Training clinical decision-making through simulation

Abstract

Clinical decision making faces relevant uncertainties, outcomes and trade-offs. It has to deal with diagnosis uncertainties, the choice of diagnostic tests, the selection of prescriptions and procedures, and the treatment follow up, many times facing severe budget limitations and lack of sophisticated equipment. This paper presents a multi-agent learning system for health care practitioners: SimDeCS (Simulation for Decision Making in the Health Care Service). This system relies on simulations of complex clinical cases integrated in a virtual learning environment, and has been developed within a program offering continuous education, training and qualification to professionals in the Brazilian health care service. SimDeCS will be made available on the Internet, thus providing access to professionals working throughout the country. The main contribution is the system architecture and the model knowledge.The learning environment has been designed as a multi-agent system where three intelligent agents are included: Domain Agent, Learner Agent, and Mediator Agent. The knowledge model is implemented by the Domain Agent through probabilistic reasoning, relying on expert human knowledge encoded in Bayesian networks. A clinical case is presented and discussed. © 2012 Springer-Verlag.