Epidemiological trends, predictive factors, and projection of tooth loss in Germany 1997-2030: part I. missing teeth in adults and seniors.

OBJECTIVE: This is the first part of a report on tooth loss in Germany 1997-2030. Here, we describe trends in the prevalence of tooth loss in adults and seniors 1997-2014, assess predictive factors for tooth loss and projected it into 2030. MATERIAL AND METHODS: Data of the cross-sectional, multi-center, nationally representative German Oral Health Studies of 1997, 2005, and 2014 were used. Age, sex, educational level, smoking status, and the cohort were used for ordinary least square regression to assess the association of predictors with tooth loss (missing teeth, MT). The yielded regression coefficients were used to predict tooth loss in 2030. RESULTS: Compared with 1997, the mean MT in adults (35-44 years old) in 2030 was predicted to decrease by two-thirds to 1.3. The prevalence of tooth loss (MT > 0) will decrease by 72% from 1997 to 2030. In 2030, half of the population of adults will not exhibit any tooth loss. Compared with 1997, the mean MT among seniors (65-74 years old) will decline to 5.6 teeth (i. e. two-thirds reduction) until 2030. Prevalence of tooth loss will be halved by 2030, and approximately one-third of this age group will not exhibit any tooth loss. CONCLUSIONS: Based on the model used, the trend of a robust decline in tooth loss will become more dynamic by the year 2030. As a result, every second adult will have experienced no tooth loss at all in 2030, and seniors will possess more teeth than they have previously lost. CLINICAL RELEVANCE: This study presents the trends of tooth loss in Germany for a period of three decades. It provides clinically relevant data for health care planning by 2030.

[Consensus recommendations on minimally invasive removal of carious tissue from dentine]. / Aanbevelingen van een consensus­bijeenkomst over weefselsparende manieren om carieus weefsel uit dentine te verwijderen.

The International Caries Consensus Collaboration (ICCC) presented recommendations on terminology, methods of carious tissue removal and managing cavitated carious lesions. It identified 'dental caries' as the disease that dentists should manage by controlling the activity of existing cavitated lesions by preserving as much hard tissue as possible, maintaining pulp sensibility and retaining functional teeth in the long-term. The ICCC recommended the level of hardness as the criterion for determining the clinical consequences of the process of demineralisation and defined new strategies for the selective removal of carious tissue. The starting point is to effectively remove the biofilm from cavitated carious lesions. Only when cavitated carious lesions are either non-cleansable or can no longer be sealed, are restorative interventions indicated, with due regard for the principles of a minimally invasive approach. Applying a restoration facilitates biofilm removal, guards the pulpodental complex and restores form, function and aesthetics.

Stem/progenitor cell-mediated pulpal tissue regeneration: a systematic review and meta-analysis.

BACKGROUND: Stem/progenitor cell-mediated pulpal regeneration could represent a promising therapeutic alternative in the field of clinical endodontics. AIM: The present study aimed to systematically assess and meta-analyse dental pulpal tissue regeneration, pulpal vitality and apical healing after the transplantation of stem/progenitor cells versus no transplantation. DATA SOURCES: MEDLINE, Cochrane CENTRAL and EMBASE were searched up to January 2019 for animal experiments and human trials evaluating the pulpal transplantation of stem/progenitor cells. Cross-referencing and hand search were additionally performed. STUDY ELIGIBILITY CRITERIA, PARTICIPANTS AND INTERVENTIONS: Based on randomized controlled clinical trials (RCTs) or controlled clinical trials (CCTs), conducted in animals or humans, the effect of the transplantation of stem/progenitor cells compared to no transplantation on pulpal tissue regeneration, pulpal vitality and apical healing was examined. STUDY APPRAISAL AND SYNTHESIS METHODS: The primary outcome was histologically determined pulpal tissue regeneration, whilst pulpal vitality and apical healing were secondary outcomes. The SYstematic Review Centre for Laboratory animal Experimentation (SYRCLE) guidelines and the revised Cochrane risk of bias tool (RoB 2.0) were used for risk-of-bias assessment. Pooled standardized differences in means (SDM) and 95% confidence intervals (95% CI) were calculated using random-effects meta-analyses. RESULTS: From 2834 identified articles, eight animal experiments (82 animals with 336 experimental pulpal defects) and one human trial (40 humans with 40 pulpal defects) were included. Risk of bias of most animal studies was high, whilst the human trial revealed 'some concerns'. Stem/progenitor cell-transplanted pulps demonstrated significantly increased pulpal tissue regeneration compared with controls (SDM [95%CI]: 6.29 [3.78-8.80]). LIMITATIONS: Data on pulpal vitality and apical healing were sparse and inconsistent. Heterogeneity across studies was substantial, publication bias was present, and mainly indirect, surrogate outcome measures were applied. The overall strength of evidence was very low. CONCLUSIONS AND IMPLICATIONS OF KEY FINDINGS: The transplanation of stem/progenitor cells shows promise for pulp regeneration, whilst clinical routine application is still not in reach. Further investigations, employing a comprehensive set of outcomes including those demonstrating functional pulp regeneration relevant for patient-centred care, are required.

