Beyond Curve Fitting: Neuro-Symbolic Agents for Context-Aware Epidemic Forecasting

TL;DR

This paper introduces a neuro-symbolic framework combining large language models and probabilistic forecasting to improve epidemic predictions by incorporating contextual information and providing interpretable insights.

Contribution

It presents a novel two-agent system that decouples contextual interpretation from forecasting, enhancing accuracy and interpretability in epidemic modeling.

Findings

Achieves competitive point forecast accuracy.

Provides robust 90% prediction intervals.

Offers human-interpretable rationales for forecasts.

Abstract

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 .