The effectiveness and efficiency of using ChatGPT for writing health care simulations

Abstract

Simulation is a crucial part of health professions education that provides essential experiential learning. Simulation training is also a solution to logistical constraints around clinical placement time and is likely to expand in the future. Large language models, most specifically ChatGPT, are stirring debate about the nature of work, knowledge and human relationships with technology. For simulation, ChatGPT may present a solution to help expand the use of simulation by saving time and costs for simulation development. To understand if ChatGPT can be used to write health care simulations effectively and efficiently, simulations written by a subject matter expert (SME) not using ChatGPT and a non-SME writer using ChatGPT were compared. Simulations generated by each group were submitted to a blinded Expert Review. Simulations were evaluated holistically for preference, overall quality, flaws and time to produce. The SME simulations were selected more frequently for implementation and were of higher quality, though the quality for multiple simulations was comparable. Preferences and flaws were identified for each set of simulations. The SME simulations tended to be preferred based on technical accuracy while the structure and flow of the ChatGPT simulations were preferred. Using ChatGPT, it was possible to write simulations substantially faster. Health Profession Educators can make use of ChatGPT to write simulations faster and potentially create better simulations. More high-quality simulations produced in a shorter amount of time can lead to time and cost savings while expanding the use of simulation.