Success and survival of post-restorations: six-year results of a prospective observational practice-based clinical study.

AIM: This prospective, noninterventional, multi-centre, practice-based study aimed to evaluate the longevity of endodontically treated teeth (ETT) restored with posts and to analyse factors influencing the success and survival of endodontic posts. METHODOLOGY: Eight general dental practitioners each placed up to 27 endodontic posts without any restriction to size and material. Teeth were restricted to incisors, canines and premolars. Multi-level Cox proportional hazards models were used to evaluate the association between clinical factors and time until failure. RESULTS: A total of 195 endodontic posts were followed-up for up to 6.5 years in 195 patients. Of these, 140 posts were judged as successful [mean success time: 59 (55-63) months]; the mean annual failure rate was 8.6%. This decreased to 4.4% when excluding recementations. 152 posts survived [mean survival time: 64 (60-67) months]. Recemented restorations had an eight times higher failure rate compared with new restorations. Furthermore, restorations with glass fibre post had a significantly lower success rate compared with titanium posts. CONCLUSION: Relatively low success and survival rates occurred for restorations with posts after root canal treatment in a private practice setting after a follow-up of up to 6.5 years. Recemented crowns had a high risk of failure.

Accuracy of tactile assessment in order to detect proximal cavitation of caries lesions in vitro.

OBJECTIVES: Discriminating non-cavitated from cavitated proximal lesions without tooth separation is only limitedly possible using visual-radiographic assessment alone. We evaluated how additional tactile assessment might increase the accuracy of this discrimination in vitro. METHODS: Surface integrity of 46 primary molars with proximal lesions extending radiographically into outer third of dentin (ICDAS-codes: 2 n = 34, 3 n = 8 and 5 n = 4) were mounted in groups of two in manikin heads and independently assessed by three examiners using visual-radiographic and additional tactile assessment using a cow-horn-ended explorer with or without gingival displacement. After examination, lesion surfaces were evaluated for possible damage using scanning-electronic microscopy. Analysis of variance (ANOVA) was performed for evaluating if tactile assessment and gingival displacement significantly affected accuracy. RESULTS: Tactile assessment significantly increased sensitivity of detecting cavities (p < 0.001, ANOVA), but decreased specificity (p < 0.05). Sensitivities/specificities varied between 33 (8)%/96 (1)% and 86 (6)%/84 (5)%. Gingival displacement had no significant impact on accuracy (p > 0.05). Scanning-electron microscopy revealed no cavitation. CONCLUSIONS: In vitro, tactile assessment of proximal surfaces was useful and safe. CLINICAL RELEVANCE: Analysis of the cavitation level by using a cow-horn-ended probe might be leading to useful information in addition to bitewing assessment under clinical circumstances.

Conventional treatment, Hall Technique or immediate pulpotomy for carious primary molars: a cost-effectiveness analysis.

