ACES: A new framework for the application of the 2018 periodontal status classification scheme to epidemiological survey data.

AIM: To propose a framework for consistently applying the 2018 periodontal status classification scheme to epidemiological surveys (Application of the 2018 periodontal status Classification to Epidemiological Survey data, ACES). PROPOSED FRAMEWORK: We specified data requirements and workflows for either completed or planned epidemiological surveys, utilizing commonly collected measures of periodontal status (clinical attachment levels [CAL], probing depths, bleeding on probing), as well as additional necessary variables for the implementation of the 2018 periodontal status classification (tooth loss due to periodontitis and complexity factors). Following detailed instructions and flowcharts, survey participants are classified as having periodontal health, gingivitis or periodontitis. Rates of edentulism must also be reported. In cases of periodontitis, instructions on how to compute the stage and extent are provided. Assessment of grade can be derived from CAL measurements (or from radiographic alveolar bone loss data) in relation to root length and the participant's age. CONCLUSIONS: ACES is a framework to be used in epidemiological studies of periodontal status that (i) have been completed, and in which stage and grade according to the 2018 classification are inferred retroactively, or (ii) are being planned. Consistent use of the proposed comprehensive approach will facilitate the comparability of periodontitis prevalence estimates across studies.

Monolithic hybrid abutment crowns (screw-retained) versus monolithic hybrid abutments with adhesively cemented monolithic crowns.

OBJECTIVES: The objective of this study is to compare monolithic hybrid abutment crowns (screw-retained) versus monolithic hybrid abutments with adhesively cemented monolithic single-tooth crowns. MATERIALS AND METHODS: Twenty subjects in need of an implant-borne restoration were randomly assigned to receive either a cement-retained (CRR) or a screw-retained (SRR) implant-supported monolithic lithium disilicate (LS2 ) reconstruction. Each patient received a titanium implant with in internal conic connection. After osseointegration and second-stage surgery, healing abutments were placed for about 10 days. The type of restoration (CRR vs. SRR) was randomly assigned, and the restorations were manufactured of monolithic LS2 . Both types of restorations, CRR and SRR, were based on a titanium component (Ti-base) that was bonded to the abutment (CRR) or the crown (SRR). The follow-up period for all restoration was 36 months. Clinical outcome was evaluated according to Functional Implant Prosthetic Score (FIPS). Quality of live (OHIP) and patient's satisfaction were assessed using patient-reported outcome measures (PROMs). Primary endpoint was loss of restoration for any reason. Kaplan-Meier curves were constructed and log-rank testing was performed (p < .05). RESULTS: One restoration of group CRR failed after 6 months due to loss of adhesion between Ti-base and individual abutment. No further biological or technical failures occurred. Kaplan-Meier analysis showed no significant difference between both treatment options (p = .317). There was no statistically significant difference between both types of restoration, neither for FIPS, OHIP, treatment time nor patient satisfaction (p > .05). CONCLUSION: Monolithic hybrid abutment crowns (screw-retained) and monolithic hybrid abutment with adhesively cemented monolithic crowns using lithium disilicate showed no statistically significant difference for implant-based reconstructions in this pilot RCT setting.

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.

Augmented Vision for Dental Students' Education in Detecting Proximal Carious Lesions on Bitewing Radiographs: A Randomized Controlled Trial.

This two-arm, parallel, randomized controlled trial aimed to assess the effect of augmented vision (AV, using interactive color overlays) on the education of dental students in detecting proximal carious lesions on bitewing radiographs compared to black-and-white textbook-like illustrations. Forty-eight preclinical third-year dental students were randomized using a random number generator into two learning groups: test (AV, allowing interaction with color-highlighted carious lesions, n = 24) and control (showing the native radiograph and a black-and-white illustration displaying the carious lesion, n = 24). First, students had 2 weeks to assess 50 bitewings (lesion prevalence on the tooth level: 54.5%) in the test or control. Due to the nature of the intervention, participants could not be blinded toward the intervention. After that, they were asked to detect lesions on 10 independent bitewings and to assess lesion extent (outer/inner enamel; outer/middle/inner dentin). The reference test was constituted by two experienced dentists. No significant differences in accuracy (test 0.84 [95% CI: 0.79, 0.88]; control 0.83 [0.78, 0.87]), AUC (test 0.82 [0.81, 0.84]; control 0.81 [0.80, 0.83]) and F1 score (test 0.79 [0.75, 0.82]; control 0.77 [0.72, 0.81]) were observed between groups. Students of both groups showed difficulties in differentiating enamel from dentin carious lesions. While AV was reported to be motivating by students, it did not increase their accuracy.

