A Novel Evidence-Based Periodontal Prognosis Model

Deep learning in periodontology and oral implantology: A scoping review

Deep learning (DL) has been employed for a wide range of tasks in dentistry. We aimed to systematically review studies employing DL for periodontal and implantological purposes. A systematic electronic search was conducted on four databases (Medline via PubMed, Google Scholar, Scopus, and Embase) and a repository (ArXiv) for publications after 2010, without any limitation on language. In the present review, we included studies that reported deep learning models' performance on periodontal or oral implantological tasks. Given the heterogeneities in the included studies, no meta-analysis was performed. The risk of bias was assessed using the QUADAS-2 tool. We included 47 studies: focusing on imaging data (n = 20) and non-imaging data in periodontology (n = 12), or dental implantology (n = 15). The detection of periodontitis and gingivitis or periodontal bone loss, the classification of dental implant systems, or the prediction of treatment outcomes in periodontology and implantology were major use cases. The performance of the models was generally high. However, it varied given the employed methods (which includes various types of convolutional neural networks (CNN) and multi-layered perceptron (MLP)), the variety in specific modeling tasks, as well as the chosen and reported outcomes, outcome measures and outcome level. Only a few studies (n = 7) showed a low risk of bias across all assessed domains. A growing number of studies evaluated DL for periodontal or implantological objectives. Heterogeneity in study design, poor reporting and a high risk of bias severely limit the comparability of studies and the robustness of the overall evidence.

lncRNA FGD5-AS1 and miR-130a Can Be Used for Prognosis Analysis of Patients with Chronic Periodontitis

Background

lncRNA and microRNA affect the occurrence and development of many diseases, so they are expected to become diagnostic or predictive indicators. But the relationship between lncRNA FGD5-AS1 and miR-130a and the prognosis of chronic periodontitis is still unclear. The purpose of this study is to explore the prognostic value of the two in chronic periodontitis.

Objective

This study set out to investigate the prognostic value of lncRNA FGD5-AS1 and miR-130a in chronic periodontitis.

Methods

Eighty-seven patients with chronic periodontitis who visited our hospital from March 2016 to August 2017 were collected as an observation group (OG), and 72 subjects with periodontal health who underwent physical examination at the same time were collected as a control group (CG). The FGD5-AS1 and miR-130a expression levels of subjects in the two groups were compared, and prognosis of 87 patients who were reviewed one year later was counted. The expression levels of patients with different prognoses were compared when they were admitted to our hospital. We drew the ROC curve and explored the prognostic value of FGD5-AS1 and miR-130a. The risk factors for adverse prognosis were analyzed through logistic regression.

Results

FGD5-AS1 was lowly expressed in patients, while miR-130a was highly expressed. FGD5-AS1 and miR-130a had certain diagnostic and predictive value in chronic periodontitis and patient prognosis. The higher the periodontal pocket, the higher the attachment loss. Lower FGD5-AS1 and higher miR-130a levels were independent prognostic risk factors.

Conclusion

lncRNA FGD5-AS1 is lowly expressed in patients with chronic periodontitis, while miR-130a is highly expressed. Both of them have certain diagnostic and prognostic value in chronic periodontitis and may be potential diagnostic and prognostic indicators.

Periodontal referral patterns in Norway: 2003 versus 2018

Objectives

Changes in periodontal referral patterns over time have been reported from the United States and Australia. To date, comparable studies have not been published from Europe. The objectives of the present study were to examine changes in periodontal referral patterns in Norway in 2003 versus 2018 and to compare these with trends observed in the United States and Australia using universal criteria for grading of periodontal severity.

Materials and methods

A retrospective analysis of 369 charts from four Norwegian periodontics clinics was completed. Data on year of referral, gender, age, tobacco smoking, periodontal status and missing teeth at initial examination, teeth planned for extraction, and periodontal case type were collected using a survey format; case type I, II, III, and IV representing increasing severity of periodontitis, case type V representing referral for other periodontal conditions (peri‐implantitis, refractory periodontitis, etc.). Chi‐square, t‐tests, and negative binomial regression were used for the statistical analysis.

Results

Compared with 2003, the 2018 data showed an increase in mean age at referral (p < 0.05), overall distribution of case type III and V (p = 0.047), and number of missing teeth (p = 0.001). Further, a decrease in prevalence of smokers (p < 0.05), but no change in number of teeth planned for extraction (p = 0.104), were observed.

Conclusions

During a period of 15 years, changes in periodontal referral patterns in Norway are similar to those in the United States and Australia. The adoption of a guideline‐based referral practice might be beneficial for both the dental profession and patients.

Development of a prognostic tool: based on risk factors for tooth loss after active periodontal therapy

Objectives

The aim of this study was to develop a prognostic tool to estimate long-term tooth retention in periodontitis patients at the beginning of active periodontal therapy (APT).

Material and methods

Tooth-related factors (type, location, bone loss (BL), infrabony defects, furcation involvement (FI), abutment status), and patient-related factors (age, gender, smoking, diabetes, plaque control record) were investigated in patients who had completed APT 10 years before. Descriptive analysis was performed, and a generalized linear-mixed model-tree was used to identify predictors for the main outcome variable tooth loss. To evaluate goodness-of-fit, the area under the curve (AUC) was calculated using cross-validation. A bootstrap approach was used to robustly identify risk factors while avoiding overfitting.

Results

Only a small percentage of teeth was lost during 10 years of supportive periodontal therapy (SPT; 0.15/year/patient). The risk factors abutment function, diabetes, and the risk indicator BL, FI, and age (≤ 61 vs. > 61) were identified to predict tooth loss. The prediction model reached an AUC of 0.77.

Conclusion

This quantitative prognostic model supports data-driven decision-making while establishing a treatment plan in periodontitis patients. In light of this, the presented prognostic tool may be of supporting value.

Clinical relevance

In daily clinical practice, a quantitative prognostic tool may support dentists with data-based decision-making. However, it should be stressed that treatment planning is strongly associated with the patient’s wishes and adherence. The tool described here may support establishment of an individual treatment plan for periodontally compromised patients.

Diagnostic sensitivity and specificity of host-derived salivary biomarkers in periodontal disease amongst adults: Systematic review

OBJECTIVE

To systematically assess the diagnostic value of host-derived salivary biomarkers based on their reported sensitivity and specificity in relation to clinical parameters of periodontal disease diagnosis in adults.

MATERIALS AND METHODS

Comprehensive search of PubMed, Nature, Cochrane and OVID (Embase, MEDLINE [R] and PsycINFO) was conducted up to 1 August 2018, using key terms relevant to the research questions and Cochrane methodology, supplemented by a grey literature search. The revised Quality Assessment of Diagnostic Accuracy Studies (QUADAS- 2) tool was used to assess the methodological quality of all included studies.

RESULTS

Seven studies were included in the review. Macrophage inflammatory protein-1αlpha (MIP-1α), interleukin-1beta (IL-1β), interleukin-6 (IL-6) and matrix metalloproteinase-8 (MMP-8) were identified as diagnostically acceptable biomarkers for periodontal disease. Overall, the combination of IL-6 and MMP-8 showed best diagnostic performance. Also, a combination of the four key biomarkers (IL-1β, IL-6, MMP-8 and MIP-1α) showed promising results for distinction between gingivitis and periodontitis, as well as for periodontitis compared with gingival health. Results are interpreted with caution due to limitations in the number of studies included and their quality.

CONCLUSION

Certain salivary biomarkers can potentially be useful in combination and singularly for the diagnosis of periodontal disease. However, further methodically robust research is required to validate these biomarkers.