Many professionals provide their lay clients with documents that are, to varying degrees, incomprehensible. Whether due to technical jargon, obscure concepts, or poor writing on the part of the professional, or low literacy, cultural barriers, or cognitive impairment on the part of the client, documents often fail to serve their intended communicative function. Perhaps nowhere is this problem more important and pervasive than in healthcare. The consequences of a patient failing to understand a prescription, hospital discharge instructions, or pre-surgery instructions can have serious, even fatal, consequences.
In this project we are developing models to allow a relational agent to effectively explain health documents to individuals with low health literacy. This involves micro-analysis of the behavior of human healthcare experts as they explain documents to patients, development of computational models of this behavior, and evaluation of the resulting systems.
This effort is in collaboration with Dr. Michael Passche-Orlow at the Boston University School of Medicine.