Characterization of the COPD Salivary Fingerprint through Surface Enhanced Raman Spectroscopy: A Pilot Study

Abstract

Chronic Obstructive Pulmonary Disease (COPD) is a debilitating pathology characterized by reduced lung function, breathlessness and rapid and unrelenting decrease in quality of life. The severity rate and the therapy selection are strictly dependent on various parameters verifiable after years of clinical observations, missing a direct biomarker associated with COPD. In this work, we report the methodological application of Surface Enhanced Raman Spectroscopy combined with Multivariate statistics for the analysis of saliva samples collected from 15 patients affected by COPD and 15 related healthy subjects in a pilot study. The comparative Raman analysis allowed to determine a specific signature of the pathological saliva, highlighting differences in determined biological species, already studied and characterized in COPD onset, compared to the Raman signature of healthy samples. The unsupervised principal component analysis and hierarchical clustering revealed a sharp data dispersion between the two experimental groups. Using the linear discriminant analysis, we created a classification model able to discriminate the collected signals with accuracies, specificities, and sensitivities of more than 98%. The results of this preliminary study are promising for further applications of Raman spectroscopy in the COPD clinical field.

Keywords: COPD; SERS; multivariate analysis; saliva.

Figure 1

(A) Optical microscopy image (10×) of a saliva drop (3µL) dried at room temperature on a Calcium Fluoride disk. Scale bar 20 µm. In box, magnification (50×) of the volumetric mass after the drying procedure. (B) Average Raman spectrum of the saliva sample collected on the volumetric mass. The grey band represents the standard deviation. The black arrows indicate the most prominent peaks of interest.

Figure 2

(A) Raman average spectra of a drop of saliva dried on aluminum substrate. The grey band represents the standard deviation. The box shows the optical microscopic image of the sample (objective 50×). The black arrows indicate the attributed peaks. (B) Comparison between the salivary spectra obtained using CaF2 and aluminum as Raman substrates and the signal of the aluminum substrate without saliva (green line).

Figure 3

Average salivary Raman spectra collected from the experimental (A) COPD and (B) CTRL groups. The grey bands represent the standard deviations.

Figure 4

(A) Overlapped average Raman spectra collected from COPD (black) and CTRL (red) subjects, with the indications of the regions with the main differences (grey boxes). (B) Subtraction spectrum between COPD and CTRL groups. The grey band represents the error propagation calculated from the spectral standard deviations. The black arrows indicate the most important peaks.

Figure 5

Results of the Principal Component Analysis showing (A) the loadings and (B) the 3-D distribution with the 95% confidence ellipse of the Principal Component 1 (36.2%), Principal Component 2 (13.8%), and Principal Component 3 (10.4%) cumulatively representing the 60.3% of the components.

Figure 6

(A) Hierarchical clustering dendogram representing the unsupervised grouping of the Canonical Variables on the base of the Euclidean distance. The dashed line represents the convergence distance. (B) Dispersion of the Canonical Variable 1 for COPD and CTRL. *** p < 0.001 One-Way ANOVA test.