Visualization of High-Dimensional Clinically Acquired Geographic Data Using the Self-Organizing Maps

Abstract

ABSTRACT. The objective of this study is to visualize high-dimensional data vectors using popular data reduction algorithms. The study reports on the effectiveness and expressiveness of a set of data reduction algorithms in the visualization of geospatial data sets derived from clinical records of patients. The experiments show that when the SOM algorithm is combined with GIS methods together they are even more powerful tools for exploratory analysis than when each is applied separately. The visual approach provides a very useful exploration environment to support the formulation of new and better study hypotheses regarding the spatial distribution of a particular disease. While it was apparent that the spatial distribution and patterns of asthma were predominately located near the major roadways and the Peace Bridge Complex, obstructive sleep apnea is slightly more widespread even in the suburbs and surrounding neighborhoods. The spatial patterns discovered between the original features of adult and childhood asthma are consistent with the SOM-trained data, but a slight difference emerges for the SOM-trained obstructive sleep apnea data set. This study is successful at gaining significant novel insights into the spatial characteristics of patient data in relation to key environmental factors.

The New and Computationally Efficient MIL-SOM Algorithm: Potential Benefits for Visualization and Analysis of a Large-Scale High-Dimensional Clinically Acquired Geographic Data

“…Although clusters of childhood asthma are similar to adult asthma, there is a wide spatial distribution of these clusters in the Westside, Downtown, and Eastside signifying the severity of asthma among children. This finding is consistent with the previous ones [ 42 , 44 ]. There are notable spatial differences between the geographic extent of the clusters generated by MIL-SOM and Kohonen's SOM algorithms because they are a good fit for epidemiological studies.…”

“…The major clusters of adult asthma are located in Downtown, Westside, and to a less extent in the Eastside of the City of Buffalo, New York. These clusters are consistent with previous findings [ 41 , 44 , 45 ] that applied traditional epidemiological methods to investigate the prevalence of adult asthma. Overall, the identified three subsets (geographic regions) of adult asthma are similar to the ones identified in childhood asthma, MIL-SOM algorithms provide tighter clusters than Kohonen's SOM.…”

A Biological Monitoring Method based on the Response Behavior of Caenorhabditis Elegans to Chemicals in Water

“…The SOM is one of the representative clustering techniques dividing data into clusters through unsupervised learning. Owing to its usefulness and relative simplicity, the SOM has been widely used in various studies such as the data analysis of environment monitoring (Li, 2015;Riga, 2015) and ecological modelling (Bae, 2014) as well as data visualization (Oyana, 2009).…”

Spatiotemporal Classification Analysis of Long-Term Environmental Monitoring Data in the Northern Part of Lake Taihu, China by Using a Self-Organizing Map

“…Canonical correlation analysis, cluster analysis (CA), discriminant analysis (DA), principal component analysis (PCA), factor analysis, absolute principle component score-multiple linear regression, and factor analysis-multiple regression analysis are the commonly accepted traditional multivariate methods used to evaluate spatiotemporal variations in environmental research (Lovchinov and Tsakovski, 2006;Zhou et al, 2007a;Omo-Irabor et al, 2008;Noori et al, 2012). In recent years, efforts have been made to involve more sophisticated approaches, such as self-organizing maps (SOM) (Tsakovski et al, 2010a, b;Jin et al, 2011;Oyana, 2009), in spatiotemporal classification, pollution pattern recognition, and modeling studies with surface water quality data sets or to compare SOM classification with more traditional multivariate statistical classification methods (Astel et al, 2007). These methods have already been used for surface water quality analyses.…”