Precision dentistry-what it is, where it fails (yet), and how to get there.

OBJECTIVES: Dentistry is stuck between the one-size-fits-all approach towards diagnostics and therapy employed for a century and the era of stratified medicine. The present review presents the concept of precision dentistry, i.e., the next step beyond stratification into risk groups, and lays out where we stand, but also what challenges we have ahead for precision dentistry to come true. MATERIAL AND METHODS: Narrative literature review. RESULTS: Current approaches for enabling more precise diagnostics and therapies focus on stratification of individuals using clinical or social risk factors or indicators. Most research in dentistry does not focus on predictions - the key for precision dentistry - but on associations. We critically discuss why both approaches (focus on a limited number of risk factors or indicators and on associations) are insufficient and elaborate on what we think may allow to overcome the status quo. CONCLUSIONS: Leveraging more diverse and broad data stemming from routine or unusual sources via advanced data analytics and testing the resulting prediction models rigorously may allow further steps towards more precise oral and dental care. CLINICAL SIGNIFICANCE: Precision dentistry refers to tailoring diagnostics and therapy to an individual; it builds on modelling, prediction making and rigorous testing. Most studies in the dental domain focus on showing associations, and do not attempt to make any predictions. Moreover, the datasets used are narrow and usually collected purposively following a clinical reasoning. Opening routine data silos and involving uncommon data sources to harvest broad data and leverage them using advanced analytics could facilitate precision dentistry.

A Survey on the Use of Artificial Intelligence by Clinicians in Dentistry and Oral and Maxillofacial Surgery.

Background: Applications of artificial intelligence (AI) in medicine and dentistry have been on the rise in recent years. In dental radiology, deep learning approaches have improved diagnostics, outperforming clinicians in accuracy and efficiency. This study aimed to provide information on clinicians' knowledge and perceptions regarding AI. Methods: A 21-item questionnaire was used to study the views of dentistry professionals on AI use in clinical practice. Results: In total, 302 questionnaires were answered and assessed. Most of the respondents rated their knowledge of AI as average (37.1%), below average (22.2%) or very poor (23.2%). The participants were largely convinced that AI would improve and bring about uniformity in diagnostics (mean Likert ± standard deviation 3.7 ± 1.27). Among the most serious concerns were the responsibility for machine errors (3.7 ± 1.3), data security or privacy issues (3.5 ± 1.24) and the divestment of healthcare to large technology companies (3.5 ± 1.28). Conclusions: Within the limitations of this study, insights into the acceptance and use of AI in dentistry are revealed for the first time.

Underscreening and undertreatment? Periodontal service provision in very old Germans.

OBJECTIVES: We aimed to assess periodontal services utilization in very old Germans. METHODS: A comprehensive sample of very old (≥ 75 years), insured at a large Northeastern statutory insurer was followed over 6 years (2012-2017). We assessed periodontal service provision, entailing (1) periodontal screening index (PSI), (2) periodontal status/treatment planning, (3) periodontal therapy (scaling and root planning with or without access surgery), (4) postoperative reevaluation, and (5) any of these four services groups. Association of utilization with (1) sex, (2) age, (3) region, (4) social hardship status, (5) ICD-10 diagnoses, and (6) diagnoses-related groups was explored. RESULTS: 404.610 individuals were followed; 173,733 did not survive follow-up. The mean (SD) age was 81.9 (5.4) years. 29.4% (119,103 individuals) utilized any periodontal service, nearly all of them the PSI. Periodontal status/treatment planning, treatment provision, and reevaluation were provided to only a small fraction (1.54-1.57%, or 6224-6345) of individuals. The utilization of the PSI increased between 2012 and 2017; no such increase was observed for treatment-related services. Utilization decreased with age; those aged > 85 years received nearly no services at all. Decreases were more pronounced for treatment-related services. Utilization was lower in rural than urban areas, those with hardship status, and those severely ill (e.g., dementia, heart insufficiency). In multivariable analysis, a previous PSI measurement tripled the odds of receiving treatment-related services (OR: 3.2; 95% CI: 3.0-3.4). CONCLUSIONS: Periodontal services utilization was low. Screening for periodontal disease significantly increased therapy provision. Social, demographic, regional, and general health aspects were associated with utilization. CLINICAL SIGNIFICANCE: The utilization of periodontal services in the very old in Northeast Germany was low, and even screening was only performed in a minority of individuals. Policies to increase identification and management of periodontitis especially in the most vulnerable individuals are needed.

