Abstract

Discrete-event simulation (DES) is widely used in healthcare Operations Research, but the models themselves are rarely shared. This limits their potential for reuse and long-term impact in the modelling and healthcare communities. This study explores the feasibility of using generative artificial intelligence (AI) to recreate published models using Free and Open Source Software (FOSS), based on the descriptions provided in an academic journal. Using a structured methodology, we successfully generated, tested and internally reproduced two DES models, including user interfaces. The reported results were replicated for one model, but not the other, likely due to missing information on distributions. These models are substantially more complex than AI-generated DES models published to date. Given the challenges we faced in prompt engineering, code generation, and model testing, we conclude that our iterative approach to model development, systematic comparison and testing, and the expertise of our team were necessary to the success of our recreated simulation models.

Research artefacts

View research summary page

Research compendium

Website: https://pythonhealthdatascience.github.io/llm_simpy

Code archive: https://doi.org/10.5281/zenodo.15090962

GitHub: https://github.com/pythonhealthdatascience/llm_simpy

Deployed models

Web app: https://pythonhealthdatascience.github.io/llm_simpy_models

Code archive: https://doi.org/10.5281/zenodo.15082494

GitHub: https://github.com/pythonhealthdatascience/llm_simpy_models

Article

Citation

BibTeX citation:

@online{monks2025,
  author = {Monks, Thomas and Harper, Alison and Heather, Amy},
  title = {Unlocking the Potential of Past Research: Using Generative
    {AI} to Reconstruct Healthcare Simulation Models},
  date = {2025-09-10},
  url = {https://pythonhealthdatascience.github.io/stars/pages/publications/2025/monks2025unlocking/},
  doi = {10.1080/01605682.2025.2554751},
  langid = {en}
}

For attribution, please cite this work as:

Monks, Thomas, Alison Harper, and Amy Heather. 2025. “Unlocking the Potential of Past Research: Using Generative AI to Reconstruct Healthcare Simulation Models.” September 10, 2025. https://doi.org/10.1080/01605682.2025.2554751.