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.

Machine Learning to Predict Apical Lesions: A Cross-Sectional and Model Development Study.

(1) Background: We aimed to identify factors associated with the presence of apical lesions (AL) in panoramic radiographs and to evaluate the predictive value of the identified factors. (2) Methodology: Panoramic radiographs from 1071 patients (age: 11-93 a, mean: 50.6 a ± 19.7 a) with 27,532 teeth were included. Each radiograph was independently assessed by five experienced dentists for AL. A range of shallow machine learning algorithms (logistic regression, k-nearest neighbor, decision tree, random forest, support vector machine, adaptive and gradient boosting) were employed to identify factors at both the patient and tooth level associated with AL and to predict AL. (3) Results: AL were detected in 522 patients (48.7%) and 1133 teeth (4.1%), whereas males showed a significantly higher prevalence than females (52.5%/44.8%; p < 0.05). Logistic regression found that an existing root canal treatment was the most important risk factor (adjusted Odds Ratio 16.89; 95% CI: 13.98-20.41), followed by the tooth type 'molar' (2.54; 2.1-3.08) and the restoration with a crown (2.1; 1.67-2.63). Associations between factors and AL were stronger and accuracy higher when using fewer complex models like decision tree (F1 score: 0.9 (0.89-0.9)). (4) Conclusions: The presence of AL was higher in root-canal treated teeth, those with crowns and molars. More complex machine learning models did not outperform less-complex ones.

Patients' perspectives on the use of artificial intelligence in dentistry: a regional survey.

The use of artificial intelligence (AI) in dentistry is rapidly evolving and could play a major role in a variety of dental fields. This study assessed patients' perceptions and expectations regarding AI use in dentistry. An 18-item questionnaire survey focused on demographics, expectancy, accountability, trust, interaction, advantages and disadvantages was responded to by 330 patients; 265 completed questionnaires were included in this study. Frequencies and differences between age groups were analysed using a two-sided chi-squared or Fisher's exact tests with Monte Carlo approximation. Patients' perceived top three disadvantages of AI use in dentistry were (1) the impact on workforce needs (37.7%), (2) new challenges on doctor-patient relationships (36.2%) and (3) increased dental care costs (31.7%). Major expected advantages were improved diagnostic confidence (60.8%), time reduction (48.3%) and more personalised and evidencebased disease management (43.0%). Most patients expected AI to be part of the dental workflow in 1-5 (42.3%) or 5-10 (46.8%) years. Older patients (> 35 years) expected higher AI performance standards than younger patients (18-35 years) (p < 0.05). Overall, patients showed a positive attitude towards AI in dentistry. Understanding patients' perceptions may allow professionals to shape AI-driven dentistry in the future.

Ethical considerations on artificial intelligence in dentistry: A framework and checklist.

OBJECTIVE: Artificial Intelligence (AI) refers to the ability of machines to perform cognitive and intellectual human tasks. In dentistry, AI offers the potential to enhance diagnostic accuracy, improve patient outcomes and streamline workflows. The present study provides a framework and a checklist to evaluate AI applications in dentistry from this perspective. METHODS: Lending from existing guidance documents, an initial draft of the checklist and an explanatory paper were derived and discussed among the groups members. RESULTS: The checklist was consented to in an anonymous voting process by 29 Topic Group Dental Diagnostics and Digital Dentistry, ITU/WHO Focus Group AI on Health's members. Overall, 11 principles were identified (diversity, transparency, wellness, privacy protection, solidarity, equity, prudence, law and governance, sustainable development, accountability, and responsibility, respect of autonomy, decision-making). CONCLUSIONS: Providers, patients, researchers, industry, and other stakeholders should consider these principles when developing, implementing, or receiving AI applications in dentistry. CLINICAL SIGNIFICANCE: While AI has become increasingly commonplace in dentistry, there are ethical concerns around its usage, and users (providers, patients, and other stakeholders), as well as the industry should consider these when developing, implementing, or receiving AI applications based on comprehensive framework to address the associated ethical challenges.

