Cardiovascular risk analysis by means of pulse morphology and clustering methodologies

Abstract

c o m p u t e r m e t h o d s a n d p r o g r a m s i n b i o m e d i c i n e 1 1 7 ( 2 0 1 4 ) [257][258][259][260][261][262][263][264][265][266] j o u r n a l h o m e p a g e : w w w . i n t l . e l s e v i e r h e a l t h . c o m / j o u r n a l s / c m p b a b s t r a c tThe purpose of this study was the development of a clustering methodology to deal with arterial pressure waveform (APW) parameters to be used in the cardiovascular risk assessment. One hundred sixteen subjects were monitored and divided into two groups. The first one (23 hypertensive subjects) was analyzed using APW and biochemical parameters, while the remaining 93 healthy subjects were only evaluated through APW parameters. The expectation maximization (EM) and k-means algorithms were used in the cluster analysis, and the risk scores (the Framingham Risk Score (FRS), the Systematic COronary Risk Evaluation (SCORE) project, the Assessing cardiovascular risk using Scottish Intercollegiate Guidelines Network (ASSIGN) and the PROspective Cardiovascular Münster (PROCAM)), commonly used in clinical practice were selected to the cluster risk validation. The result from the clustering risk analysis showed a very significant correlation with ASSIGN (r = 0.582, p < 0.01) and a significant correlation with FRS (r = 0.458, p < 0.05). The results from the comparison of both groups also allowed to identify the cluster with higher cardiovascular risk in the healthy group. These results give new insights to explore this methodology in future scoring trials.© 2014 Elsevier Ireland Ltd. All rights reserved. IntroductionThe atherosclerotic cardiovascular disease (CVD) is the most common cause of death worldwide, resulting from the combination of several risk factors [1]. The international guidelines [2,3] consider that individuals with established CVD should be the first priority for preventive measures application. The concern in changing the current healthcare paradigm, from reactive towards preventive care, aims at identify individuals for risk in early stages of disease development, and then, * Corresponding author. Tel.: +351 239410109.E-mail address: vaniagalmeida@lei.fis.uc.pt (V.G. Almeida).direct more efforts and attention to the risk factors modification [4,5]. Fortunately, this is an emergent tendency that can be addressed using the traditional risk scores, but also using innovative predictive algorithms. During the last years many risk estimation systems have been developed in order to assist clinicians in the risk assessment, and in the individual chances prediction, for CVD development. The major challenges of these tools are the capabilities to: (1) identify high risk individuals, (2) weight the individual effects of all risk factors, (3) stratify or organize who needs lifestyle advice or medical therapy, and finally (4) avoid http://dx

Machine learning in cardiovascular medicine: are we there yet?

“…Instead, the goal is to learn the relationship between variables and uncover hidden structure in a data set. Examples of unsupervised learning include clustering methods (hierarchical or K means),28 principal component analysis, information maximising component analysis,29 self-organising maps,30 topological data analysis and deep learning. Specifically, deep learning is an emerging subdiscipline of machine learning that leverages an artificial neural network with many hidden layers of neurons.…”

Decision Support based on Bio-PEPA Modeling and Decision Tree Induction

“…Descriptive methods, such as clustering and association rules, disclose concealed patterns that sum up the relationship between variables without predicting target values. Clustering regroups a set of objects with a similar specificity, as used by Almeida et al (2014) in cardiovascular risk assessment where the resulting five clusters showed the intrinsic relation between features. Association rules identify a degree of association between features and their frequency, as achieved by Ou-yang et al (2013) where the impact of prescribed drugs on Stevens-Johnson syndrome was detected.…”