AIM: To compare the cost-effectiveness of three strategies for treating primary molars with cavitated carious lesions and sensible (vital), asymptomatic pulps. METHODOLOGY: Conventional excavation and restoration, Hall Technique (caries sealing using a preformed crown), and pulpotomy were compared. As the latter would not be applied to all teeth in clinical reality, decision-making under perfect information was modelled, with teeth at-risk for pulpal complications receiving immediate pulpotomy, whilst all others were treated conventionally. A Markov model was constructed and transition probabilities derived from randomized trials and systematic reviews. A carious molar in a 5-year-old child was followed until exfoliation. Cost-effectiveness was assessed within the German healthcare system using a public-payer perspective. Monte Carlo microsimulations were performed to evaluate the primary outcome, costs (in Euros) per year of tooth retention. RESULTS: Conventional treatment was least effective and more expensive than the Hall Technique. Risk-based pulpotomy was more costly, but also more effective than alternatives. Overall, the Hall Technique was most cost-effective (9.77 Euros year-1 ), followed by pulpotomy (11.75 Euros year-1 ) and conventional treatment (13.31 Euros year-1 ). For payers willing to invest >59 Euros per additional year of tooth retention, risk-based pulpotomy was most cost-effective. Providing pulpotomy to all teeth was not cost-effective. CONCLUSIONS: The Hall Technique was most cost-effective, whilst conventional treatment was least effective and more costly. Performing pulpotomy for molars at-risk of pulpal complications might be effective, but was more expensive than alternatives. Moreover, accurately predicting such pulpal complications is currently not possible. Risk-based decision-making does not necessarily reduce costs.

Managing Carious Lesions: Consensus Recommendations on Terminology.

Variation in the terminology used to describe clinical management of carious lesions has contributed to a lack of clarity in the scientific literature and beyond. In this article, the International Caries Consensus Collaboration presents 1) issues around terminology, a scoping review of current words used in the literature for caries removal techniques, and 2) agreed terms and definitions, explaining how these were decided.Dental cariesis the name of the disease, and thecarious lesionis the consequence and manifestation of the disease-the signs or symptoms of the disease. The termdental caries managementshould be limited to situations involving control of the disease through preventive and noninvasive means at a patient level, whereascarious lesion managementcontrols the disease symptoms at the tooth level. While it is not possible to directly relate the visual appearance of carious lesions' clinical manifestations to the histopathology, we have based the terminology around the clinical consequences of disease (soft, leathery, firm, and hard dentine). Approaches to carious tissue removal are defined: 1)selective removal of carious tissue-includingselective removal to soft dentineandselective removal to firm dentine; 2)stepwise removal-including stage 1,selective removal to soft dentine, and stage 2,selective removal to firm dentine6 to 12 mo later; and 3)nonselective removal to hard dentine-formerly known ascomplete caries removal(technique no longer recommended). Adoption of these terms, around managing dental caries and its sequelae, will facilitate improved understanding and communication among researchers and within dental educators and the wider clinical dentistry community.

Managing Carious Lesions: Consensus Recommendations on Carious Tissue Removal.

The International Caries Consensus Collaboration undertook a consensus process and here presents clinical recommendations for carious tissue removal and managing cavitated carious lesions, including restoration, based on texture of demineralized dentine. Dentists should manage the disease dental caries and control activity of existing cavitated lesions to preserve hard tissues and retain teeth long-term. Entering the restorative cycle should be avoided as far as possible. Controlling the disease in cavitated carious lesions should be attempted using methods which are aimed at biofilm removal or control first. Only when cavitated carious lesions either are noncleansable or can no longer be sealed are restorative interventions indicated. When a restoration is indicated, the priorities are as follows: preserving healthy and remineralizable tissue, achieving a restorative seal, maintaining pulpal health, and maximizing restoration success. Carious tissue is removed purely to create conditions for long-lasting restorations. Bacterially contaminated or demineralized tissues close to the pulp do not need to be removed. In deeper lesions in teeth with sensible (vital) pulps, preserving pulpal health should be prioritized, while in shallow or moderately deep lesions, restoration longevity becomes more important. For teeth with shallow or moderately deep cavitated lesions, carious tissue removal is performed according toselective removal to firm dentine.In deep cavitated lesions in primary or permanent teeth,selective removal to soft dentineshould be performed, although in permanent teeth,stepwise removalis an option. The evidence and, therefore, these recommendations support less invasive carious lesion management, delaying entry to, and slowing down, the restorative cycle by preserving tooth tissue and retaining teeth long-term.

Cariogenic effects of probiotic Lactobacillus rhamnosus GG in a dental biofilm model.