Long-term costs of post-restorations: 7-year practice-based results from Germany.

OBJECTIVES: We evaluated the initial and follow-up treatment costs of different post-restorations in a practice-based German healthcare setting. METHODS: A total of 139 incisors, canines, or premolars received post-restorations placed by eight general dental practitioners in Germany, and were followed over a mean ± SD 7.1 ± 4.5 years. Preformed metal (MP, n = 68), glass-fiber (GF, n = 28), or cast post-and-core buildups (MC, n = 23) had been used to retain crowns or bridge anchors. Preformed metal and glass-fiber had also been used to retain directly built up post-retained composite restorations (PC, n = 20). Material and treatment costs for the initial post-restorations as well as restorative, endodontic, or surgical re-treatments were estimated from a public-payer-perspective in Germany. Associations between total and annualized total costs and covariates were assessed using generalized linear modeling. The study was registered in the German Clinical Trials Register (DRKS-ID: DRKS00012938). RESULTS: MC showed highest initial treatment costs (557.23 Euro), but the least re-treatments (6/23, 26%), while PC showed lowest initial costs (203.52 Euro) but the most re-treatments (11/20, 55%). Costs for MP/GF post-crowns were initially similarly costly (496.47/496.87 Euro), and both also showed similar re-treatments (35%/36%). The overall annual failure rate was 5.2% (MC: 3.5%, MP: 4.6%, GF: 5.3%, PC: 10.3%). Including costs for the resulting re-treatments, mean total costs were 591.66 Euro (MC), 548.31 Euro (MP), 526.37 Euro (GF), and 361.81 Euro (PC). Annualized total costs were 171.36 Euro (MC), 141.75 Euro (MP), 146.12 Euro (GF), and 135.65 Euro (PC). Total and annualized total costs were highest for MC, with PC being the significantly less costly option (p < 0.001). CONCLUSIONS: Within German healthcare, both initial and follow-up costs for post-restorations were considerable. Saving costs initially may, at least partially, be offset by more complications long-term. CLINICAL RELEVANCE: Dentists need to be aware that the placement of posts is not only initially costly but also comes with significant long-term costs for treating occurring complications. This should be communicated with patients and considered during treatment planning.

Dental service utilization in the very old: an insurance database analysis from northeast Germany.

OBJECTIVES: We assessed dental service utilization in very old Germans. METHODS: A comprehensive sample of 404,610 very old (≥ 75 years), insured at a large statutory insurer (Allgemeine Ortskrankenkasse Nordost, active in the federal states Berlin, Brandenburg, Mecklenburg-Western Pomerania), was followed over 6 years (2012-2017). Our outcome was the utilization of dental services, in total (any utilization) and in five subgroups: (1) examinations and associated assessment or advice, (2) restorations, (3) surgery, (4) prevention, (5) outreach care. Association of utilization with (1) sex, (2) age, (3) region, (4) social hardship status, (5) ICD-10 diagnoses, and (6) German modified diagnosis-related groups (GM-DRGs) was explored. RESULTS: The mean (SD) age of the sample was 81.9 (5.4) years. The utilization of any dental service was 73%; utilization was highest for examinations (68%), followed by prevention (44%), surgery (33%), restorations (32%), and outreach care (13%). Utilization decreased with age for nearly all services except outreach care. Service utilization was significantly higher in Berlin and most cities compared with rural municipalities, and in individuals with common, less severe, and short-term conditions compared with life-threatening and long-term conditions. In multi-variable analysis, social hardship status (OR: 1.14; 95% CI: 1.12-1.16), federal state (Brandenburg 0.85; 0.84-0.87; Mecklenburg-Western Pomerania: 0.80; 0.78-0.82), and age significantly affected utilization (0.95; 0.95-0.95/year), together with a range of co-morbidities according to ICD-10 and DRG. CONCLUSIONS: Social, demographic, regional, and general health aspects were associated with the utilization of dental services in very old Germans. Policies to maintain access to services up to high age are needed. CLINICAL SIGNIFICANCE: The utilization of dental services in the very old in northeast Germany showed significant disparities within populations. Policies to allow service utilization for sick, economically disadvantaged, rural and very old populations are required. These may include incentives for outreach servicing, treatment-fee increases for specific populations, or referral schemes between general medical practitioners and dentists.

