The use of cluster and discriminant analysis in the investigations of the role of trace metals in the pathogenesis of Parkinson's disease

The elemental data were processed using two multivariate techniques, namely cluster and discriminant analysis. The statistical methods were used for data reduction, both unsupervised and supervised classification as well as for the creation of a model that would simplify case identification based on the elemental analysis of SN tissue. The results of cluster analysis confirmed the statistical significance of the differences in elemental composition of PD and control SN nerve cells. Based on the results of discriminant analysis, the elements (P, Cl, Fe, Cu and Zn) that played the greatest role in the process of differentiation between neurons from examined groups were determined.