Simulating Disease Transmission Models Via Agent Interaction Using Large Language Models
Keywords:
Disease Modeling, Agent-based Modeling, Large Language Models, Public Health, Epidemiological SimulationSynopsis
This is a Chapter in:
Book:
Competitive Tools, Techniques, and Methods
Print ISBN 978-1-6692-0008-6
Online ISBN 978-1-6692-0007-9
Series:
Chronicle of Computing
https://www.okipublishing.com/book/index.php/okip/catalog/series/1
Chapter Abstract:
Traditional epidemic models often fall short in capturing the complexity of human behaviors, a gap highlighted by the COVID-19 pandemic. This research explores the integration of large language models (LLMs) and agent-based modeling (ABM) with the Susceptible-Exposed-Infectious-Recovered (SEIR) framework to enhance epidemiological simulations. By leveraging LLMs, this study aims to develop a more dynamic and realistic model of disease transmission that reflects individual and community-level interactions. Our methodology utilizes the HPC-powered Mesa-Geo framework to incorporate geographically informed human agents (GeoAgents) and simulates disease spread through a detailed SEIR model, enriched by the advanced capabilities of the GPT4-XL Flan Alpaca model for generating nuanced human interactions. Preliminary results indicate that such an integration can effectively simulate complex social behaviors and adherence to public health measures, suggesting a promising direction for future epidemiological modeling. This approach not only addresses critical gaps in traditional modeling but also sets the stage for further research that could enhance public health strategies through more accurate and adaptive simulations.
Cite this paper as:
Chen J., Alhajjar E. (2024). Simulating Disease Transmission Models Via Agent Interaction Using Large Language Models. In: Tiako P.F. (ed) Competitive Tools, Techniques, and Methods. Chronicle of Computing. OkIP. CAIS24#23. https://doi.org/10.55432/978-1-6692-0007-9_18
Presented at:
The 2024 OkIP International Conference on Automated and Intelligent Systems (CAIS) in Oklahoma City, Oklahoma, USA, and Online on October 2, 2024
Contact:
Elie Alhajjar
eliealhajjar@gmail.com
References
Novakovic, A. and Marshall, AH (2022). The CP-ABM approach for modelling COVID-19 infection dynamics and quantifying the effects of non-pharmaceutical interventions. Pattern Recognit. 130:108790. Doi: 10.1016/j.patcog.2022.108790. PMID: 35601479; PMCID: PMC9107333.
Miksch, F., Jahn, B., Espinosa, KJ, Chhatwal, J., Siebert, U. and Popper, N. (2019). Why should we apply ABM for decision analysis for infectious diseases?-An example for dengue interventions. PLoS One. 14(8):e0221564. Doi: 10.1371/journal.pone.0221564. PMID: 31454373; PMCID: PMC6711507.
Jackson, J., Lewis, K., Norton, M. and Gray, Kurt. (2016). Agent-Based Modeling: A Guide for Social Psychologists. Social Psychological and Personality Science. 8. 10.1177/1948550617691100.
Cokljat, M., Cruz, C. V., Carrara, V. I., et al. (2024). Comparison of WHO versus national COVID-19 therapeutic guidelines across the world: not exactly a perfect match. BMJ Global Health. doi:10.1136/bmjgh-2023-014188
Wu, Z., Peng, R., Han, X., Zheng, S., Zhang, Y. and Xiao, C. (2023). Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations. ArXiv, abs/2311.06330.
Hunter, E., Mac Namee, B. and Kelleher, J. D. (2018). A Comparison of Agent-Based Models and Equation Based Models for Infectious Disease Epidemiology, 26th AIAI Irish Conference on Artificial Intelligence and Cognitive Science. doi.org/10.21427/rtq2-hs52.
Park, J. S., O’Brien, J., Cai, C. J., Morris, M. R., Liang, P. and Bernstein, M. S. (2023). Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (pp. 1-22).
Perez, L. and Dragicevic, S. (2009). An agent-based approach for modeling dynamics of contagious disease spread. Int J Health Geogr. 8:50. Doi: 10.1186/1476-072X-8-50. PMID: 19656403; PMCID: PMC2729742.
Eubank, S., Eckstrand, I., Lewis, B., Venkatramanan, S., Marathe, M., Barrett, CL. et al. (2020). Impact of Non-pharmaceutical Interventions (NPIs) to Reduce COVID-19 Mortality and Healthcare Demand. Bull Math Biol. 82(4):52. Doi: 10.1007/s11538-020-00726-x. PMID: 32270376; PMCID:PMC7140590.
