The cluster analysis technique of pattern recognition: application to the trace metal composition of cardiovascular tissues. |
| |
| Authors: | J Webb W Niedermeier J H Griggs K A Kirk M E Turner T N James |
| |
| Affiliation: | Division of Clinical Immunology and Rheumatology, Department of Medicine, University of Alabama in Birmingham, Birmingham, Alabama U.S.A.;Department of Biostatistics, University of Alabama in Birmingham, Birmingham, Alabama U.S.A.;Cardiovascular Research and Training Center, University of Alabama in Birmingham, Birmingham, Alabama 35294 U.S.A. |
| |
| Abstract: | Application of the statistical method of cluster analysis as a pattern recognition technique was investigated by classification of cardiovascular tissues on the basis of their trace metal composition. The distribution patterns of 13 trace metals among 17 tissues of the heart and its appended blood vessels were determined. Cluster analysis of the data resulted in ready differentiation of tissues derived from ordinary and specialized myocardium from those of blood vessels and heart valves. Further similarities and differences among the 17 tissues were identified by comparing the patterns generated when different numbers of groups (i.e., 3, 4, 5, 6, and 7 groups) were designated. It is suggested that cluster analysis may provide a generally useful tool in the interpretation of data from multi-phasic laboratory testing procedures. |
| |
| Keywords: | Present address: The Australian National University Canberra (Australia). |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
