Beyond Curve Fitting: Neuro-Symbolic Agents for Context-Aware Epidemic Forecasting
This addresses the need for context-aware epidemic forecasting in public health, though it is incremental as it combines existing methods like LLMs with neuro-symbolic techniques.
The paper tackled the problem of forecasting hand, foot, and mouth disease by integrating contextual drivers like school calendars and weather, achieving competitive point forecasting accuracy and robust 90% prediction intervals with coverage of 0.85-1.00 on real-world datasets from Hong Kong and Lishui, China.
Effective surveillance of hand, foot and mouth disease (HFMD) requires forecasts accounting for epidemiological patterns and contextual drivers like school calendars and weather. While classical models and recent foundation models (e.g., Chronos, TimesFM) incorporate covariates, they often lack the semantic reasoning to interpret the causal interplay between conflicting drivers. In this work, we propose a two-agent framework decoupling contextual interpretation from probabilistic forecasting. An LLM "event interpreter" processes heterogeneous signals-including school schedules, meteorological summaries, and reports-into a scalar transmission-impact signal. A neuro-symbolic core then combines this with historical case counts to produce calibrated probabilistic forecasts. We evaluate the framework on real-world HFMD datasets from Hong Kong (2023-2024) and Lishui, China (2024). Compared to traditional and foundation-model baselines, our approach achieves competitive point forecasting accuracy while providing robust 90% prediction intervals (coverage 0.85-1.00) and human-interpretable rationales. Our results suggest that structurally integrating domain knowledge through LLMs can match state-of-the-art performance while yielding context-aware forecasts that align with public health workflows. Code is available at https://github.com/jw-chae/forecast_MED .