Abstract
Personal health libraries (PHL) are increasingly becoming the mainstay as a single point for patient centered health information management and services. However, the transition to a solely PHL based health information management (HIM) will, at the very least, take a very long time. It is more likely therefore to co-evolve with our current systems for HIMs. In this emerging scenario, the traditional obstacles of data integration among autonomous HIMs face novel challenges. Additionally, the goal to make PHLs responsive to open-ended and personalized health information needs adds unknown wrinkles to current challenges. In this paper, we propose a new architecture, and a knowledge-based information retrieval and processing model for PHLs. We show that by using a declarative data integration language, a knowledge representation scheme and knowledge graph induction technique from health information texts, we are able to respond to patient queries in unprecedented ways in the context of their PHLs.