Moving Beyond Branching: Evaluating Educational Impact of Procedurally-Generated Virtual Patients

Electronic virtual patients (VPs) are interactive screen-based computer simulations of real-life clinical scenarios that are widely used for the purposes of health sciences education. VPs allow for safe and supportive experiences for health sciences students to practice problem solving and diagnostic skills without endangering real patients. Our previous work investigated the feasibility of procedurally generating virtual patient cases that leverage Bayesian network (BN) models learned from EMR data to present clinical scenarios and control outcomes of learners' decisions within the context of a presented VP. In this paper, we describe an experiment that compares a VP case based on a BN model to one created using a traditional narrative-branched VP system across multiple categories. Our results show that the narrative-branched VP case was rated significantly higher than its BN-based counterpart on reflecting the learning objectives, introducing/reinforcing clinical skills, attitudes, and behaviors relevant to sepsis treatment, providing formative feedback for choices/outcomes, and being more effective in teaching the subject matter to novice clinical practitioners. The BN-based VP case was rated significantly higher than the branched-narrative version on representing clinical variations associated with sepsis, on realism, and on learner engagement.