Gaze patterns of dentists while evaluating bitewing radiographs.

OBJECTIVES: Understanding dentists' gaze patterns on radiographs may allow to unravel sources of their limited accuracy and develop strategies to mitigate them. We conducted an eye tracking experiment to characterize dentists' scanpaths and thus their gaze patterns when assessing bitewing radiographs to detect primary proximal carious lesions. METHODS: 22 dentists assessed a median of nine bitewing images each, resulting in 170 datasets after excluding data with poor quality of gaze recording. Fixation was defined as an area of attentional focus related to visual stimuli. We calculated time to first fixation, fixation count, average fixation duration, and fixation frequency. Analyses were performed for the entire image and stratified by (1) presence of carious lesions and/or restorations and (2) lesion depth (E1/2: outer/inner enamel; D1-3: outer-inner third of dentin). We also examined the transitional nature of the dentists' gaze. RESULTS: Dentists had more fixations on teeth with lesions and/or restorations (median=138 [interquartile range=87, 204]) than teeth without them (32 [15, 66]), p<0.001. Notably, teeth with lesions had longer fixation durations (407 milliseconds [242, 591]) than those with restorations (289 milliseconds [216, 337]), p<0.001. Time to first fixation was longer for teeth with E1 lesions (17,128 milliseconds [8813, 21,540]) than lesions of other depths (p = 0.049). The highest number of fixations were on teeth with D2 lesions (43 [20, 51]) and lowest on teeth with E1 lesions (5 [1, 37]), p<0.001. Generally, a systematic tooth-by-tooth gaze pattern was observed. CONCLUSIONS: As hypothesized, while visually inspecting bitewing radiographic images, dentists employed a heightened focus on certain image features/areas, relevant to the assigned task. Also, they generally examined the entire image in a systematic tooth-by-tooth pattern.

Impact of Noisy Labels on Dental Deep Learning-Calculus Detection on Bitewing Radiographs.

Supervised deep learning requires labelled data. On medical images, data is often labelled inconsistently (e.g., too large) with varying accuracies. We aimed to assess the impact of such label noise on dental calculus detection on bitewing radiographs. On 2584 bitewings calculus was accurately labeled using bounding boxes (BBs) and artificially increased and decreased stepwise, resulting in 30 consistently and 9 inconsistently noisy datasets. An object detection network (YOLOv5) was trained on each dataset and evaluated on noisy and accurate test data. Training on accurately labeled data yielded an mAP50: 0.77 (SD: 0.01). When trained on consistently too small BBs model performance significantly decreased on accurate and noisy test data. Model performance trained on consistently too large BBs decreased immediately on accurate test data (e.g., 200% BBs: mAP50: 0.24; SD: 0.05; p < 0.05), but only after drastically increasing BBs on noisy test data (e.g., 70,000%: mAP50: 0.75; SD: 0.01; p < 0.05). Models trained on inconsistent BB sizes showed a significant decrease of performance when deviating 20% or more from the original when tested on noisy data (mAP50: 0.74; SD: 0.02; p < 0.05), or 30% or more when tested on accurate data (mAP50: 0.76; SD: 0.01; p < 0.05). In conclusion, accurate predictions need accurate labeled data in the training process. Testing on noisy data may disguise the effects of noisy training data. Researchers should be aware of the relevance of accurately annotated data, especially when testing model performances.

Federated vs Local vs Central Deep Learning of Tooth Segmentation on Panoramic Radiographs.

