An Infectious Disease Spread Simulation Based on Large Language Model Decision Making

2026-06-04 · Source: Takara TLDR - Daily AI Papers · Field: Science & Research — Artificial Intelligence & Machine Learning, Health & Medical Research, Mathematics & Computational Sciences · Depth: Expert, medium

Summary

An Infectious Disease Spread Simulation Based on Large Language Model Decision Making introduces a novel spatially grounded, agent-based simulation framework. This framework integrates decisions generated by large language models (LLMs) regarding self-reported influenza-like illness into a synthetic population derived from census data. It emphasizes location, assigning agents to specific spatial units within cities to reflect real-world demographic distributions and enable geographically diverse behavioral modeling. The study implemented and compared three decision scenarios—independent reasoning, household influence, and message framing—simulating self-reporting outcomes in San Francisco and Atlanta. Results indicate that income and and education are the primary factors influencing reporting rate variations, with geography, LLM model choice, and message framing showing smaller but consistent effects. This framework produces synthetic data that captures both social and geographic heterogeneity, supporting advanced spatial epidemiological modeling and bias-aware behavioral analysis.

Key takeaway

For public health researchers and urban planners designing interventions, this simulation underscores the critical influence of socioeconomic factors and geography on disease reporting behavior. You should prioritize understanding income and education disparities, alongside spatial distributions, when developing public health strategies. This approach enables more targeted and effective interventions, moving beyond generalized models to address specific community needs and potential biases in reporting.

Key insights

LLMs can simulate human behavior in spatially-grounded disease spread models, revealing demographic drivers.

Principles

• Income and education strongly drive health reporting behavior.
• Geographic context influences behavioral modeling outcomes.
• LLM choice and message framing have consistent, smaller effects.

Method

Integrate LLM-generated decisions into a census-based synthetic population. Assign agents to spatial units using real-world census data. Simulate and compare decision scenarios (e.g., independent, household, framing).

In practice

• Generate synthetic data for spatial epidemiology.
• Conduct bias-aware behavioral analysis.
• Model public health intervention impacts.

Topics

• Infectious Disease Modeling
• Large Language Models
• Agent-Based Simulation
• Spatial Epidemiology
• Public Health Interventions
• Behavioral Dynamics

Code references

• FudanDISC/SocialAgent

Best for: AI Scientist, Research Scientist

Related on AIssential

• An Infectious Disease Spread Simulation Based on Large Language Model Decision Making — LLMs can simulate human decision-making in spatially-grounded infectious disease models, revealing key socioeconomic drivers.
• An Infectious Disease Spread Simulation Based on Large Language Model Decision Making — LLMs can simulate nuanced human health behaviors in spatially-grounded agent-based models, revealing demographic disparities.
• Policy4OOD: A Knowledge-Guided World Model for Policy Intervention Simulation against the Opioid Overdose Crisis — World models can unify forecasting, counterfactual reasoning, and policy optimization for complex public health crises like the opioid epidemic.
• Neetyabhas: A Framework for Uncertainty-Aware Public Policy Optimization in Rational Agent-Based Models — Public policy optimization benefits from integrating individual behaviors and real-world uncertainties into agent-based models.
• How AI is helping improve heart health in rural Australia — AI-driven population health analytics can proactively identify and address health risks in underserved communities.
• Mapping neighbourhood-level drivers of type 2 diabetes for precision public health using predictive and causal machine learning — Neighbourhood-level factors, identified via ML and causal inference, predict Type 2 diabetes risk and inform targeted public health.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Takara TLDR - Daily AI Papers.