Probiotic bacteria have been suggested to inhibit Streptococcus mutans (SM) and thus prevent dental caries. However, supporting evidence is weak and probiotic species might be cariogenic themselves. Thus, we compared and combined the probiotic Lactobacillus rhamnosus GG (LGG) with SM and analysed the resulting mineral loss (ΔZ) in dental tissues. We simulated three biofilm compositions (SM, LGG, SM × LGG), two lesion sites (smooth enamel, dentin cavity) and two nutrition supply frequencies (twice/day, 6 times/day) in a multi-station, continuous-culture biofilm model. A total of 240 bovine enamel and dentin samples were cut, polished and embedded. All experimental procedures were performed in independent duplicates, with 10 samples being allocated to each group for each experiment (final sample size n = 20/group). Biofilms were cultured on the specimens and supplied with 2% sucrose medium and artificial saliva in consecutive pulses. After 10 days, ΔZ and bacterial numbers were assessed. SM × LGG biofilms caused significantly increased ΔZ compared with SM or LGG biofilms (p < 0.01, Mann-Whitney test), and ΔZ was significantly increased in dentin cavities compared with smooth enamel lesions (p < 0.01). Bacterial numbers did not significantly differ between biofilms of different species (p > 0.05, ANOVA). Frequent nutrition supply significantly increased bacterial numbers (p < 0.01). Biofilms in dentin cavities compared to smooth enamel harboured significantly more bacteria (p < 0.05). LGG induced mineral loss especially in dentin cavities and under highly cariogenic conditions. LGG did not have inhibitory effects on SM, but rather contributed to the caries process in vitro.

Artificial Intelligence in Orthodontics: Critical Review.

With increasing digitalization in orthodontics, certain orthodontic manufacturing processes such as the fabrication of indirect bonding trays, aligner production, or wire bending can be automated. However, orthodontic treatment planning and evaluation remains a specialist's task and responsibility. As the prediction of growth in orthodontic patients and response to orthodontic treatment is inherently complex and individual, orthodontists make use of features gathered from longitudinal, multimodal, and standardized orthodontic data sets. Currently, these data sets are used by the orthodontist to make informed, rule-based treatment decisions. In research, artificial intelligence (AI) has been successfully applied to assist orthodontists with the extraction of relevant data from such data sets. Here, AI has been applied for the analysis of clinical imagery, such as automated landmark detection in lateral cephalograms but also for evaluation of intraoral scans or photographic data. Furthermore, AI is applied to help orthodontists with decision support for treatment decisions such as the need for orthognathic surgery or for orthodontic tooth extractions. One major challenge in current AI research in orthodontics is the limited generalizability, as most studies use unicentric data with high risks of bias. Moreover, comparing AI across different studies and tasks is virtually impossible as both outcomes and outcome metrics vary widely, and underlying data sets are not standardized. Notably, only few AI applications in orthodontics have reached full clinical maturity and regulatory approval, and researchers in the field are tasked with tackling real-world evaluation and implementation of AI into the orthodontic workflow.

Big Data in Epidemiology: Brave New World?

Epidemiology is experiencing a significant shift toward the utilization of big data for health monitoring and decision-making. This article discusses the recent example of the World Health Organization (WHO) global oral health status report and regional summaries, which faced criticisms due to its reliance on big data from the Global Burden of Disease (GBD) study. We address the arguments for and against the use of big data in epidemiology and provide an assessment of the value and limitations of big data epidemiology. Moreover, we provide recommendations as to how the oral health community should reconcile traditional epidemiologic approaches with big data and advanced data analytics. This Perspective article highlights the challenges of the current epidemiologic landscape, the potential of big data, and the need for a balanced approach to data utilization in epidemiology.

Does information about MIH on dental homepages in Germany offer high quality? A systematic search and analysis.

PURPOSE: The internet is increasingly used to seek health information. A dental condition of increasing concern and public interest is molar incisor hypomineralisation (MIH), why we evaluated the information quality of German dentists 'websites on the topic of MIH. METHODS: A systematic search was performed by two independent investigators using three search engines. The information content of websites on MIH and technical, functional aspects, overall quality, and risk of bias were assessed using validated instruments (LIDA, DISCERN). Practice-related characteristics (practice type, specialization, setting, number and mean age of dentists) were recorded, and associations of these characteristics with websites' overall quality were explored using multivariable linear regression modelling. RESULTS: 70 sites were included. 52% were multipractices in urban areas (49%). The most common age group was middle-aged individuals (41-50 years). The average number of dentists/practice was 2.5. The majority met more than 50% of the DISCERN and LIDA criteria (90%, 91%). The MIH definition was frequently used (67%), MIH symptoms were described (64%), and 58% mentioned therapies. The prevalence of MIH was mentioned less frequently (48%). MIH example photographs were rarely shown (14%). In multivariable analysis, most practice-related factors were not significant for overall site quality. Only chain practices had slightly higher quality in this regard (2.2; 95% CI of 0.3-4.1). CONCLUSIONS: MIH is mentioned on a large proportion of dentists' websites. Overall technical, functional, and generic quality was high. Risk of bias is limited. While most websites provided a basic definition of MIH and its symptoms, important information for patients was missing.