OBJECTIVE: Federated Learning (FL) enables collaborative training of artificial intelligence (AI) models from multiple data sources without directly sharing data. Due to the large amount of sensitive data in dentistry, FL may be particularly relevant for oral and dental research and applications. This study, for the first time, employed FL for a dental task, automated tooth segmentation on panoramic radiographs. METHODS: We employed a dataset of 4,177 panoramic radiographs collected from nine different centers (n = 143 to n = 1881 per center) across the globe and used FL to train a machine learning model for tooth segmentation. FL performance was compared against Local Learning (LL), i.e., training models on isolated data from each center (assuming data sharing not to be an option). Further, the performance gap to Central Learning (CL), i.e., training on centrally pooled data (based on data sharing agreements) was quantified. Generalizability of models was evaluated on a pooled test dataset from all centers. RESULTS: For 8 out of 9 centers, FL outperformed LL with statistical significance (p<0.05); only the center providing the largest amount of data FL did not have such an advantage. For generalizability, FL outperformed LL across all centers. CL surpassed both FL and LL for performance and generalizability. CONCLUSION: If data pooling (for CL) is not feasible, FL is shown to be a useful alternative to train performant and, more importantly, generalizable deep learning models in dentistry, where data protection barriers are high. CLINICAL SIGNIFICANCE: This study proves the validity and utility of FL in the field of dentistry, which encourages researchers to adopt this method to improve the generalizability of dental AI models and ease their transition to the clinical environment.

Super-Resolution of Dental Panoramic Radiographs Using Deep Learning: A Pilot Study.

Using super-resolution (SR) algorithms, an image with a low resolution can be converted into a high-quality image. Our objective was to compare deep learning-based SR models to a conventional approach for improving the resolution of dental panoramic radiographs. A total of 888 dental panoramic radiographs were obtained. Our study involved five state-of-the-art deep learning-based SR approaches, including SR convolutional neural networks (SRCNN), SR generative adversarial network (SRGAN), U-Net, Swin for image restoration (SwinIr), and local texture estimator (LTE). Their results were compared with one another and with conventional bicubic interpolation. The performance of each model was evaluated using the metrics of mean squared error (MSE), peak signal-to-noise ratio (PNSR), structural similarity index (SSIM), and mean opinion score by four experts (MOS). Among all the models evaluated, the LTE model presented the highest performance, with MSE, SSIM, PSNR, and MOS results of 7.42 ± 0.44, 39.74 ± 0.17, 0.919 ± 0.003, and 3.59 ± 0.54, respectively. Additionally, compared with low-resolution images, the output of all the used approaches showed significant improvements in MOS evaluation. A significant enhancement in the quality of panoramic radiographs can be achieved by SR. The LTE model outperformed the other models.

Machine Learning in Dentistry: A Scoping Review.

Machine learning (ML) is being increasingly employed in dental research and application. We aimed to systematically compile studies using ML in dentistry and assess their methodological quality, including the risk of bias and reporting standards. We evaluated studies employing ML in dentistry published from 1 January 2015 to 31 May 2021 on MEDLINE, IEEE Xplore, and arXiv. We assessed publication trends and the distribution of ML tasks (classification, object detection, semantic segmentation, instance segmentation, and generation) in different clinical fields. We appraised the risk of bias and adherence to reporting standards, using the QUADAS-2 and TRIPOD checklists, respectively. Out of 183 identified studies, 168 were included, focusing on various ML tasks and employing a broad range of ML models, input data, data sources, strategies to generate reference tests, and performance metrics. Classification tasks were most common. Forty-two different metrics were used to evaluate model performances, with accuracy, sensitivity, precision, and intersection-over-union being the most common. We observed considerable risk of bias and moderate adherence to reporting standards which hampers replication of results. A minimum (core) set of outcome and outcome metrics is necessary to facilitate comparisons across studies.

How Do Users Respond to Mass Vaccination Centers? A Cross-Sectional Study Using Natural Language Processing on Online Reviews to Explore User Experience and Satisfaction with COVID-19 Vaccination Centers.

