Trabeculae microstructure parameters serve as effective predictors for marginal bone loss of dental implant in the mandible 

2020 ◽  
Author(s):  
Hengguo Zhang ◽  
Jie Shan ◽  
Ping Zhang ◽  
Hongbing Jiang
Keyword(s):  
Machine Learning ◽  
Bone Loss ◽  
Trabecular Bone ◽  
Dental Implant ◽  
Early Stage ◽  
Superior Performance ◽  
Morphological Parameters ◽  
Marginal Bone Loss ◽  
Microstructure Parameters ◽  
Functional Loading

Abstract Background: To investigate the effectiveness and feasibility of machine learning models based on trabecular microstructure parameters for predicting the occurrence of marginal bone loss (MBL) of the submerged dental implant in mandible. Methods: Clinical variables and morphological parameters of trabecular bone were collected from 81 subjects with submerged implants in the mandible (41 cases of abnormal MBL and 40 as normal controls). We measured the peri-implant MBL level by a cone-beam computed tomography (CBCT) at the follow-up of 20.95±2.67 months after functional loading. The morphological parameters and possible factors associated with MBL were collected in a mean of 3.98±1.06 months at the early loading stage. All variables were analyzed using correlation and covariance matrices. Support vector machine (SVM), artificial neural network (ANN), logistic regression (LR) model and random forest (RF) were actualized to predict abnormal MBL.Results: At the early stage of functional loading, the abnormal MBL cases showed a significant increase of structure model index (SMI) and trabecular pattern factor (Tb.Pf) in peri-implant. Meanwhile, SMI and Tb.Pf simultaneously revealed a significantly high positive correlation with MBL. The SVM model exhibited the best outcome in predicting MBL (AUC = 0.967), followed by ANN (AUC = 0.928), LR (AUC = 0.906), RF (AUC = 0.842), SMI alone (AUC = 0.705) and Tb.Pf alone (AUC = 0.663). Compared with one single predictor, all algorithm models yielded significantly superior performance.Conclusion: Abnormal MBL cases demonstrated the premonitory morphological variation in trabecular bone at the early stage. MBL prediction could be achieved by machine learning methods.

scholarly journals Trabeculae microstructure parameters serve as effective predictors for marginal bone loss of dental implant in the mandible

2020 ◽  
Author(s):  
Hengguo Zhang ◽  
Jie Shan ◽  
Ping Zhang ◽  
Hongbing Jiang
Keyword(s):  
Machine Learning ◽  
Bone Loss ◽  
Trabecular Bone ◽  
Dental Implant ◽  
Early Stage ◽  
Superior Performance ◽  
Morphological Parameters ◽  
Marginal Bone Loss ◽  
Microstructure Parameters ◽  
Functional Loading

Abstract Background : To investigate the effectiveness and feasibility of machine learning models based on trabecular microstructure parameters for predicting the occurrence of marginal bone loss (MBL) of the submerged dental implant in mandible. Methods : Clinical variables and morphological parameters of trabecular bone were collected from 81 subjects with submerged implants in the mandible (41 cases of abnormal MBL and 40 as normal controls). We measured the peri-implant MBL level by a cone-beam computed tomography (CBCT) at the follow-up of 20.95±2.67 months after functional loading. The morphological parameters and possible factors associated with MBL were collected in a mean of 3.98±1.06 months at the early loading stage. All variables were analyzed using correlation and covariance matrices. Support vector machine (SVM), artificial neural network (ANN), logistic regression (LR) model and random forest (RF) were actualized to predict abnormal MBL. Results : At the early stage of functional loading, the abnormal MBL cases showed a significant increase of structure model index (SMI) and trabecular pattern factor (Tb.Pf) in peri-implant. Meanwhile, SMI and Tb.Pf simultaneously revealed a significantly high positive correlation with MBL. The LR model exhibited the best outcome in predicting MBL (AUC = 0.956), followed by SVM (AUC = 0.928), RF (AUC = 0.917), ANN (AUC = 0.900), SMI alone (AUC = 0.705) and Tb.Pf alone (AUC = 0.663). Compared with one single predictor, all algorithm models yielded significantly superior performance. Conclusion : Abnormal MBL cases demonstrated the premonitory morphological variation in trabecular bone at the early stage. MBL prediction could be achieved by machine learning methods.

scholarly journals Trabeculae microstructure parameters serve as effective predictors for marginal bone loss of dental implant in the mandible

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Hengguo Zhang ◽  
Jie Shan ◽  
Ping Zhang ◽  
Xin Chen ◽  
Hongbing Jiang
Keyword(s):  
Bone Loss ◽  
Dental Implant ◽  
Alveolar Bone ◽  
Early Stage ◽  
Support Vector ◽  
Marginal Bone Loss ◽  
Svm Model ◽  
Microstructure Parameters ◽  
Artificial Neural Network Ann ◽  
Normal Controls

