TY - JOUR A1 - Vollmer, Andreas A1 - Vollmer, Michael A1 - Lang, Gernot A1 - Straub, Anton A1 - Kübler, Alexander A1 - Gubik, Sebastian A1 - Brands, Roman C. A1 - Hartmann, Stefan A1 - Saravi, Babak T1 - Performance analysis of supervised machine learning algorithms for automatized radiographical classification of maxillary third molar impaction JF - Applied Sciences N2 - Background: Oro-antral communication (OAC) is a common complication following the extraction of upper molar teeth. The Archer and the Root Sinus (RS) systems can be used to classify impacted teeth in panoramic radiographs. The Archer classes B-D and the Root Sinus classes III, IV have been associated with an increased risk of OAC following tooth extraction in the upper molar region. In our previous study, we found that panoramic radiographs are not reliable for predicting OAC. This study aimed to (1) determine the feasibility of automating the classification (Archer/RS classes) of impacted teeth from panoramic radiographs, (2) determine the distribution of OAC stratified by classification system classes for the purposes of decision tree construction, and (3) determine the feasibility of automating the prediction of OAC utilizing the mentioned classification systems. Methods: We utilized multiple supervised pre-trained machine learning models (VGG16, ResNet50, Inceptionv3, EfficientNet, MobileNetV2), one custom-made convolutional neural network (CNN) model, and a Bag of Visual Words (BoVW) technique to evaluate the performance to predict the clinical classification systems RS and Archer from panoramic radiographs (Aim 1). We then used Chi-square Automatic Interaction Detectors (CHAID) to determine the distribution of OAC stratified by the Archer/RS classes to introduce a decision tree for simple use in clinics (Aim 2). Lastly, we tested the ability of a multilayer perceptron artificial neural network (MLP) and a radial basis function neural network (RBNN) to predict OAC based on the high-risk classes RS III, IV, and Archer B-D (Aim 3). Results: We achieved accuracies of up to 0.771 for EfficientNet and MobileNetV2 when examining the Archer classification. For the AUC, we obtained values of up to 0.902 for our custom-made CNN. In comparison, the detection of the RS classification achieved accuracies of up to 0.792 for the BoVW and an AUC of up to 0.716 for our custom-made CNN. Overall, the Archer classification was detected more reliably than the RS classification when considering all algorithms. CHAID predicted 77.4% correctness for the Archer classification and 81.4% for the RS classification. MLP (AUC: 0.590) and RBNN (AUC: 0.590) for the Archer classification as well as MLP 0.638) and RBNN (0.630) for the RS classification did not show sufficient predictive capability for OAC. Conclusions: The results reveal that impacted teeth can be classified using panoramic radiographs (best AUC: 0.902), and the classification systems can be stratified according to their relationship to OAC (81.4% correct for RS classification). However, the Archer and RS classes did not achieve satisfactory AUCs for predicting OAC (best AUC: 0.638). Additional research is needed to validate the results externally and to develop a reliable risk stratification tool based on the present findings. KW - oro-antral communication KW - oro-antral fistula KW - prediction KW - machine learning KW - teeth extraction KW - complications KW - classification KW - artificial intelligence Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-281662 SN - 2076-3417 VL - 12 IS - 13 ER - TY - JOUR A1 - Vollmer, Andreas A1 - Saravi, Babak A1 - Vollmer, Michael A1 - Lang, Gernot Michael A1 - Straub, Anton A1 - Brands, Roman C. A1 - Kübler, Alexander A1 - Gubik, Sebastian A1 - Hartmann, Stefan T1 - Artificial intelligence-based prediction of oroantral communication after tooth extraction utilizing preoperative panoramic radiography JF - Diagnostics N2 - Oroantral communication (OAC) is a common complication after tooth extraction of upper molars. Profound preoperative panoramic radiography analysis might potentially help predict OAC following tooth extraction. In this exploratory study, we evaluated n = 300 consecutive cases (100 OAC and 200 controls) and trained five machine learning algorithms (VGG16, InceptionV3, MobileNetV2, EfficientNet, and ResNet50) to predict OAC versus non-OAC (binary classification task) from the input images. Further, four oral and maxillofacial experts evaluated the respective panoramic radiography and determined performance metrics (accuracy, area under the curve (AUC), precision, recall, F1-score, and receiver operating characteristics curve) of all diagnostic approaches. Cohen's kappa was used to evaluate the agreement between expert evaluations. The deep learning algorithms reached high specificity (highest specificity 100% for InceptionV3) but low sensitivity (highest sensitivity 42.86% for MobileNetV2). The AUCs from VGG16, InceptionV3, MobileNetV2, EfficientNet, and ResNet50 were 0.53, 0.60, 0.67, 0.51, and 0.56, respectively. Expert 1–4 reached an AUC of 0.550, 0.629, 0.500, and 0.579, respectively. The specificity of the expert evaluations ranged from 51.74% to 95.02%, whereas sensitivity ranged from 14.14% to 59.60%. Cohen's kappa revealed a poor agreement for