To reach large groups of vaccine recipients, several high-income countries introduced mass vaccination centers for COVID-19. Understanding user experiences of these novel structures can help optimize their design and increase patient satisfaction and vaccine uptake. This study drew on user online reviews of vaccination centers to assess user experience and identify its key determinants over time, by sentiment, and by interaction. Machine learning methods were used to analyze Google reviews of six COVID-19 mass vaccination centers in Berlin from December 2020 to December 2021. 3647 user online reviews were included in the analysis. Of these, 89% (3261/3647) were positive according to user rating (four to five of five stars). A total of 85% (2740/3647) of all reviews contained text. Topic modeling of the reviews containing text identified five optimally latent topics, and keyword extraction identified 47 salient keywords. The most important themes were organization, friendliness/responsiveness, and patient flow/wait time. Key interactions for users of vaccination centers included waiting, scheduling, transit, and the vaccination itself. Keywords connected to scheduling and efficiency, such as "appointment" and "wait", were most prominent in negative reviews. Over time, the average rating score decreased from 4.7 to 4.1, and waiting and duration became more salient keywords. Overall, mass vaccination centers appear to be positively perceived, yet users became more critical over the one-year period of the pandemic vaccination campaign observed. The study shows that online reviews can provide real-time insights into newly set-up infrastructures, and policymakers should consider their use to monitor the population's response over time.

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.

Resin Infiltration of Non-Cavitated Proximal Caries Lesions in Primary and Permanent Teeth: A Systematic Review and Scenario Analysis of Randomized Controlled Trials.

The present study aimed to meta-analyze and evaluate the certainty of evidence for resin infiltration of proximal carious lesions in primary and permanent teeth. While resin infiltration has been shown efficacious for caries management, the certainty of evidence remains unclear. The protocol was registered with PROSPERO (CRD42018080895), and PRISMA guidelines have been followed. The databases PubMed, Embase, and Cochrane CENTRAL were systematically screened, complemented by hand searches and cross-referencing. Eleven relevant articles were identified and included, i.e., randomized controlled trials (RCTs) comparing the progression of resin infiltrated proximal caries lesions (combined with non-invasive measures) in primary or permanent teeth with non-invasive measures. Random-effects meta-analyses and trial sequential analyses (TSA) were performed for per-protocol (PP), intention-to-treat (ITT), and best/worst case (BC/WC) scenarios. Six included trials assessed lesions in permanent teeth and five trails assessed lesions in primary teeth. The trials had a high or unclear risk of bias. Risk of caries progression was significantly reduced for infiltrated lesions in the PP, ITT, and BC scenarios in both permanent teeth and primary teeth, but not in the WC scenario. According to the TSA, firm evidence was reached for all of the scenarios except the WC. In conclusion, there is firm evidence for resin infiltration arresting proximal caries lesions in permanent and primary teeth.

Deep learning: A primer for dentists and dental researchers.

OBJECTIVES: Despite deep learning's wide adoption in dental artificial intelligence (AI) research, researchers from other dental fields and, more so, dental professionals may find it challenging to understand and interpret deep learning studies, their employed methods, and outcomes. The objective of this primer is to explain the basic concept of deep learning. It will lay out the commonly used terms, and describe different deep learning approaches, their methods, and outcomes. METHODS: Our research is based on the latest review studies, medical primers, as well as the state-of-the-art research on AI and deep learning, which have been gathered in the current study. RESULTS: In this study, a basic understanding of deep learning models and various approaches to deep learning is presented. An overview of data management strategies for deep learning projects is presented, including data collection, data curation, data annotation, and data preprocessing. Additionally, we provided a step-by-step guide for completing a real-world project. CONCLUSION: Researchers and clinicians can benefit from this study by gaining insight into deep learning. It can be used to critically appraise existing work or plan new deep learning projects. CLINICAL SIGNIFICANCE: This study may be useful to dental researchers and professionals who are assessing and appraising deep learning studies within the field of dentistry.

Artificial intelligence for oral and dental healthcare: Core education curriculum.