Abstract Marginal bone loss (MBL) is one of the leading causes of dental implant failure. This study aimed to investigate the feasibility of machine learning (ML) algorithms based on trabeculae microstructure parameters to predict the occurrence of severe MBL. Eighty-one patients (41 severe MBL cases and 40 normal controls) were involved in the current study. Four ML models, including support vector machine (SVM), artificial neural network (ANN), logistic regression (LR), and random forest (RF), were employed to predict severe MBL. The area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity were used to evaluate the performance of these models. At the early stage of functional loading, severe MBL cases showed a significant increase of structure model index and trabecular pattern factor in peri-implant alveolar bone. The SVM model exhibited the best outcome in predicting MBL (AUC = 0.967, sensitivity = 91.67%, specificity = 100.00%), followed by ANN (AUC = 0.928, sensitivity = 91.67%, specificity = 93.33%), LR (AUC = 0.906, sensitivity = 91.67%, specificity = 93.33%), RF (AUC = 0.842, sensitivity = 75.00%, specificity = 86.67%). Together, ML algorithms based on the morphological variation of trabecular bone can be used to predict severe MBL.

scholarly journals Trabeculae microstructure parameters serve as effective predictors for marginal bone loss of dental implant in the mandible

2020 ◽  
Author(s):  
Hengguo Zhang ◽  
Jie Shan ◽  
Ping Zhang ◽  
Xin Chen ◽  
hongbing jiang
Keyword(s):  
Bone Loss ◽  
Dental Implant ◽  
Alveolar Bone ◽  
Early Stage ◽  
Support Vector ◽  
Marginal Bone Loss ◽  
Svm Model ◽  
Microstructure Parameters ◽  
Artificial Neural Network Ann ◽  
Normal Controls

Marginal bone loss (MBL) is one of the leading causes of dental implant failure. This study aimed to investigate the feasibility of machine learning (ML) algorithms based on trabeculae microstructure parameters to predict the occurrence of severe MBL. Eighty-one patients (41 severe MBL cases and 40 normal controls) were involved in the current study. Four ML models, including support vector machine (SVM), artificial neural network (ANN), logistic regression (LR), and random forest (RF), were employed to predict severe MBL. The area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity were used to evaluate the performance of these models. At the early stage of functional loading, severe MBL cases showed a significant increase of structure model index and trabecular pattern factor in peri-implant alveolar bone. The SVM model exhibited the best outcome in predicting MBL (AUC = 0.967, sensitivity = 91.67%, specificity=100.00%), followed by ANN (AUC = 0.928, sensitivity = 91.67%, specificity=93.33%), LR (AUC = 0.906, sensitivity = 91.67%, specificity = 93.33%), RF (AUC = 0.842, sensitivity = 75.00%, specificity = 86.67%). Together, ML algorithms based on the morphological variation of trabecular bone can be used to predict severe MBL.

scholarly journals Comparative Analysis of Peri-Implant Bone Loss in Extra-Short, Short, and Conventional Implants. A 3-Year Retrospective Study

2020 ◽  
Vol 17 (24) ◽  
pp. 9278
Author(s):  
Daycelí Estévez-Pérez ◽  
Naia Bustamante-Hernández ◽  
Carlos Labaig-Rueda ◽  
María Fernanda Solá-Ruíz ◽  
José Amengual-Lorenzo ◽  
...  
Keyword(s):  
Bone Loss ◽  
Survival Rates ◽  
Marginal Bone Loss ◽  
Posterior Maxilla ◽  
Group 3 ◽  
Group 2 ◽  
Wide Neck ◽  
Implant Length ◽  
Functional Loading ◽  
Group 1

Objective: To evaluate the influence of implant length on marginal bone loss, comparing implants of 4 mm, 6 mm, and >8 mm, supporting two splinted crowns after 36-month functional loading. Materials and Methods: this retrospective clinical trial evaluated the peri-implant behavior of splinted crowns (two per case) on pairs of implants of the same length placed in the posterior maxilla (molar area). Implants were divided into three groups according to length (Group 1: extra-short 4 mm; Group 2: short 6 mm; Group 3: conventional length >8 mm). Marginal bone loss was analyzed using standardized periapical radiographs at the time of loading and 36 months later. Results: 24 patients (19 women and 5 men) were divided into three groups, eight rehabilitations per group, in the position of the maxillary first and second molars. The 48 Straumann® Standard Plus (Regular Neck (RN)/Wide Neck (WN)) implants were examined after 36 months of functional loading. Statistical analysis found no significant differences in bone loss between the three groups (p = 0.421). No implant suffered biological complications or implant loss. Long implants were associated with less radiographic bone loss. Conclusions: extra-short (4 mm); short (6 mm); and conventional length (>8 mm) implants in the posterior maxilla present similar peri-implant bone loss and 100% survival rates in rehabilitation, by means of two splinted crowns after 36 months of functional loading. Implants placed in posterior positions present better bone loss results than implants placed in anterior positions, regardless of the interproximal area where bone loss is measured. Conventional length (>8 mm) implants show better behavior in terms of distal bone loss than short (6 mm) and extra-short (4 mm) implants.

