Enabling personalized healthcare by analyzing semantic dependencies in a conceptual co-occurrence network based on a medical vocabulary

Abstract

The amount of medical knowledge is constantly growing thus providing new hope for people having health-related problems. However a challenge is to develop flexible methods to facilitate managing and interpreting large medical knowledge entities. There is a need to enhance health literacy by developing personalized health support tools. Furthermore there is a need to assist decision-making with decision support tools. The recent and on-going changes in everyday life both on technological and societal levels (for example adoption of smart phones and personal mobile medical tracking devices, social networking, open source and open data initiatives, fast growth of accumulated medical data, need for new self-care solutions for aging European population) motivate to invest in the development of new computerized personalized methods for knowledge management of medical data for diagnosis and treatment. To enable creation of new adaptive personalized health support tools we have carried out an evaluation of semantic dependencies in a conceptual co-occurrence network covering a set of concepts of a medical vocabulary with experimental results ranging up to 2994 unique nouns, 82814 unique conceptual links and 200000 traversed link steps.