In modern society, the amount of information has been significantly increased according to the development of IT convergence technology. That leads to develop information obtaining and searching technologies from lots of data. However, they don't seem to have been actually effective for users' health care and promotion not only for limitations of Web-based information and but for lack of personalization. Health information support services have been generally developed in a format of inputting data on bio-information acquired into the computer for the existing network-based transmission. In this paper, a life habits disease system that uses the existing medical data and Framingham risk factor(FRS) performs neural network is proposed. Based on the proposed system, it is possible to provide the fundamental data and guideline to doctors for recognizing the life habits disease diagnosis of patients and that represents increases in the welfare of patients.