A family health history - incorporating a “family tree” along with health conditions for each family member - can significantly improve disease risk assessments, even when all available genetic tests have been done. The family history is crucially important for determining risk for many chronic conditions, including cardiovascular disease, diabetes, and cancer, and represents an integration of disease risk stemming from genetic, environmental, and behavioral factors. Despite this, most health providers do a poor job of collecting family health histories, if they do it at all.
The purpose of this project is to develop a relational agent that simulates the behavior of a genetics counselor in collecting a family health history from individuals by interviewing them about their family. Preliminary testing has shown that patients recruited from a safety net hospital (40% low health literacy) find the agent significantly easier to use compared with a conventional web-based tool.
This work is supported by the NIH National Human Genome Research Institute, and is a collaboration with Dr. Catharine Wang at the Boston University School of Public Health, and Dr. Michael Paasche-Orlow at Boston Medical Center.