Patient education materials, describing medical conditions or procedures, are ubiquitous in healthcare, and their creation and dissemination comprise large industries. While many advances have been made in biomedical informatics in the retrieval of these materials, medical illustrations—which are pervasive components of these materials—have largely defied empirical study and innovation.
We are developing an authoring tool to allow clinicians to rapidly develop conversational agent-based media to explain patient education materials in a way that is adaptive to embedded illustrations and patient characteristics, and is interactive and tailored to patient knowledge and needs. We will evaluate the use of agents produced with this tool to explain patient education materials deployed via standard web browsers and in Virtual Reality (VR) to provide anticipatory guidance through immersive 3D depictions of organs and medical procedures.
This work is supported by the National Library of Medicine, and is a collaboration with Dr. Michael Paasche-Orlow (Tufts Medical Center).