scholarly journals Factors associated with the survival rate and the marginal bone loss of dental implant over 7-years loading

2018 ◽  
Vol 34 (3) ◽  
pp. 252-252
Author(s):  
Jung-Hyeok Choi ◽  
Jae-kwon Koh ◽  
Eun-Young Kwon ◽  
Ji-Young Joo ◽  
Ju-Youn Lee ◽  
...  
Keyword(s):  
Survival Rate ◽  
Bone Loss ◽  
Dental Implant ◽  
Marginal Bone Loss ◽  
Factors Associated

Dental Implant Thread Design and the Consequences on Long-Term Marginal Bone Loss

2016 ◽  
Vol 25 (4) ◽  
pp. 471-477 ◽  
Author(s):  
Zeev Ormianer ◽  
Shlomo Matalon ◽  
Jonathan Block ◽  
Jerry Kohen
Keyword(s):  
Bone Loss ◽  
Dental Implant ◽  
Marginal Bone Loss

scholarly journals Clinical and radiological of the effects of two different implant surfaces on marginal tissues

2021 ◽  
Vol 11 (Suppl. 1) ◽  
pp. 152-159
Author(s):  
Muhammet Bahattin Bingül ◽  
Belgin Gülsün
Keyword(s):  
Bone Loss ◽  
Dental Implants ◽  
Dental Implant ◽  
Surface Group ◽  
Plaque Index ◽  
X Rays ◽  
Marginal Bone Loss ◽  
Pocket Depth ◽  
Significant Difference ◽  
Roughened Surface

Aim: In this study, our aim is to compare the effects of dental implants with nano laser excimer technology surface (NLE) and dental implant surfaces (MTX) with micro-roughened surface on marginal tissues with clinical and radiological data. Methodology: A total of 117 dental implants were followed clinically and radiologically. Clinically; Plaque index (silness-leöe), bleeding index in boring, pocket depth were evaluated and recorded 1 week after the insertion of the healing cap, 3 months, 6 months and 12 months after the end of the prosthesis. In the same periods, periapical x-rays were taken with the Rinn Holder method and the amount of marginal bone loss was measured. The data were analyzed with IBM SPSS Statistics Version 22 package program. Results: There was no loss in the implants included in the study. There was no statistically significant difference between the groups in terms of plaque index, bleeding index values (p>0,05). However, the pocket depth of the dental implant group with nano laser excimer technology surface is significantly lower than the micro-roughened surface group. There are statistically significant differences between the groups in terms of radiological marginal bone loss at 0, 3, 6, and 12 months (p<0,05). Radiological marginal bone loss values ​​of the micro-roughened surface group at 0, 3, 6, and 12 months were significantly lower compared to the same periods of the nano laser excimer technology group. Conclusion: It has been determined that the surface properties of dental implants can be effective on marginal tissues. In addition, we believe that routine checks by dentists who perform dental implant applications will increase the success of dental implants.   How to cite this article: Bingül MB, Gülsün B. Clinical and radiological of the effects of two different implant surfaces on marginal tissues. Int Dent Res 2021;11(Suppl.1):152-9. https://doi.org/10.5577/intdentres.2021.vol11.suppl1.23     Linguistic Revision: The English in this manuscript has been checked by at least two professional editors, both native speakers of English.

scholarly journals Failure Rate, Marginal Bone Loss and Pink Esthetic of Socket-Shield Technique for Immediate Dental Implant Placement in the Esthetic Zone. A Systematic Review and Meta-Analysis

2021 ◽  
Author(s):  
Alvaro Zubizarreta Macho ◽  
Roberta Rucco ◽  
Sergio Toledano Gil ◽  
Juan Carlos Bernabeu Mira ◽  
Jose María Montiel-Company ◽  
...  
Keyword(s):  
Systematic Review ◽  
Bone Loss ◽  
Dental Implant ◽  
Failure Rate ◽  
Meta Analysis ◽  
Marginal Bone Loss ◽  
Implant Placement
Sign in / Sign up

Export Citation Format

Share Document