Patient-Specific Variations in Biomarkers across Gingivitis and Periodontitis

Abstract

This study investigates the use of saliva, as an emerging diagnostic fluid in conjunction with classification techniques to discern biological heterogeneity in clinically labelled gingivitis and periodontitis subjects (80 subjects; 40/group) A battery of classification techniques were investigated as traditional single classifier systems as well as within a novel selective voting ensemble classification approach (SVA) framework. Unlike traditional single classifiers, SVA is shown to reveal patient-specific variations within disease groups, which may be important for identifying proclivity to disease progression or disease stability. Salivary expression profiles of IL-1ß, IL-6, MMP-8, and MIP-1α from 80 patients were analyzed using four classification algorithms (LDA: Linear Discriminant Analysis [LDA], Quadratic Discriminant Analysis [QDA], Naïve Bayes Classifier [NBC] and Support Vector Machines [SVM]) as traditional single classifiers and within the SVA framework (SVA-LDA, SVA-QDA, SVA-NB and SVA-SVM). Our findings demonstrate that performance measures (sensitivity, specificity and accuracy) of traditional classification as single classifier were comparable to that of the SVA counterparts using clinical labels of the samples as ground truth. However, unlike traditional single classifier approaches, the normalized ensemble vote-counts from SVA revealed varying proclivity of the subjects for each of the disease groups. More importantly, the SVA identified a subset of gingivitis and periodontitis samples that demonstrated a biological proclivity commensurate with the other clinical group. This subset was confirmed across SVA-LDA, SVA-QDA, SVA-NB and SVA-SVM. Heatmap visualization of their ensemble sets revealed lack of consensus between these subsets and the rest of the samples within the respective disease groups indicating the unique nature of the patients in these subsets. While the source of variation is not known, the results presented clearly elucidate the need for novel approaches that accommodate inherent heterogeneity and personalized variations within disease groups in diagnostic characterization. The proposed approach falls within the scope of P4 medicine (predictive, preventive, personalized, and participatory) with the ability to identify unique patient profiles that may predict specific disease trajectories and targeted disease management.

Matrix metalloproteinase‐8 levels in periodontal disease patients: A systematic review

“…It results from the interaction of periodontopathogenic bacteria with the host immune‐inflammatory response. To date, several components in oral fluids have been proposed as possible biomarkers for periodontitis, but most appear to have limited usefulness because they reflect inflammation rather than loss of periodontal support …”

Influence of Periodontal Clinical Status on Salivary Levels of Glutathione Reductase

“…A large milieu of multiple periodontal disease biomarkers have been described in oral fluids originating from periodontopathic bacteria or from the host response, so that biologic active substances involved in this process might build a pool of possible biomarkers for the periodontopathogenic process 28 . Given that the use of salivary biomarkers could help dentistry move toward the era of personalized medicine and that individualized clinical decision‐making in periodontology requires significant improvement in the ability to define risk and predict disease progression, 28 , 29 molecular and immunologic analyses are essential to verify the effect of other factors associated with variations in clinical characteristics of AgP and CP. Among these, several studies associate periodontal diseases with an imbalance between oxidants and antioxidants, thus suggesting that this imbalance can be the result of an increase in FR production and/or a defect in antioxidant activity 17,20,30‐32 .…”

“…Although the majority of tissue breakdown observed in periodontal diseases is considered to be the result of an altered inflammatory/immune response to microbial plaque that involves the massive release of PMNs, FRs, ROS, and the reduction of antioxidant enzyme levels, 29,35‐39 little is known about the significance of salivary concentration of GR regarding periodontal clinical status. In contrast with the findings of previous studies in which no differences 14 , 19 or diminished GR levels have been detected in CP, 17 , 20 the data presented herein showed that the activity of GR not only differed significantly between the two periodontitis groups, being significantly greater in patients with AgP, but also was significantly greater than that observed in the saliva of periodontally HCs.…”

Integrated biomarker profiling of smokers with periodontitis

“…The present study applies an ensemble classification framework ( SVA : selective‐voting ensemble classification approach) (Nagarajan et al. , Nagarajan & Upreti ) for discerning the biology of periodontitis and non‐periodontitis populations, while providing insights into potential variations within the periodontitis population. In a recent study (Nagarajan et al.…”

“…In a recent study (Nagarajan et al. ), we had demonstrated the usefulness of SVA in understanding potential variations between gingivitis and periodontitis populations using four critical salivary biomarkers (IL‐1ß, IL‐6, MIP‐1 α , MMP‐8) corresponding to fundamental biologic processes driving the disease such as inflammation, tissue destruction and bone remodelling (Ebersole et al. , Hajishengallis & Sahingur , Reynolds , Hienz et al.…”