Research on Applications of Multi-Agent System Based on Execution Engine in Clinical Decision-Making

摘要

Medical errors have become a common concern of social problems. One important reason is the lack of clinical experience. Clinical guidelines are the solution to this problem; however, they are always kept being updated. Let the system adapt to the changing clinical guidelines is a challenging idea. In this paper we propose MAS (Multi-Agent System) based on the Execution Engine can achieve this goal. In the MAS, clinical guidelines are mapped into rules, which are stored in the rule repository and could be processed by the Execution Engine, to guide agents' behaviors. Rules in the system are configurable and Execution Engine can always obtain the latest data at runtime without interrupting system running, so it implements the system's adaptability. Agents, which could be deployed in distributed environments, simulate doctors' roles to do aided diagnosis by collaborations which implements data sharing and improves the accuracy of decision-making greatly.