in heterogeneous formats and exhibits performance benefits over existing models.