OBJECTIVES: Artificial intelligence (AI) is swiftly entering oral health services and dentistry, while most providers show limited knowledge and skills to appraise dental AI applications. We aimed to define a core curriculum for both undergraduate and postgraduate education, establishing a minimum set of outcomes learners should acquire when taught about oral and dental AI. METHODS: Existing curricula and other documents focusing on literacy of medical professionals around AI were screened and relevant items extracted. Items were scoped and adapted using expert interviews with members of the IADR's e-oral health group, the ITU/WHO's Focus Group AI for Health and the Association for Dental Education in Europe. Learning outcome levels were defined and each item assigned to a level. Items were systematized into domains and a curricular structure defined. The resulting curriculum was consented using an online Delphi process. RESULTS: Four domains of learning outcomes emerged, with most outcomes being on the "knowledge" level: (1) Basic definitions and terms, the reasoning behind AI and the principle of machine learning, the idea of training, validating and testing models, the definition of reference tests, the contrast between dynamic and static AI, and the problem of AI being a black box and requiring explainability should be known. (2) Use cases, the required types of AI to address them, and the typical setup of AI software for dental purposes should be taught. (3) Evaluation metrics, their interpretation, the relevant impact of AI on patient or societal health outcomes and associated examples should be considered. (4) Issues around generalizability and representativeness, explainability, autonomy and accountability and the need for governance should be highlighted. CONCLUSION: Both educators and learners should consider this core curriculum during planning, conducting and evaluating oral and dental AI education. CLINICAL SIGNIFICANCE: A core curriculum on oral and dental AI may help to increase oral and dental healthcare providers' literacy around AI, allowing them to critically appraise AI applications and to use them consciously and on an informed basis.

Developing Automated Computer Algorithms to Phenotype Periodontal Disease Diagnoses in Electronic Dental Records.

OBJECTIVE: Our objective was to phenotype periodontal disease (PD) diagnoses from three different sections (diagnosis codes, clinical notes, and periodontal charting) of the electronic dental records (EDR) by developing two automated computer algorithms. METHODS: We conducted a retrospective study using EDR data of patients (n = 27,138) who received care at Temple University Maurice H. Kornberg School of Dentistry from January 1, 2017 to August 31, 2021. We determined the completeness of patient demographics, periodontal charting, and PD diagnoses information in the EDR. Next, we developed two automated computer algorithms to automatically diagnose patients' PD statuses from clinical notes and periodontal charting data. Last, we phenotyped PD diagnoses using automated computer algorithms and reported the improved completeness of diagnosis. RESULTS: The completeness of PD diagnosis from the EDR was as follows: periodontal diagnosis codes 36% (n = 9,834), diagnoses in clinical notes 18% (n = 4,867), and charting information 80% (n = 21,710). After phenotyping, the completeness of PD diagnoses improved to 100%. Eleven percent of patients had healthy periodontium, 43% were with gingivitis, 3% with stage I, 36% with stage II, and 7% with stage III/IV periodontitis. CONCLUSIONS: We successfully developed, tested, and deployed two automated algorithms on big EDR datasets to improve the completeness of PD diagnoses. After phenotyping, EDR provided 100% completeness of PD diagnoses of 27,138 unique patients for research purposes. This approach is recommended for use in other large databases for the evaluation of their EDR data quality and for phenotyping PD diagnoses and other relevant variables.

Predicting mortality in the very old: a machine learning analysis on claims data.

Machine learning (ML) may be used to predict mortality. We used claims data from one large German insurer to develop and test differently complex ML prediction models, comparing them for their (balanced) accuracy, but also the importance of different predictors, the relevance of the follow-up period before death (i.e. the amount of accumulated data) and the time distance of the data used for prediction and death. A sample of 373,077 insured very old, aged 75 years or above, living in the Northeast of Germany in 2012 was drawn and followed over 6 years. Our outcome was whether an individual died in one of the years of interest (2013-2017) or not; the primary metric was (balanced) accuracy in a hold-out test dataset. From the 86,326 potential variables, we used the 30 most important ones for modeling. We trained a total of 45 model combinations: (1) Three different ML models were used; logistic regression (LR), random forest (RF), extreme gradient boosting (XGB); (2) Different periods of follow-up were employed for training; 1-5 years; (3) Different time distances between data used for prediction and the time of the event (death/survival) were set; 0-4 years. The mortality rate was 9.15% in mean per year. The models showed (balanced) accuracy between 65 and 93%. A longer follow-up period showed limited to no advantage, but models with short time distance from the event were more accurate than models trained on more distant data. RF and XGB were more accurate than LR. For RF and XGB sensitivity and specificity were similar, while for LR sensitivity was significantly lower than specificity. For all three models, the positive-predictive-value was below 62% (and even dropped to below 20% for longer time distances from death), while the negative-predictive-value significantly exceeded 90% for all analyses. The utilization of and costs for emergency transport as well as emergency and any hospital visits as well as the utilization of conventional outpatient care and laboratory services were consistently found most relevant for predicting mortality. All models showed useful accuracies, and more complex models showed advantages. The variables employed for prediction were consistent across models and with medical reasoning. Identifying individuals at risk could assist tailored decision-making and interventions.