the oral and maxillofacial expert evaluations (Cohen's kappa: 0.1285). Overall, present data indicate that OAC cannot be sufficiently predicted from preoperative panoramic radiography. The false-negative rate, i.e., the rate of positive cases (OAC) missed by the deep learning algorithms, ranged from 57.14% to 95.24%. Surgeons should not solely rely on panoramic radiography when evaluating the probability of OAC occurrence. Clinical testing of OAC is warranted after each upper-molar tooth extraction. KW - artificial intelligence KW - deep learning KW - X-ray KW - tooth extraction KW - oroantral fistula KW - operative planning Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-278814 SN - 2075-4418 VL - 12 IS - 6 ER - 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 - Winter, Anna A1 - Schulz, Stefan M. A1 - Schmitter, Marc A1 - Brands, Roman C. A1 - Straub, Anton A1 - Kübler, Alexander A1 - Borgmann, Anna A1 - Hartmann, Stefan T1 - Oral-health-related quality of life in patients with medication-related osteonecrosis of the jaw: a prospective clinical study JF - International Journal of Environmental Research and Public Health N2 - Medication-related osteonecrosis of the jaw (MRONJ) represents an adverse side effect of antiresorptive and antiangiogenic medications. It is associated with impaired quality of life, oral health, and oral function and can be classified into various stages. The purpose of this prospective clinical study is to evaluate the impact of stages I and II MRONJ on oral-health-related quality of life (OHRQoL) and related parameters. Patients’ OHRQoL, satisfaction with life, oral discomfort, and oral health were assessed using the German version of the Oral Health Impact Profile (OHIP-G49), visual analog scales (VAS), and Satisfaction with Life Scale (SWLS) at baseline (T0), 10 days (T1), and 3 months after treatment (T2) in 36 patients. Data were analyzed using Kolmogorov–Smirnov test, two-way mixed ANOVAs, and follow-up Mann–Whitney U tests. The impact of treatment effects on the original seven OHIP domain structures and the recently introduced four-dimensional OHIP structure were evaluated using linear regression analysis. Thirty-six patients received surgical MRONJ treatment. Before treatment, patients’ perceived OHRQoL, oral discomfort, oral health, and satisfaction with life were negatively affected by MRONJ. Surgical treatment significantly improved OHRQoL and related parameters (all p ≤ 0.012). This improvement was greater in patients with higher impairment at T0. OHRQoL and oral restrictions were still impaired after treatment in patients who needed prosthetic treatment. The four-dimensional structure revealed valuable information beyond the standard seven OHIP domains. Increased awareness of MRONJ risks and an interdisciplinary treatment approach for MRONJ patients are needed. KW - oral-health-related quality of life KW - satisfaction with life KW - oral health KW - medication-related osteonecrosis of the jaw KW - treatment benefit KW - OHIP-49 KW - SWLS Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-288141 SN - 1660-4601 VL - 19 IS - 18 ER - TY - JOUR A1 - Straub, Anton A1 - Stapf, Maximilian A1 - Fischer, Markus A1 - Vollmer, Andreas A1 - Linz, Christian A1 - Lâm, Thiên-Trí A1 - Kübler, Alexander A1 - Brands, Roman C. A1 - Scherf-Clavel, Oliver A1 - Hartmann, Stefan T1 - Bone concentration of ampicillin/sulbactam: a pilot study in patients with osteonecrosis of the jaw JF - International Journal of Environmental Research and Public Health N2 - Osteonecrosis of the jaw (ONJ) occurs typically after irradiation of the head and neck area or after the intake of antiresorptive agents. Both interventions can lead to compromised bone perfusion and can ultimately result in infection and necrosis. Treatment usually consists of surgical necrosectomy and prolonged antibiotic therapy, usually through beta-lactams such as ampicillin/sulbactam. The poor blood supply in particular raises the question as to whether this form of antibiosis can achieve sufficient concentrations in the bone. Therefore, we investigated the antibiotic concentration in plasma and bone samples in a prospective study. Bone samples were collected from the necrosis core and in the vital surrounding bone. The measured concentrations in plasma for ampicillin and sulbactam were 126.3 ± 77.6 and 60.2 ± 35.0 µg/mL, respectively. In vital bone and necrotic bone samples, the ampicillin/sulbactam concentrations were 6.3 ± 7.8/1.8 ± 2.0 µg/g and 4.9 ± 7.0/1.7 ± 1.7 µg/g, respectively. These concentrations are substantially lower than described in the literature. However, the concentration seems sufficient to kill most bacteria, such as Streptococci and Staphylococci, which are mostly present in the biofilm of ONJ. We, therefore, conclude that intravenous administration of ampicillin/sulbactam remains a valuable treatment in the therapy of ONJ. Nevertheless, increasing resistance of Escherichia coli towards beta-lactam antibiotics have been reported and should be considered. KW - osteonecrosis of the jaw KW - ARONJ KW - MRONJ KW - ONJ KW - osteoradionecrosis KW - antibiotic bone concentration KW - jaw bone KW - beta-lactam KW - ampicillin Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-297413 SN - 1660-4601 VL - 19 IS - 22 ER -