Deep learning for cephalometric landmark detection: systematic review and meta-analysis.

OBJECTIVES: Deep learning (DL) has been increasingly employed for automated landmark detection, e.g., for cephalometric purposes. We performed a systematic review and meta-analysis to assess the accuracy and underlying evidence for DL for cephalometric landmark detection on 2-D and 3-D radiographs. METHODS: Diagnostic accuracy studies published in 2015-2020 in Medline/Embase/IEEE/arXiv and employing DL for cephalometric landmark detection were identified and extracted by two independent reviewers. Random-effects meta-analysis, subgroup, and meta-regression were performed, and study quality was assessed using QUADAS-2. The review was registered (PROSPERO no. 227498). DATA: From 321 identified records, 19 studies (published 2017-2020), all employing convolutional neural networks, mainly on 2-D lateral radiographs (n=15), using data from publicly available datasets (n=12) and testing the detection of a mean of 30 (SD: 25; range.: 7-93) landmarks, were included. The reference test was established by two experts (n=11), 1 expert (n=4), 3 experts (n=3), and a set of annotators (n=1). Risk of bias was high, and applicability concerns were detected for most studies, mainly regarding the data selection and reference test conduct. Landmark prediction error centered around a 2-mm error threshold (mean; 95% confidence interval: (-0.581; 95 CI: -1.264 to 0.102 mm)). The proportion of landmarks detected within this 2-mm threshold was 0.799 (0.770 to 0.824). CONCLUSIONS: DL shows relatively high accuracy for detecting landmarks on cephalometric imagery. The overall body of evidence is consistent but suffers from high risk of bias. Demonstrating robustness and generalizability of DL for landmark detection is needed. CLINICAL SIGNIFICANCE: Existing DL models show consistent and largely high accuracy for automated detection of cephalometric landmarks. The majority of studies so far focused on 2-D imagery; data on 3-D imagery are sparse, but promising. Future studies should focus on demonstrating generalizability, robustness, and clinical usefulness of DL for this objective.

Knowledge, attitudes, and beliefs regarding molar incisor hypomineralization (MIH) amongst German dental students.

BACKGROUND: Knowledge of molar incisor hypomineralization (MIH) has relevance for paediatric dentists. AIM: To assess final-year German dental students' knowledge, attitudes, and beliefs regarding MIH. MATERIALS AND METHODS: A previously validated questionnaire was posted to the 31 German dental schools. Demographic covariates as well as knowledge regarding diagnosis and prevalence, and attitudes and beliefs around aetiology and management were collected. RESULTS: Twenty-two (71%) dental schools responded and a total of 877 students participated. Most (97%) were familiar with MIH and 88% were aware of the diagnostic criteria for MIH; however, only 42% knew how to implement them. One-third were able to identify MIH and 16% reported diagnostic confidence when doing so; 90% assumed the MIH prevalence to be <10%. Two-thirds of the respondents implicated genetic components as the main aetiological factor of MIH. Resin composite (60%) and preformed metal crowns (46%) were the dental materials most often suggested for restorative management. Almost all (98%) respondents were interested in receiving more clinical training. CONCLUSION: German students were familiar with MIH; however, they reported low levels of knowledge and confidence regarding its prevalence and diagnosis. Standardized nationwide, up-to-date curricula should be implemented to educate future dentists in Germany.

Machine Learning for Health: Algorithm Auditing & Quality Control.

Developers proposing new machine learning for health (ML4H) tools often pledge to match or even surpass the performance of existing tools, yet the reality is usually more complicated. Reliable deployment of ML4H to the real world is challenging as examples from diabetic retinopathy or Covid-19 screening show. We envision an integrated framework of algorithm auditing and quality control that provides a path towards the effective and reliable application of ML systems in healthcare. In this editorial, we give a summary of ongoing work towards that vision and announce a call for participation to the special issue  Machine Learning for Health: Algorithm Auditing & Quality Control in this journal to advance the practice of ML4H auditing.

Clustering effects of oral conditions based on clinical and radiographic examinations.

