Application of Unsupervised Multivariate Analysis Methods to Raman Spectroscopic Assessment of Human Dental Enamel

Abstract

This work explores the suitability of data treatment methodologies for Raman spectra of teeth using multivariate analysis methods. Raman spectra were measured in our laboratory and obtained from control enamel samples and samples with a protective treatment before and after an erosive attack. Three different approaches for data treatment were undertaken in order to evaluate the aptitude of distinguishing between groups: A—Principal Component Analysis of the numerical parameters derived from deconvoluted spectra; B—PCA of average Raman spectra after baseline correction; and C—PCA of average raw Raman spectra. Additionally, Hierarchical Cluster Analysis were applied to Raman spectra of enamel measured with different laser wavelengths (638 nm or 785 nm) to evaluate the most suitable choice of illumination. According to the different approaches, PC1 scores obtained between control and treatment group were A—50.5%, B—97.1% and C—83.0% before the erosive attack and A—55.2%, B—93.2% and C—87.8% after an erosive attack. The obtained results showed that performing PCA analysis of raw or baseline corrected Raman spectra of enamel was not as efficient in the evaluation of samples with different treatments. Moreover, acquiring Raman spectra with a 785 nm laser increases precision in the data treatment methodologies.