An Agent Based Approach to Patient Scheduling Using Experience Based Learning

This paper describes an agent based approach to patient scheduling using experience based learning and an integer programming model. The evaluation on different learning techniques shows that the experience based learning (EBL) provides a better solution. The time required to process a particular job is reduced as the experience processed by it increases. The processing time can be calculated with the help of EBL. The main objective of this patient scheduling system is to reduce the waiting time of patient in hospitals and to complete their treatment in minimum required time. The proposed framework is implemented in JADE. In this approach the patients are represented as patient agent (PA) and resources as resource agent (RA). This mathematical model provides an optimal solution. The comparisons of the proposed framework with other scheduling rules shows that an agent based approach to patient scheduling using EBL gives better results. learning technique would be a good choice (Kanaga, Valarmathi, & Murali, in press). Here we consider each patient and resources as agents and they interact with each other (Janiak & Rudek, 2005). The agent based approach considers the patients as Patient Agents (PA) and resources as Resource Agents (RA). The PA requests for the resource. A special agent named Common Agent (CA) is also introduced in this framework. CA refers to a general physician who decides on what tasks the patient has to undergo. The proposed framework is trying to reduce the DOI: 10.4018/jats.2010100101 2 International Journal of Agent Technologies and Systems, 2(4), 1-9, October-December 2010 Copyright © 2010, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. patients waiting time and tardiness. We can further reduce this by incorporating experience based learning. The learning models in scheduling are based on the learning curve introduced by Wright (Janiak, Janiak, Rudek, & Wielgus, 2009). In scheduling problems with a new experience-based learning model, job processing times are described by “S”-shaped functions that are dependent on the experience of the processor. In patient scheduling, decisions are made according to the learning model (Becker, Navarro, Krempels & Panchenko, 2003).