Affiliations: [a] Department of Informatics, University of Piraeus, Greece | [b] Department of Ecology and the Environment, Technological Education Institute of the Ionian Islands, Greece | [c] Laboratory of Experimental Surgery and Surgical Research, University of Athens, Greece
Abstract: Computer-based education has already been acknowledged as an important asset for medical education. For example, web-based educational systems for medicine and health provide an additional important advantage to remote learners through platform- and time-independence. However, such systems are difficult to create as they require a lot of effort from both medical tutors and software engineers. Therefore, repetition of effort has to be avoided and such systems should be able to be used to their full extent from whoever requires medical and health knowledge on the specific topics. This means that they need to incorporate intelligent techniques in order to be able to adapt dynamically to the needs of individual users rather than have many static educational systems designed solely for different kinds of users. In view of this, in this paper we address the problem of developing an adaptive e-learning system for the medical domain of Atheromatosis. Atheromatosis of the aortic arch has been recognized as an important source of embolism, which is a frequent cause of stroke. This is the main reason that the particular topic is of interest to a wide range of users with different background knowledge and needs (e.g. medical students, nurses, common people interested in maintaining a good health, etc.). The inference mechanism of the system uses a combination of rule-based reasoning and a decision making theory. In order to design the reasoning mechanism of the system, and thus incorporate the decision making theory successfully, we conducted an empirical study. The empirical study involved distribution of questionnaires to several classes of potential users of an e-learning system about Atheromatosis and analysis of the results by computer and medical experts. The results of the empirical study were used for designing the reasoning mechanism of the system.
Keywords: Intelligent medical tutoring systems, adaptive e-learning, empirical study, artificial intelligence in medical education