OBJECTIVES: The intra-class correlation coefficient (ICC) is a measure of intra-subject clustering effects. A priori estimates of the ICC and the associated design effect (DE) are required for sample size estimation in clustered studies, and should be considered during their analysis, too. We aimed to determine the clustering effects of carious lesions, apical lesions, periodontal bone loss, and periodontal pocketing, assessed in clinical or radiographic examinations. METHODS: A subsample of patients (n = 175) enrolled in the fifth German Oral Health Study provided data on clinically determined carious teeth (i.e., with untreated carious lesions, WHO method) as well as teeth with periodontal pocketing (i.e., with maximum probing-pocket-depths ≥ 4 mm). A sample of panoramic radiographs (n = 85) from randomly chosen patients, examined from 2010 to 2017 at the Charité dental hospital, provided data on radiographically determined carious teeth (i.e., with lesions extending into dentine or enamel), teeth with apical lesions (determined by dentists via majority vote), and teeth with periodontal bone loss (≥ 20% of root-length). The ICC and its 95% confidence interval (95% CI) were determined. RESULTS: There were 3839 and 1961 teeth assessed in clinical and radiographic evaluations, respectively. For clinically or radiographically determined carious lesions, the ICC (95% CI) was 0.20 (0.16-0.24) or 0.19 (0.14-0.25), respectively. For clinical pocketing or radiographic bone loss, the ICC was 0.40 (0.35-0.46) or 0.30 (0.24-0.38), respectively. The lowest ICC was found for apical lesions at 0.08 (0.06-0.13). CONCLUSIONS: The ICC varied between assessment methods and conditions. Clustered trials should account for this during study planning and data analysis. CLINICAL RELEVANCE: Within the limitations of this study, and considering the risk of selection bias and the limited sample sizes of both datasets, clustering effects were substantial but varied between dental conditions. Studies not accounting for this during planning and analysis may yield misleading estimates if clustering is present.

Secondary caries: what is it, and how it can be controlled, detected, and managed?

OBJECTIVES: To assess how to control, detect, and treat secondary caries. This review serves to inform a joint ORCA/EFCD consensus process. METHODS: Systematic and non-systematic reviews were performed or consulted and narratively synthesized. RESULTS: Secondary (or recurrent) caries is defined as a lesion associated with restorations or sealants. While the restorative material itself has some influence on secondary caries, further factors like the presence and size of restoration gaps, patients' caries risk, and the placing dentist's experience seem more relevant. Current detection methods for secondary caries are only sparsely validated and likely prone for the risk of over-detection. In many patients, it might be prudent to prioritize specific detection methods to avoid invasive overtreatment. Detected secondary caries can be managed either by repair of the defective part of the restoration or its complete replacement. CONCLUSIONS: There is sparse data towards the nature of secondary caries and how to control, detect, and treat it. CLINICAL SIGNIFICANCE: Despite often claimed to be a major complication of restorations, there is surprisingly little data on secondary caries. Longer-term studies may be needed to identify differences in secondary caries risk between materials and to identify characteristic features of progressive lesions (i.e., those in need of treatment).

Prosthetic treatment patterns in the very old: an insurance database analysis from Northeast Germany.

OBJECTIVES: We assessed dental prosthetic services utilization in very old Germans. METHODS: A comprehensive sample of 404,610 very old (≥ 75 years), insured at one large statutory insurer (Allgemeine Ortskrankenkasse Nordost, acting in the federal states Berlin, Brandenburg, Mecklenburg-Vorpommern), were followed over 6 years (2012-2017). Our outcome was the utilization of prosthetic services, in total and seven subgroups: (1) Crowns/partial crowns, (2) fixed dental prostheses (FDPs), (3) partial removable prostheses (RDPs), (4) full RDPs, (5) temporary services, (6) relining/rebasing/repairing/extending RDPs, (7) repairing FDPs. Association of utilization with (1) gender, (2) age, (3) region, (4) social hardship status, (5) ICD-10 diagnoses and (6) German diagnoses related groups (G-DRG) was explored. RESULTS: The mean (SD) age of the sample was 81.9 (5.4) years; mean follow-up was 1689 (705) days. The mean utilization of any prosthetic service was 27.0%; the most often utilized service type were total RDPs (13.2% utilization), crowns (8.1%), and partial RDPs (7.1%). Utilization decreased with age for nearly all services (except relining/rebasing/repairing/extending RDPs). Utilization of prosthetic services was significantly higher in Berlin and most cities compared with rural municipalities and in individuals with common, less severe conditions according to ICD-10 and DRGs compared with life-threatening conditions or dementia. In multivariable analysis, gender (OR; 95% CI: 0.95; 0.93-0.98), social hardship status (1.19; 1.17-1.21), federal state (Brandenburg 0.57; 0.56-0.59; Mecklenburg-Vorpommern: 0.66; 0.64-0.67) and age significantly affected utilization (0.95; 0.95-0.95/year). CONCLUSIONS: Patient-related and healthcare factors determine the utilization of prosthetic services in very old Germans. Interventions to maintain sufficient prosthetic care up to high age are required. CLINICAL SIGNIFICANCE: The utilization of prosthetic services in the very old in Northeast Germany showed significant disparities within populations and service types. There seems to be great need to better understand the drivers of utilization, and to develop and evaluate interventions to maintain sufficient prosthetic care up to high age.

