Authoring adaptive tutoring systems for complex visual skills

In the world of Intelligent Tutoring Systems research, the connection between learner models and interaction models has been largely ignored. Similarly, previous works have not accounted for the dynamic representation of interface contents based on the underlying pedagogic directives. The paper describes an approach to the authoring of training contents aimed at intermediate-level learners of medical Radiology. It is argued that, in certain dialogues designed for supporting visual diagnosis, it is worthwhile employing domain-general teaching mechanisms and reuse them in various domain-specific situations. An empirical study has been carried out with a corpus of human-to-human tutorial dialogues to identify the component features of expertise in medical Radiology. The results of the study form the basis for implementing interface and learner models that guide long-term tutorial interactions through an intelligent shell called RUI. Conclusions and future research directions are also described briefly.