This paper explores the application of Swarm-Structured Multi-Agent Systems (MAS) to establish medical necessity, a process that involves a systematic review of patient-specific medical structured and unstructured data against clinical guidelines. We addressed this complex task by decomposing it into smaller, more manageable sub-tasks. Each sub-task is handled by a specialized AI agent. We conduct a systematic study of the impact of various prompting strategies on these agents and benchmark different Large Language Models (LLMs) to determine their accuracy in completing these tasks. Additionally, we investigate how these agents can provide explainability, thereby enhancing trust and transparency within the system.

翻译：本文探讨了采用群集结构多智能体系统(MAS)建立医疗必要性的方法，该过程涉及根据临床指南对患者特定的结构化与非结构化医疗数据进行系统性审查。我们通过将这一复杂任务分解为更小、更易管理的子任务来应对挑战。每个子任务由专门的AI智能体处理。我们系统研究了不同提示策略对这些智能体的影响，并对多种大型语言模型(LLM)进行了基准测试，以评估其完成任务的准确性。此外，我们还探究了这些智能体如何提供可解释性，从而增强系统的可信度与透明度。