Integrated biomarker profiling of smokers with periodontitis

Abstract

In the context of precision medicine, understanding patient-specific variation is an important step in developing targeted and patient-tailored treatment regimens for periodontitis. While several studies have successfully demonstrated the usefulness of molecular expression profiling in conjunction with single classifier systems in discerning distinct disease groups, the majority of these studies do not provide sufficient insights into potential variations within the disease groups. Aim The goal of the present study is to discern biological response profiles of periodontitis and non-periodontitis smoking subjects using an informed panel of biomarkers across multiple scales (salivary, oral microbiome, pathogens and other markers). Materials and Methods The investigation uses a novel ensemble classification approach (SVA-SVM) to differentiate disease groups and patient-specific biological variation of systemic inflammatory mediators and IgG antibody to oral commensal and pathogenic bacteria within the groups. Results Sensitivity of SVA-SVM is shown to be considerably higher than several traditional independent classifier systems. Patient-specific networks generated from SVA-SVM are also shown to reveal cross-talk between biomarkers in discerning the disease groups. High-confidence classifiers in these network abstractions comprised of host responses to microbial infection elucidated their critical role in discerning the disease groups. Conclusions Host adaptive immune responses to the oral colonization/infection contribute significantly to creating the profiles specific for periodontitis patients with potential to assist in defining patient-specific risk profiles and tailored interventions.

Biologic modelling of periodontal disease progression

“…This study reports the modelling of periodontal disease progression using a combination of biomarkers in conjunction with traditional single classifier systems and an ensemble predictive modelling framework (Nagarajan et al., ). Our results demonstrate the synergistic role of baseline biomarker expression profiles contained in biological fluids and subgingival plaque in identifying progressors prior to clinical detection.…”

“…The ensemble predictive modelling framework is a variant of our recently proposed approach (Nagarajan et al., ; Nagarajan & Upreti, , ) and uses pairs of biomarkers as features in order to generate multiple base classifiers in conjunction with a resampling and majority voting strategy. The merits of the ensemble framework over traditional single classifier systems are also discussed in our earlier studies (Nagarajan, Miller, Dawson, Al‐Sabbagh, & Ebersole, ; Nagarajan & Upreti, , ; Nagarajan et al., ). The training and testing phases of the predictive modelling framework are shown in Figure .…”

“…Various studies have characterized the microbiome, which could contain novel biomolecular targets and provide insight into disease variation (Kilian et al, 2016). Molecules in saliva and serum have also provided insights into the potential biology of the disease (Ebersole, Nagarajan, Akers, & Miller, 2015;Gursoy et al, 2016;Kinney et al, 2011;Nagarajan, Al-Sabbagh, Dawson, & Ebersole, 2017;Yoon, Cheng, Philipone, Turner, & Lamster, 2012). However, our understanding of these bacterial-host biological interactions is generally limited.…”

Salivary Levels of NLRP3 Inflammasome‐Related Proteins as Potential Biomarkers of Periodontal Clinical Status

“…In the context of personalized medicine, understanding patient‐specific variation is an important step in developing targeted and patient‐tailored treatment regimens for periodontitis 32 . Accordingly, several studies 33‐37 have unveiled the potential to identify and measure panels of biomarkers in saliva for diagnosing periodontal diseases and monitoring not only progression of periodontopathogenic processes but also periodontal health 34 . In this line, some studies have provided novel insights regarding inflammasome‐related proteins across the spectrum of periodontal disease, 15‐17,38‐41 and compelling evidence suggests that oral biofilms may concomitantly regulate expression of inflammasomes and their associated cytokine targets 16‐18,39‐41 .…”

The potential of salivary biomarkers for predicting the sensitivity and monitoring the response to nonsurgical periodontal therapy: A preliminary assessment

“…The observation window (4‐6 weeks) was relatively short in this study; longer‐term large‐scale studies with consideration of disease severity, activity, and bacterial profiles are needed to confirm the predictability, sensitivity, and specificity of these salivary biomarkers. Furthermore, considering patient‐specific variations in biomarker profiles and clinical conditions, alternative statistical analyses, such as support vector machine and selective voting ensemble classification approaches, may be feasible for integrating and identifying the relevance of salivary biomarkers with periodontitis progression and treatment responses …”