Evaluation of the Clinical, Technical, and Financial Aspects of Cost-Effectiveness Analysis of Artificial Intelligence in Medicine: Scoping Review and Framework of Analysis.

BACKGROUND: Cost-effectiveness analysis of artificial intelligence (AI) in medicine demands consideration of clinical, technical, and economic aspects to generate impactful research of a novel and highly versatile technology. OBJECTIVE: We aimed to systematically scope existing literature on the cost-effectiveness of AI and to extract and summarize clinical, technical, and economic dimensions required for a comprehensive assessment. METHODS: A scoping literature review was conducted to map medical, technical, and economic aspects considered in studies on the cost-effectiveness of medical AI. Based on these, a framework for health policy analysis was developed. RESULTS: Among 4820 eligible studies, 13 met the inclusion criteria for our review. Internal medicine and emergency medicine were the clinical disciplines most frequently analyzed. Most of the studies included were from the United States (5/13, 39%), assessed solutions requiring market access (9/13, 69%), and proposed optimization of direct resources as the most frequent value proposition (7/13, 53%). On the other hand, technical aspects were not uniformly disclosed in the studies we analyzed. A minority of articles explicitly stated the payment mechanism assumed (5/13, 38%), while it remained unspecified in the majority (8/13, 62%) of studies. CONCLUSIONS: Current studies on the cost-effectiveness of AI do not allow to determine if the investigated AI solutions are clinically, technically, and economically viable. Further research and improved reporting on these dimensions seem relevant to recommend and assess potential use cases for this technology.

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.

Emulating Clinical Diagnostic Reasoning for Jaw Cysts with Machine Learning.

The detection and classification of cystic lesions of the jaw is of high clinical relevance and represents a topic of interest in medical artificial intelligence research. The human clinical diagnostic reasoning process uses contextual information, including the spatial relation of the detected lesion to other anatomical structures, to establish a preliminary classification. Here, we aimed to emulate clinical diagnostic reasoning step by step by using a combined object detection and image segmentation approach on panoramic radiographs (OPGs). We used a multicenter training dataset of 855 OPGs (all positives) and an evaluation set of 384 OPGs (240 negatives). We further compared our models to an international human control group of ten dental professionals from seven countries. The object detection model achieved an average precision of 0.42 (intersection over union (IoU): 0.50, maximal detections: 100) and an average recall of 0.394 (IoU: 0.50-0.95, maximal detections: 100). The classification model achieved a sensitivity of 0.84 for odontogenic cysts and 0.56 for non-odontogenic cysts as well as a specificity of 0.59 for odontogenic cysts and 0.84 for non-odontogenic cysts (IoU: 0.30). The human control group achieved a sensitivity of 0.70 for odontogenic cysts, 0.44 for non-odontogenic cysts, and 0.56 for OPGs without cysts as well as a specificity of 0.62 for odontogenic cysts, 0.95 for non-odontogenic cysts, and 0.76 for OPGs without cysts. Taken together, our results show that a combined object detection and image segmentation approach is feasible in emulating the human clinical diagnostic reasoning process in classifying cystic lesions of the jaw.

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.