Lifestyle risk association aggregation

IoT application in health care provides ways to monitor and collect health related biomarkers, in particular, lifestyle related data, by recording and analyzing long-term data, to provide insight to patients' status. In order to make most use of this application, linking the collected patients' data with a disease predictive model will generate a personalized disease progression and predictions. Various risk factors have been researched extensively to find the effect on the disease. However, risk factors are fragmented all over medical literature, and often each publication reports on one or a few risk factors, a combination of several of those factors, often from different research. In this paper, we propose an approach to explore the combination of risk factors. The outcome will form a base for a complete risk prediction model that can be used for many health applications.