Trustworthy Artificial Intelligence in Dentistry: Learnings from the EU AI Act.

Artificial intelligence systems (AISs) gain relevance in dentistry, encompassing diagnostics, treatment planning, patient management, and therapy. However, questions about the generalizability, fairness, and transparency of these systems remain. Regulatory and governance bodies worldwide are aiming to address these questions using various frameworks. On March 13, 2024, members of the European Parliament approved the Artificial Intelligence Act (AIA), which emphasizes trustworthiness and human-centeredness as relevant aspects to regulate AISs beyond safety and efficacy. This review presents the AIA and similar regulatory and governance efforts in other jurisdictions and lays out that regulations such as the AIA are part of a complex ecosystem of interdependent and interwoven legal requirements and standards. Current efforts to regulate dental AISs require active input from the dental community, with participation of dental research, education, providers, and patients being relevant to shape the future of dental AISs.

Diagnostic Strategies for Restorations Management: A 70-Month RCT.

We aimed to evaluate the impact of 2 visual diagnostic strategies for assessing secondary caries and managing permanent posterior restorations on long-term survival. We conducted a diagnostic cluster-randomized clinical trial with 2 parallel groups using different diagnostic strategies: (C+AS) based on caries assessment, marginal adaptation, and marginal staining aspects of the FDI (World Dental Federation) criteria and (C) based on caries assessment using the Caries Associated with Restorations or Sealants (CARS) criteria described by the International Caries Detection and Assessment System (ICDAS). The treatment for the restoration was conducted based on the decision made following the allocated diagnostic strategy. The restorations were then clinically reevaluated for up to 71 mo. The primary outcome was restoration failure (including tooth-level failure: pain, endodontic treatment, and extraction). Cox regression analyses with shared frailty were conducted in the intention-to-treat population, and hazard ratios (HRs) and 95% confidence intervals (95% CIs) were derived. We included 727 restorations from 185 participants and reassessed 502 (69.1%) restorations during follow-up. The evaluations occurred between 6 and 71 mo. At baseline, C led to almost 4 times fewer interventions compared with the C+AS strategy. A total of 371 restorations were assessed in the C group, from which 31 (8.4%) were repaired or replaced. In contrast, the C+AS group had 356 restorations assessed, from which 113 (31.7%) were repaired or replaced. During follow-up, 34 (9.2%) failures were detected in the restorations allocated to the C group and 30 (8.4%) allocated to the C+AS group in the intention-to-treat population, with no significant difference between the groups (HR = 0.83; 95% CI = 0.51 to 1.38; P = 0.435, C+AS as reference). In conclusion, a diagnostic strategy focusing on marginal defects results in more initial interventions but does not improve longevity over the caries-focused strategy, suggesting the need for more conservative approaches.

Visualization of Pulpal Structures by SWIR in Endodontic Access Preparation.

Endodontic access preparation is one of the initial steps in root canal treatments and can be hindered by the obliteration of pulp canals and formation of tertiary dentin. Until now, methods for direct intraoperative visualization of the 3-dimensional anatomy of teeth have been missing. Here, we evaluate the use of shortwave infrared radiation (SWIR) for navigation during stepwise access preparation. Nine teeth (3 anteriors, 3 premolars, and 3 molars) were explanted en bloc with intact periodontium including alveolar bone and mucosa from the upper or lower jaw of human body donors. Analysis was performed at baseline as well as at preparation depths of 5 mm, 7 mm, and 9 mm, respectively. For reflection, SWIR was used at a wavelength of 1,550 nm from the occlusal direction, whereas for transillumination, SWIR was passed through each sample at the marginal gingiva from the buccal as well as oral side at a wavelength of 1,300 nm. Pulpal structures could be identified as darker areas approximately 2 mm before reaching the pulp chamber using SWIR transillumination, although they were indistinguishable under normal circumstances. Furcation areas in molars appeared with higher intensity than areas with canals. The location of pulpal structures was confirmed by superimposition of segmented micro-computed tomography (µCT) images. By radiomic analysis, significant differences between pulpal and parapulpal areas could be detected in image features. With hierarchical cluster analysis, both segments could be confirmed and associated with specific clusters. The local thickness of µCTs was calculated and correlated with SWIR transillumination images, by which a linear dependency of thickness and intensity could be demonstrated. Lastly, by in silico simulations of light propagation, dentin tubules were shown to be a crucial factor for understanding the visibility of the pulp. In conclusion, SWIR transillumination may allow direct clinical live navigation during endodontic access preparation.