Comparison of periodontitis patients' classification in the 2018 versus 1999 classification.

OBJECTIVES: We aimed to assess how the 2018 and 1999 classifications of periodontal diseases reflect (a) patients' characteristics, (b) disease severity/extent/progression and (c) tooth loss (TL) during observation period. METHODS: A total of 251 patients were followed over 21.8 ± 6.2 years. For the 1999 classification, using clinical attachment level (CAL), patients were classified as localized/generalized, mild/moderate/severe and aggressive/chronic periodontitis. For the 2018 classification, patients were staged according to their CAL or bone loss (BL) and the number of lost teeth (stages I-IV). Further factors like probing pocket depths (PPD) or furcation involvement modified the stage. The extent was sub-classified as generalized/localized. Patients were graded according to the BL/age index, smoking and/or diabetes. RESULTS: According to the 1999 classification, most patients suffered from generalized severe chronic periodontitis (203/251) or generalized aggressive periodontitis (45/251). Patients with aggressive periodontitis were younger and less often female or smokers. They showed similar TL (0.25 ± 0.22 teeth/patient*year) as generalized severe chronic periodontitis patients (0.23 ± 0.25 teeth/patient*year). According to the 2018 classification, most patients were classified as generalized III-C (140/251), III-B (31/251) or IV-C (64/251). Patients' age, smoking status, CAL, PPD and BL were well reflected. TL differed between IV-C (0.36 ± 0.47), generalized III-C (0.21 ± 0.24) and localized forms (0.10-0.15). CONCLUSIONS: Patients' characteristics, disease severity/extent/progression and TL were well reflected by the 2018 classification.

Predictors for tooth loss in periodontitis patients: Systematic review and meta-analysis.

AIM: A range of predictors for tooth loss in periodontitis patients have been reported. We performed a systematic review and meta-analysis to assess the consistency and magnitude of any association between a total of 12 predictors and tooth loss. MATERIALS AND METHODS: Medline/Embase/Central were searched for longitudinal studies investigating the association between predictors and tooth loss in periodontitis patients. Random-effects meta-analysis was performed, and study quality assessed. RESULTS: Twenty studies (15,422 patients, mean follow-up: 12 years) were included. The mean annual tooth loss/patient was 0.12 (min./max: 0.01/0.36). Older patients (n = 8 studies; OR: 1.05, 95% CI: 1.03-1.08/year), non-compliant ones (n = 11; 1.51, 1.06-2.16), diabetics (n = 7; 1.80, 1.26-2.57), those with IL-1-polymorphism (n = 3; 1.80; 1.29-2.52) and smokers (n = 15; 1.98, 1.58-2.48) had a significantly higher risk of tooth loss. Teeth with bone loss (n = 3; 1.04, 1.03-1.05/%), high probing pocket depth (n = 6; 3.19, 1.70-5.98), mobility (n = 4; 3.71, 1.65-8.38) and molars (n = 4; 4.22, 2.12-8.39), especially with furcation involvement (n = 5; 2.68, 1.75-4.08) also showed higher risks. Gender (n = 16; 0.95, 0.86-1.05) and endodontic affection (n = 3; 3.62, 0.99-13.2) were not significantly associated with tooth loss. CONCLUSIONS: Older, non-compliant, smoking or diabetic patients, and teeth with bone loss, high probing pocket depth, mobility, or molars, especially with furcation involvement showed higher risks of tooth loss.

