Changes in the Salivary Metabolic Profile of Generalized Periodontitis Patients after Non-surgical Periodontal Therapy: A Metabolomic Analysis Using Nuclear Magnetic Resonance Spectroscopy

Abstract

Pattern analysis of the salivary metabolic profile has been proven accurate in discriminating between generalized periodontitis (GP) patients and healthy individuals (HI), as this disease modifies the salivary concentrations of specific metabolites. Due to the scarcity of data from previous studies, this study aimed to evaluate if non-surgical periodontal therapy (NST) could affect the metabolomic profile in GP patients' saliva and if it compares to that of HI. Unstimulated salivary samples were collected from 11 HI and 12 GP patients before and 3 months after NST. Nuclear Magnetic Resonance (NMR) spectroscopy, followed by a supervised multivariate statistical approach on entire saliva spectra and partial least square (PLS) discriminant analysis, were performed to obtain metabolic profiles. In the GP group, periodontal treatment improved all clinical parameters, but not all the diseased sites were eradicated. PLS revealed an accuracy of 100% in distinguishing between metabolic profiles of GP patients before and after NST. Orthogonal projection to latent structure was able to discriminate between the three groups of subjects with an accuracy of 85.6%. However, the post-NST metabolic profile of GP patients could not be completely assimilated to that of HI. Although NST may produce significant changes in the metabolic profile, GP patients maintained a distinctive fingerprint compared to HI.

Keywords: diagnosis; metabolomics; periodontal therapy; periodontitis; saliva.

Figure 1

Score plot of Multilevel partial least square (PLS) pairwise discrimination of baseline (B) and after therapy (AT) salivary samples in generalized periodontitis (GP) patients. p-value calculated using a premutation test procedure was <0.01 (p = 0.0099).

Figure 2

Projection of the proton nuclear magnetic resonance (¹H NMR) spectral buckets on the two dimensions of the Orthogonal Projections to Latent Structures-Discriminant Analysis (OPLS-DA) considering the subspace for healthy individuals (HI) and generalized periodontitis (GP) patients at two different treatment stages (baseline, B, and after treatment, A)T. The relative confusion-matrix and overall predictive accuracy (calculated following 100 runs of Monte Carlo cross validation) are also reported. p-value calculated using a premutation test procedure was <0.01.

Figure 3

Boxplots representing the fluctuations of each metabolite among the three groups: GP patients at baseline (B, red box), GP patients after non-surgical therapy (AT, yellow box) and HI (healthy individuals, green box). p-value and FDR values are also reported. FDR < 0.05 is considered statistically significant.