Objective Emergency medical services(EMSs)management requires maintaining a delicate balance between time,resources,and quality of care.Rapid and effective decision-making is crucial for patient outcomes.Our goal is t...Objective Emergency medical services(EMSs)management requires maintaining a delicate balance between time,resources,and quality of care.Rapid and effective decision-making is crucial for patient outcomes.Our goal is to integrate advanced large language models(LLMs)into EMS systems to assist in triage decisions and test their practicality and benefits.Methods 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 understand-ing characteristics of LLMs to achieve a comprehensive assessment of the dynamic changes in the condition of the injured and emergency resources.Thus,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 4 different LLMs(GPT-4,GLM-4,Qwen-max-0428,and Baichuan2-7b-chat-v1)in various scenarios,including different numbers of injured individuals and various types of large-scale casualty events on our self-built emer-gency medical dispatch simulation platform,and was compared with the nearest transport method.Additionally,the differences between doctors and LLMs in terms of triage decisions were compared,and emergency experts were invited to evaluate the triage decision results and processes.Results We conducted experiments on EMSs under 6 different resource environment conditions.With compre-hensive patient information and hospital treatment capacity information,GLM-4,GPT-4,and Qwen-max-0428 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,whereas 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 LLMs have guiding and training significance for inexperienced triage personnel in making triage decisions.However,in clinicians’evaluations,it was revealed that LLMs possess good decision-making abilities,but there is still scope for improvement compared to the level of emergency experts.Conclusion 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.展开更多
In this paper,an emergency decision-making method,based on case-based reasoning and cloud model,is proposed to solve the risk decision-making problem in emergency response.Casebased reasoning,by allowing the decision-...In this paper,an emergency decision-making method,based on case-based reasoning and cloud model,is proposed to solve the risk decision-making problem in emergency response.Casebased reasoning,by allowing the decision-maker to referring to past decisions,introduces a short-cut to formulate feasible emergency alternatives.Cloud model is used to evaluate and optimise the emergency response alternatives.To evaluate emergency response alternatives,the decision criterion must be determined according to the aim and characteristics of emergency rescue in disasters or accidents.Then,the weight cloud and evaluation cloud of the decision criterion are determined by the Delphi method combined with backward cloud generator,and the synthesised cloud of each alternative is calculated through arithmetic rules of cloud.Finally,a ranking of all response alternatives can be determined,and the best alternative is selected.Case study shows that the method makes the conversion between qualitative description and quantitative indication more effective.展开更多
基金supported by National Natural Science Foundation of China(Grant No.82172069,No.82572379)Key Research Project of Zhejiang Laboratory(Grant No.2022ND0AC01)+1 种基金Fundamental Re-search Funds for the Central Universities(Grant Nos.226-2025-00006,226-2024-00163)the Innovation and Development Special Fund of Hangzhou West Sci-Tech Innovation Corridor.
文摘Objective Emergency medical services(EMSs)management requires maintaining a delicate balance between time,resources,and quality of care.Rapid and effective decision-making is crucial for patient outcomes.Our goal is to integrate advanced large language models(LLMs)into EMS systems to assist in triage decisions and test their practicality and benefits.Methods 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 understand-ing characteristics of LLMs to achieve a comprehensive assessment of the dynamic changes in the condition of the injured and emergency resources.Thus,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 4 different LLMs(GPT-4,GLM-4,Qwen-max-0428,and Baichuan2-7b-chat-v1)in various scenarios,including different numbers of injured individuals and various types of large-scale casualty events on our self-built emer-gency medical dispatch simulation platform,and was compared with the nearest transport method.Additionally,the differences between doctors and LLMs in terms of triage decisions were compared,and emergency experts were invited to evaluate the triage decision results and processes.Results We conducted experiments on EMSs under 6 different resource environment conditions.With compre-hensive patient information and hospital treatment capacity information,GLM-4,GPT-4,and Qwen-max-0428 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,whereas 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 LLMs have guiding and training significance for inexperienced triage personnel in making triage decisions.However,in clinicians’evaluations,it was revealed that LLMs possess good decision-making abilities,but there is still scope for improvement compared to the level of emergency experts.Conclusion 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.
基金This work was supported by National Social Science Fund of China[grant number 18BGL232].
文摘In this paper,an emergency decision-making method,based on case-based reasoning and cloud model,is proposed to solve the risk decision-making problem in emergency response.Casebased reasoning,by allowing the decision-maker to referring to past decisions,introduces a short-cut to formulate feasible emergency alternatives.Cloud model is used to evaluate and optimise the emergency response alternatives.To evaluate emergency response alternatives,the decision criterion must be determined according to the aim and characteristics of emergency rescue in disasters or accidents.Then,the weight cloud and evaluation cloud of the decision criterion are determined by the Delphi method combined with backward cloud generator,and the synthesised cloud of each alternative is calculated through arithmetic rules of cloud.Finally,a ranking of all response alternatives can be determined,and the best alternative is selected.Case study shows that the method makes the conversion between qualitative description and quantitative indication more effective.
