Please use this identifier to cite or link to this item: https://ah.lib.nccu.edu.tw/handle/140.119/98241
題名: Daily Health Assessment System Using Prediction Model for Self-rated Health by Vital Sign Pattern
作者: Huang, Kuan-Ling;Chen, Ya-Hung;Liao, Chun-Feng;Fu, Li-Chen
廖峻鋒
貢獻者: 資科系
日期: Oct-2014
上傳時間: 22-Jun-2016
摘要: With the growing population of aging people around the world, there is an increasing needs for elders to be aware of their health status not only in hospital but also in home environment. Due to recent advances of health monitoring technologies, elder people are able to easily assess their physiological well-being at home. However, most of current physiological monitoring systems focus on the patient with critical situation such as the intensive care unit and there are relatively fewer systems aim to assess these trends in home scenario. Additionally, most of the current home vital sign monitoring systems use pre-determined threshold to identify the dangerous situation over single measurement or just focus on the system architecture as well as communication technique. It is essential to develop a healthcare system that is capable to make an alarm far before elderly people is in acute situation. In this paper, a data model is built for the vital sign trends over certain number of days. In order to determine the dangerous situation, this model is associated with a common health assess tool - self-rated health, which has been confirmed a predictor for mortality over elder population. To demonstrate the feasibility of our system, four subjects aging from 58 to 95 had been participated in experiment and collected vital sign once a day. The result shows that the proposed system is able to identify the poor health condition based on the collected data with high precision.
關聯: Proc. IEEE Healthcare Innovation Point-Of-Care Technologies Conference, Seattle, Washington, USA, 2014, 95-98
資料類型: conference
DOI: http://dx.doi.org/10.1109/HIC.2014.7038883
Appears in Collections:會議論文

Files in This Item:
File Description SizeFormat
index.html159 BHTML2View/Open
Show full item record

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.