Attitudes and behaviour regarding deep dentin caries removal: a survey among German dentists.

Incomplete removal of deep caries has been shown to reduce the risks of pulp exposure and postoperative pulpal complications. It is therefore of interest whether dentists perform one- or two-step incomplete excavation, and which criteria and methods they use to assess and provide removal of deep caries. This study investigated the attitudes and behaviour of dentists in northern Germany using a new, validated questionnaire. The survey included 2,346 practitioners, 821 (35%) of whom responded. Demographic and sensitivity analysis did not indicate selection bias. 50% of dentists considered only complete excavation, even if pulp exposure was likely. If caries was to be removed incompletely, 77% considered two-step excavation. Hardness was the most important criterion to assess excavation. To treat an exposed pulp, 75% of dentists considered direct capping, 70% refused incomplete excavation fearing caries progression or pulp damage, and 59% reported to prefer more invasive treatment to facilitate restoration longevity. Over 50% recognised an influence of professional regulations on their treatment decisions. There was a moderate correlation between attitudes and behaviour of dentists, with dentists who suspected residual caries to be harmful rejecting incomplete excavation and vice versa. Cluster analysis identified two groups of dentists with opposite attitudes and behaviour, independently from dentist's age or gender. In conclusion, the majority of surveyed dentists was sceptical about leaving caries during excavation and does not practice incomplete caries removal. Therefore, benefits of partial excavation should be highlighted in under- and postgraduate education and regulatory incentives modified to promote minimally invasive techniques.

Preoperative risk assessment does not allow to predict root filling length using machine learning: A longitudinal study.

OBJECTIVES: First we aimed to identify significant associations between preoperative risk factors and achieving optimal root filling length (RFL) during orthograde root canal treatments (RCT) and second to predict successful RFL using machine learning. METHODS: Teeth receiving RCT at one university clinic from 2016-2020 with complete documentation were included. Successful RFL was defined to be 0-2mm of the apex, suboptimal RFL >2mm or beyond the apex. Logistic regression (logR) was used for association analyses; logR and more advanced machine learning (random forest (RF), support vector machine (SVM), decision tree (DT), gradient boosting machine (GBM) and extreme gradient boosting (XGB)) were employed for predictive modeling. RESULTS: 555 completed RCT (343 patients, female/male 32.1/67.9%) were included. In our association analysis (involving the full dataset), unsuccessful RFL was more likely in undergraduate students (US): OR 2.74, 95% CI [1.61, 4.75], p < 0.001), teeth with indistinct canal paths (OR 11.04, [2.87, 44.88], p < 0.001), root canals reduced in size (OR 2.56, [1.49, 4.46], p < 0.01), retreatments (OR 3.13, [1.6, 6.41], p < 0.001). Subgroup analyses revealed that dentists were more successful in mitigating risks than undergraduate students. Prediction of RFL on a separate testset was limitedly possible regardless of the machine learning approach. CONCLUSIONS: Achieving RFL is depending on the operator and several risk factors. The predictive performance on the technical outcome of a root canal treatment utilizing ML algorithms was insufficient. CLINICAL SIGNIFICANCE: Preoperative risk assessment is a relevant step in endodontic treatment planning. Single radiographic risk factors were significantly associated with achieving (or not achieving) optimal RFL and showed higher predictive value than a more complex risk assessment form.

Identification of Dental Implant Systems Using a Large-Scale Multicenter Data Set.