More teeth in more elderly: Periodontal treatment needs in Germany 1997-2030.

OBJECTIVE: With more teeth retained for longer in an ageing population, population-wide periodontal treatment needs may increase. We assessed and projected periodontal treatment needs from 1997 to 2030 in Germany. METHODS: Partial-mouth probing-pocket depths (PPDs) from repeated waves (1997, 2005, 2014) of the nationally representative German Oral Health Studies were transformed into full-mouth PPDs via decision-tree-based ensemble-modelling. In line with German healthcare-regulations, teeth with PPD ≥ 4 mm were regarded as needing periodontal treatment. Weighted means were interpolated cross-sectionally by fitting spline-curves and then regressed longitudinally 1997-2030. RESULTS: In 1997, younger adults (35-44 years old) had a mean of 7.4 teeth needing treatment (overall 93.8 million teeth); this decreased to 4.8 teeth (47.3 million teeth) in 2014. For 2030, we project 3.2 teeth (33.7 million teeth). In seniors, an increase was recorded (1997: 4.5 teeth, 33.5 million teeth; 2014: 7.5 teeth, 63.4 million teeth); this is expected to continue until 2030 (to 12.2 teeth, 140.8 million teeth). The cumulative number of teeth needing treatment increased from 2000 (355 million) to 2015 (365 million), and will increase further to 2030 (464 million). CONCLUSIONS: Population-wide periodontal treatment needs may increase until 2030, mainly in the elderly. Concepts for addressing, these growing needs are required.

Conquering class imbalances in deep learning-based segmentation of dental radiographs with different loss functions.

OBJECTIVE: The imbalanced nature of real-world datasets is an ongoing challenge in the field of machine and deep learning. In medicine and in dentistry, most data samples represent patients not affected by pathologies, and on imagery, pathologic image areas are often smaller than healthy ones. Selecting suitable loss functions during deep learning is essential and may help to overcome the resulting imbalance. We assessed six different loss functions for one exemplary task, tooth structure segmentation on bitewing radiographs, for their performance. METHODS: Six different loss functions (Focal Loss, Dice Loss, Tversky Loss and hybrid losses of Cross-Entropy and Dice Loss, Focal and Dice Loss, Focal and Generalized Dice Loss) were compared on a tooth structure segmentation task of 1,625 bitewing radiographs. Training was performed using three different model architectures (U-Net, Linknet, DeepLavbV3+) over a 5-fold cross-validation. Tooth structures consisted of the classes (occurrence in% of samples/captures areas measured on pixel level) enamel (100 %/25 %), dentin (100 %/50 %), root canal (100 %/10 %), filling (81 %/8 %) and crown (28 %/5 %). RESULTS: Hybrid loss functions significantly outperformed standalone ones and provided robust results over the different architectures for the classes enamel, dentin, root canal and filling. Specifically, the Dice Focal loss reached high performance to conquer both image level and pixel level class imbalance, respectively. CLINICAL SIGNIFICANCE: In dental use cases it is often important to predict minority classes such as pathologies accurately. Using specific loss function may be an effective strategy to overcome data imbalance when training deep learning models.

Expert gaze as a usability indicator of medical AI decision support systems: a preliminary study.

Given the current state of medical artificial intelligence (AI) and perceptions towards it, collaborative systems are becoming the preferred choice for clinical workflows. This work aims to address expert interaction with medical AI support systems to gain insight towards how these systems can be better designed with the user in mind. As eye tracking metrics have been shown to be robust indicators of usability, we employ them for evaluating the usability and user interaction with medical AI support systems. We use expert gaze to assess experts' interaction with an AI software for caries detection in bitewing x-ray images. We compared standard viewing of bitewing images without AI support versus viewing where AI support could be freely toggled on and off. We found that experts turned the AI on for roughly 25% of the total inspection task, and generally turned it on halfway through the course of the inspection. Gaze behavior showed that when supported by AI, more attention was dedicated to user interface elements related to the AI support, with more frequent transitions from the image itself to these elements. When considering that expert visual strategy is already optimized for fast and effective image inspection, such interruptions in attention can lead to increased time needed for the overall assessment. Gaze analysis provided valuable insights into an AI's usability for medical image inspection. Further analyses of these tools and how to delineate metrical measures of usability should be developed.