Multi-agent based Patient Scheduling Using Particle Swarm Optimization

Patient scheduling is the process of scheduling and sequencing the patients for various multiple resources in health care domain. The multiple constraints and multiple goals to be achieved in minimal time makes this problem highly complex. Computational complexity is high in using exact methods for solving optimization problem. Motivated by the real needs in hospital environments, this paper focuses on finding an optimal schedule using the meta-heuristic technique Particle Swarm Optimization (PSO) and coordinating the hospital environment using multi-agents. Agents have been proved to be an effective approach to resource allocation because of its coordination and social abilities. For solving, various agents like Patient Agent (PA), Resource Agent (RA) and Common Agent (CA) are used. In addition to these agents a PSO Agent is used to perform the PSO optimization. On arrival of the patients, this PSO agent is called to perform PSO optimization dynamically and an optimized schedule is generated. The objective is to reduce the patient waiting time in the hospital. This agent based approach is implemented in JADE (Java Agent Development Environment) and tested for different data sets. The results are compared with the traditional dispatching rules like First Come First Serve(FCFS), Minimum Slack(MS),Shortest Processing Time(SPT) and Longest Processing Time (LPT). The performance improvement of total weighted waiting time in Agent-based Patient Scheduling using PSO (APS-PSO) for 10 resources and 50 patients is 4.13% when compared to the best performing dispatching rule MS and 52% with respect to LPT. Similarly, there is an average of 8.69% improvement in terms of total weighted completion time. When the number of late patient is considered, the performance of the PSO based approach increased by 17%.