TY - JOUR A1 - Vollmer, Andreas A1 - Vollmer, Michael A1 - Lang, Gernot A1 - Straub, Anton A1 - Shavlokhova, Veronika A1 - Kübler, Alexander A1 - Gubik, Sebastian A1 - Brands, Roman A1 - Hartmann, Stefan A1 - Saravi, Babak T1 - Associations between periodontitis and COPD: An artificial intelligence-based analysis of NHANES III JF - Journal of Clinical Medicine N2 - A number of cross-sectional epidemiological studies suggest that poor oral health is associated with respiratory diseases. However, the number of cases within the studies was limited, and the studies had different measurement conditions. By analyzing data from the National Health and Nutrition Examination Survey III (NHANES III), this study aimed to investigate possible associations between chronic obstructive pulmonary disease (COPD) and periodontitis in the general population. COPD was diagnosed in cases where FEV (1)/FVC ratio was below 70% (non-COPD versus COPD; binary classification task). We used unsupervised learning utilizing k-means clustering to identify clusters in the data. COPD classes were predicted with logistic regression, a random forest classifier, a stochastic gradient descent (SGD) classifier, k-nearest neighbors, a decision tree classifier, Gaussian naive Bayes (GaussianNB), support vector machines (SVM), a custom-made convolutional neural network (CNN), a multilayer perceptron artificial neural network (MLP), and a radial basis function neural network (RBNN) in Python. We calculated the accuracy of the prediction and the area under the curve (AUC). The most important predictors were determined using feature importance analysis. Results: Overall, 15,868 participants and 19 feature variables were included. Based on k-means clustering, the data were separated into two clusters that identified two risk characteristic groups of patients. The algorithms reached AUCs between 0.608 (DTC) and 0.953% (CNN) for the classification of COPD classes. Feature importance analysis of deep learning algorithms indicated that age and mean attachment loss were the most important features in predicting COPD. Conclusions: Data analysis of a large population showed that machine learning and deep learning algorithms could predict COPD cases based on demographics and oral health feature variables. This study indicates that periodontitis might be an important predictor of COPD. Further prospective studies examining the association between periodontitis and COPD are warranted to validate the present results. KW - COPD KW - periodontitis KW - bone loss KW - machine learning KW - prediction KW - artificial intelligence KW - model KW - gingivitis Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-312713 SN - 2077-0383 VL - 11 IS - 23 ER - TY - JOUR A1 - Jockel-Schneider, Yvonne A1 - Stoelzel, Peggy A1 - Hess, Jeanine A1 - Haubitz, Imme A1 - Fickl, Stefan A1 - Schlagenhauf, Ulrich T1 - Impact of a specific collagen peptide food supplement on periodontal inflammation in aftercare patients — a randomised controlled trial JF - Nutrients N2 - Background: This controlled clinical trial evaluated the impact of a specific collagen peptide food supplement on parameters of periodontal inflammation in aftercare patients. Methods: A total of 39 study patients were enrolled. At baseline, bleeding on probing (BoP; primary outcome), gingival index (GI), plaque control record (PCR), recession (REC) and probing pocket depth (PPD) for the calculation of the periodontal inflamed surface area (PISA) were documented. After subsequent professional mechanical plaque removal (PMPR), participants were randomly provided with a supply of sachets containing either a specific collagen peptide preparation (test group; n = 20) or a placebo (placebo group; n = 19) to be consumed dissolved in liquid once daily until reevaluation at day 90. Results: PMPR supplemented with the consumption of the specific collagen peptides resulted in a significantly lower mean percentage of persisting BoP-positive sites than PMPR plus placebo (test: 10.4% baseline vs. 3.0% reevaluation; placebo: 14.2% baseline vs. 9.4% reevaluation; effect size: 0.86). Mean PISA and GI values were also reduced compared to baseline, with a significant difference in favor of the test group (PISA test: 170.6 mm\(^2\) baseline vs. 53.7 mm\(^2\) reevaluation; PISA placebo: 229.4 mm\(^2\) baseline vs. 184.3 mm\(^2\) reevaluation; GI test: 0.5 baseline vs. 0.1 reevaluation; GI placebo: 0.4 baseline vs. 0.3 reevaluation). PCR was also significantly decreased in both experimental groups at revaluation, but the difference between the groups did not reach the level of significance. Conclusions: The supplementary intake of specific collagen peptides may further enhance the anti-inflammatory effect of PMPR in periodontal recall patients. KW - collagen KW - peptide fragment KW - bleeding on probing KW - gingival KW - food supplement KW - periodontitis KW - gingivitis Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-290471 SN - 2072-6643 VL - 14 IS - 21 ER - TY - JOUR A1 - Schlagenhauf, Ulrich A1 - Rehder, Juliane A1 - Gelbrich, Götz A1 - Jockel‐Schneider, Yvonne T1 - Consumption of Lactobacillus reuteri‐containing lozenges improves periodontal health in navy sailors at sea: A randomized controlled trial JF - Journal of Periodontology N2 - Background The objective of this trial was to evaluate whether the regular consumption of probiotics may improve the known deterioration of periodontal health in navy sailors during deployments at sea. Methods 72 healthy sailors of a naval ship on a practicing mission at sea were recruited and randomly provided with a blinded supply of lozenges to be consumed twice daily for the following 42 days containing either the probiotic strains Lactobacillus reuteri (DSM 17938 and L. reuteri (ATTC PTA 5289) (test n = 36) or no probiotics (placebo n = 36). At baseline, at day 14 and day 42 bleeding on probing (primary outcome), gingival index, plaque control record, probing attachment level, and probing pocket depth were assessed at the Ramfjord teeth. Results At baseline there were no significant differences between the groups. At day 14 and day 42 test group scores of all assessed parameters were significantly improved (P < 0.001) compared to baseline and to the placebo group which by contrast showed a significant (P < 0.001) deterioration of all parameters at the end of the study. Conclusions The consumption of probiotic L. reuteri‐lozenges is an efficacious measure to improve and maintain periodontal health in situations with waning efficacy of personal oral hygiene. KW - gingivitis KW - oral hygiene KW - probiotics Y1 - 2020 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-215577 VL - 91 IS - 10 SP - 1328 EP - 1338 ER -