Automated explanation of research informed consent by virtual agents

Abstract

A virtual agent that explains research informed consent documents to study volunteers is described, along with a series of development efforts and evaluation studies. A study of nurse administration of informed consent finds that human explanations follow the structure of the document, and that much of information provided verbally is not contained in the document at all. A study of pedagogical strategies used by a virtual consent agent finds that automatic tailoring of document content based on users’ knowledge receives the highest ratings of satisfaction compared to two control conditions that provided fixed amounts of information. We finally report on an approach that lets clinicians construct their own virtual agents for informed consent, along with a study that finds that nurses are able to use the system to develop and extend agents to explain their own study consent forms.