Enhancing emergency medical service diversion decision-making through large language models integration

Managing emergency medical services requires maintaining a delicate balance between time, resources, and the quality of care. Rapid and effective decision-making is crucial for patient outcomes. Our goal is to integrate advanced large language models into emergency medical service (EMS) systems to assist in triage decisions and test their practicality and benefits. This method is designed for emergency triage scenarios. By designing specific prompts to introduce heuristic emergency strategies, it makes full use of the multi-turn dialogue capability and contextual understanding characteristics of large language models to achieve a comprehensive assessment of the dynamic changes in the condition of the injured and emergency resources. In this way, it forms dynamic triage decisions for a large number of injured people, and can also provide detailed explanations of the decision reasons. This method was evaluated and verified using four different large language models (as GPT-4, GLM-4, Qwen-max-0428 and Baichuan2-7b-chat-v1) in various scenarios, including different numbers of injured people and different types of large-scale casualty events on our self-built emergency medical dispatch simulation platform, and was compared with the nearest transport method. Additionally, the differences between doctors and large language models in triage decisions were compared, and emergency experts were invited to evaluate the triage decision results and processes. We conducted experiments on emergency medical services under six different resource environment conditions. With comprehensive patient information and hospital treatment capacity information, GLM-4, GPT-4, and Qwen-max-0428 all demonstrated decision-making capabilities far surpassing traditional evacuation methods. GLM-4 and Qwen-max-0428 improved survival rates by an average of 15% after prompt optimization, while GPT-4 performed even better, with an average improvement in survival rates reaching 23% after prompt optimization. The consistency level of manual controlled trials (as high as 0.67) reveals that large language models have guiding and training significance for inexperienced triage personnel in making triage decisions. However, in clinicians’ evaluations, it is revealed that large language models already possess good decision-making abilities, but there is still a certain gap compared to the level of emergency experts. This study highlights the potential of LLMs in EMS diversion decision-making and suggests that more comprehensive emergency information can further enhance their decision-making abilities.