Knowledge graphs In medical domain

Abstract

With the explosion of healthcare information, there has been a tremendous amount of heterogeneous Textual Medical Knowledge(TMK), which plays an essential role in healthcare information systems. Existing works for integrating and utilizing the textual medical knowledge mainly focus on straightforward connections establishment and pay less attention to make computers interpret and retrieve knowledge correctly and quickly. In our work, we explore a novel model to organize and integrate the TMK into Knowledge graphs. We then employ a framework to automatically retrieve knowledge in knowledge graphs with high precision. In our work, we plan to build high quality and comprehensive Medical Knowledge Graph which is highly scalable. Our Knowledge Graph would be based on the custom created ontology - MedOnto. Moreover, most of the Medical Knowledge bases do not focus on the application based aspects of personal health like information about drugs, their brand names, prices etc. We also develop a WebApp called MedMate which can help doctors in selecting drugs and common men to get low cost drugs and other informations regarding the drugs prescribed. As part of the application, we plan to build an efficient recommender system based on the above topics