This study aimed to evaluate the efficacy of deep learning (DL) for the identification and classification of various types of dental implant systems (DISs) using a large-scale multicenter data set. We also compared the classification accuracy of DL and dental professionals. The data set, which was collected from 5 college dental hospitals and 10 private dental clinics, contained 37,442 (24.8%) periapical and 113,291 (75.2%) panoramic radiographic images and consisted of a total of 10 manufacturers and 25 different types of DISs. The classification accuracy of DL was evaluated using a pretrained and modified ResNet-50 architecture, and comparison of accuracy performance and reading time between DL and dental professionals was conducted using a self-reported questionnaire. When comparing the accuracy performance for classification of DISs, DL (accuracy: 82.0%; 95% confidence interval [CI], 75.9%-87.0%) outperformed most of the participants (mean accuracy: 23.5% ± 18.5%; 95% CI, 18.5%-32.3%), including dentists specialized (mean accuracy: 43.3% ± 20.4%; 95% CI, 12.7%-56.2%) and not specialized (mean accuracy: 16.8% ± 9.0%; 95% CI, 12.8%-20.9%) in implantology. In addition, DL tends to require lesser reading and classification time (4.5 min) than dentists who specialized (75.6 ± 31.0 min; 95% CI, 13.1-78.4) and did not specialize (91.3 ± 38.3 min; 95% CI, 74.1-108.6) in implantology. DL achieved reliable outcomes in the identification and classification of various types of DISs, and the classification accuracy performance of DL was significantly superior to that of specialized or nonspecialized dental professionals. DL as a decision support aid can be successfully used for the identification and classification of DISs encountered in clinical practice.

Multi-modal deep learning for automated assembly of periapical radiographs.

OBJECTIVES: Periapical radiographs are oftentimes taken in series to display all teeth present in the oral cavity. Our aim was to automatically assemble such a series of periapical radiographs into an anatomically correct status using a multi-modal deep learning model. METHODS: 4,707 periapical images from 387 patients (on average, 12 images per patient) were used. Radiographs were labeled according to their field of view and the dataset split into a training, validation, and test set, stratified by patient. In addition to the radiograph the timestamp of image generation was extracted and abstracted as follows: A matrix, containing the normalized timestamps of all images of a patient was constructed, representing the order in which images were taken, providing temporal context information to the deep learning model. Using the image data together with the time sequence data a multi-modal deep learning model consisting of two residual convolutional neural networks (ResNet-152 for image data, ResNet-50 for time data) was trained. Additionally, two uni-modal models were trained on image data and time data, respectively. A custom scoring technique was used to measure model performance. RESULTS: Multi-modal deep learning outperformed both uni-modal image-based learning (p<0.001) and time-based learning (p<0.05). The multi-modal deep learning model predicted tooth labels with an F1-score, sensitivity and precision of 0.79, respectively, and an accuracy of 0.99. 37 out of 77 patient datasets were fully correctly assembled by multi-modal learning; in the remaining ones, usually only one image was incorrectly labeled. CONCLUSIONS: Multi-modal modeling allowed automated assembly of periapical radiographs and outperformed both uni-modal models. Dental machine learning models can benefit from additional data modalities. CLINICAL SIGNIFICANCE: Like humans, deep learning models may profit from multiple data sources for decision-making. We demonstrate how multi-modal learning can assist assembling periapical radiographs into an anatomically correct status. Multi-modal learning should be considered for more complex tasks, as clinically a wealth of data is usually available and could be leveraged.

Data Dentistry: How Data Are Changing Clinical Care and Research.

Data are a key resource for modern societies and expected to improve quality, accessibility, affordability, safety, and equity of health care. Dental care and research are currently transforming into what we term data dentistry, with 3 main applications: 1) medical data analysis uses deep learning, allowing one to master unprecedented amounts of data (language, speech, imagery) and put them to productive use. 2) Data-enriched clinical care integrates data from individual (e.g., demographic, social, clinical and omics data, consumer data), setting (e.g., geospatial, environmental, provider-related data), and systems level (payer or regulatory data to characterize input, throughput, output, and outcomes of health care) to provide a comprehensive and continuous real-time assessment of biologic perturbations, individual behaviors, and context. Such care may contribute to a deeper understanding of health and disease and a more precise, personalized, predictive, and preventive care. 3) Data for research include open research data and data sharing, allowing one to appraise, benchmark, pool, replicate, and reuse data. Concerns and confidence into data-driven applications, stakeholders' and system's capabilities, and lack of data standardization and harmonization currently limit the development and implementation of data dentistry. Aspects of bias and data-user interaction require attention. Action items for the dental community circle around increasing data availability, refinement, and usage; demonstrating safety, value, and usefulness of applications; educating the dental workforce and consumers; providing performant and standardized infrastructure and processes; and incentivizing and adopting open data and data sharing.