%0 Journal Article
%T Investigation on Cardiovascular Risk Prediction Using Physiological Parameters
%A Wan-Hua Lin
%A Heye Zhang
%A Yuan-Ting Zhang
%J Computational and Mathematical Methods in Medicine
%D 2013
%I Hindawi Publishing Corporation
%R 10.1155/2013/272691
%X Cardiovascular disease (CVD) is the leading cause of death worldwide. Early prediction of CVD is urgently important for timely prevention and treatment. Incorporation or modification of new risk factors that have an additional independent prognostic value of existing prediction models is widely used for improving the performance of the prediction models. This paper is to investigate the physiological parameters that are used as risk factors for the prediction of cardiovascular events, as well as summarizing the current status on the medical devices for physiological tests and discuss the potential implications for promoting CVD prevention and treatment in the future. The results show that measures extracted from blood pressure, electrocardiogram, arterial stiffness, ankle-brachial blood pressure index (ABI), and blood glucose carry valuable information for the prediction of both long-term and near-term cardiovascular risk. However, the predictive values should be further validated by more comprehensive measures. Meanwhile, advancing unobtrusive technologies and wireless communication technologies allow on-site detection of the physiological information remotely in an out-of-hospital setting in real-time. In addition with computer modeling technologies and information fusion. It may allow for personalized, quantitative, and real-time assessment of sudden CVD events. 1. Introduction Cardiovascular disease (CVD) remains the worldĄŻs top killer for death at this moment. As reported by World Health Organization [1], CVD will continue to dominate mortality trends in the coming decades. Moreover, it is always associated with substantial socioeconomic burden. Therefore, a considerable demand to improve cardiovascular health is greatly desired. CVDs are chronic diseases that occur by long-term cumulative effects of risk factors. Besides, a large number of people die from acute cardiovascular events without prior symptoms [2]. And about two-thirds of deaths caused by CVD occur in out-of-hospital conditions [3]. It is therefore important to develop effective risk prediction approaches for screening individuals who are at high risk of developing CVD for timely prevention and treatment at an early stage before obvious symptoms happen. In the past decades, several prediction models have been proposed to estimate a 10-year risk of developing CVD. The models are expressed as multivariate regression equations using risk factors as variables. The most influential model is the Framingham Risk Score (FRS), which predicts coronary heart disease (CHD) using traditional risk
%U http://www.hindawi.com/journals/cmmm/2013/272691/