%0 Journal Article
%T Quantitatively Plotting the Human Face for Multivariate Data Visualisation Illustrated by Health Assessments Using Laboratory Parameters
%A Wang Hongwei
%A Liu Hui
%J Computational and Mathematical Methods in Medicine
%D 2013
%I Hindawi Publishing Corporation
%R 10.1155/2013/390212
%X Objective. The purpose of this study was to describe a new data visualisation system by plotting the human face to observe the comprehensive effects of multivariate data. Methods. The Graphics Device Interface (GDI+) in the Visual Studio.NET development platform was used to write a program that enables facial image parameters to be recorded, such as cropping and rotation, and can generate a new facial image according to values from sets of normal data ( was still counted as 3). The measured clinical laboratory parameters related to health status were obtained from senile people, glaucoma patients, and fatty liver patients to illustrate the facial data visualisation system. Results. When the eyes, nose, and mouth were rotated around their own axes at the same angle, the deformation effects were similar. The deformation effects for any abnormality of the eyes, nose, or mouth should be slightly higher than those for simultaneous abnormalities. The facial changes in the populations with different health statuses were significant compared with a control population. Conclusions. The comprehensive effects of multivariate may not equal the sum of each variable. The 3 facial data visualisation system can effectively distinguish people with poor health status from healthy people. 1. Introduction Data visualisation is the study of visual representation of data to communicate information clearly and effectively through graphical means [1¨C3]. The medical sciences have a uniquely intertwined relationship with bioinformatics. The rapidly expanding field of biology creates enormous challenges to enable researchers to gain insights from large and highly complex data sets. Although researchers and practitioners often create patterns that can be visually identified, such as charts, graphs, and interactive displays, when solving a large range of problems, there are no definite accepted methods to identify these complex relationships [4¨C6]. Traditional data visualisation systems are mostly based on mathematical models, but complex bioinformatic correlations may not follow previously known statistical rules. Therefore, it is essential to explore methods for data visualisation that do not completely rely on mathematical models. We established the facial data visualisation system based on changes in human facial features. Certain specific bioinformatics rules for correlations may be elucidated with the use of the data visualisation system. Chernoff first developed the idea of using human facial characteristics as a means to visualise data [7, 8]. The idea behind using faces is
%U http://www.hindawi.com/journals/cmmm/2013/390212/