Data Dentistry: How Data Are Changing Clinical Care and Research

Advanced Imaging in Dental Research: From Gene Mapping to AI Global Data

Advances in imaging technologies combined with artificial intelligence (AI) are transforming dental, oral, and craniofacial research. This editorial highlights breakthroughs ranging from gene expression mapping to visualizing the availability of global AI data, providing new insights into biological complexity and clinical applications.

Cybersecurity threats and preparedness: Implications for dental schools

BACKGROUND

Cybersecurity threats are a growing concern in healthcare, where digital systems now underpin patient care, financial management, and educational operations. A cybersecurity breach in a Dental school environment can have widespread consequences to the mission of the school-patient care, research, education and service. For dental school administrators, these risks highlight the necessity of robust cybersecurity measures. For student learners, the impact may include interruptions to their education. For patients, it could mean compromised personal data and reduced access to clinical care.

RESULTS & CONCLUSION

While many sectors have responded to increasing cyber threats by enhancing their defenses, healthcare and dental schools, often lag in implementing necessary protections. This emphasizes the need for proactive measures, such as regular system audits, advanced encryption methods, and ongoing cybersecurity training for administrators and students alike, to mitigate future risks and safeguard institutional integrity.

Publicly Available Dental Image Datasets for Artificial Intelligence

The development of artificial intelligence (AI) in dentistry requires large and well-annotated datasets. However, the availability of public dental imaging datasets remains unclear. This study aimed to provide a comprehensive overview of all publicly available dental imaging datasets to address this gap and support AI development. This observational study searched all publicly available dataset resources (academic databases, preprints, and AI challenges), focusing on datasets/articles from 2020 to 2023, with PubMed searches extending back to 2011. We comprehensively searched for dental AI datasets containing images (intraoral photos, scans, radiographs, etc.) using relevant keywords. We included datasets of >50 images obtained from publicly available sources. We extracted dataset characteristics, patient demographics, country of origin, dataset size, ethical clearance, image details, FAIRness metrics, and metadata completeness. We screened 131,028 records and extracted 16 unique dental imaging datasets. The datasets were obtained from Kaggle (18.8%), GitHub, Google, Mendeley, PubMed, Zenodo (each 12.5%), Grand-Challenge, OSF, and arXiv (each 6.25%). The primary focus was tooth segmentation (62.5%) and labeling (56.2%). Panoramic radiography was the most common imaging modality (58.8%). Of the 13 countries, China contributed the most images (2,413). Of the datasets, 75% contained annotations, whereas the methods used to establish labels were often unclear and inconsistent. Only 31.2% of the datasets reported ethical approval, and 56.25% did not specify a license. Most data were obtained from dental clinics (50%). Intraoral radiographs had the highest findability score in the FAIR assessment, whereas cone-beam computed tomography datasets scored the lowest in all categories. These findings revealed a scarcity of publicly available imaging dental data and inconsistent metadata reporting. To promote the development of robust, equitable, and generalizable AI tools for dental diagnostics, treatment, and research, efforts are needed to address data scarcity, increase diversity, mandate metadata completeness, and ensure FAIRness in AI dental imaging research.

Integrated bioinformatic analysis of protein landscape in gingival crevicular fluid unveils sequential bioprocess in orthodontic tooth movement

BACKGROUND

The biological mechanisms driving orthodontic tooth movement (OTM) remain incompletely understood. Gingival crevicular fluid (GCF) is an important indicator of the periodontal bioprocess, providing valuable cues for probing the molecular mechanisms of OTM.

METHODS

A rigorous review of the clinical studies over the past decade was conducted after registering the protocol with PROSPERO and adhering to inclusion criteria comprising human subjects, specified force magnitudes and force application modes. The thorough screening investigated differentially expressed proteins (DEPs) in GCF associated with OTM. Protein-protein interaction (PPI) analysis was carried out using the STRING database, followed by further refinement through Cytoscape to isolate top hub proteins.

RESULTS

A comprehensive summarization of the OTM-related GCF studies was conducted, followed by an in-depth exploration of biomarkers within the GCF. We identified 13 DEPs, including ALP, IL-1β, IL-6, Leptin, MMP-1, MMP-3, MMP-8, MMP-9, PGE2, TGF-β1, TNF-α, OPG, RANKL. Bioinformatic analysis spotlighted the top 10 hub proteins and their interactions involved in OTM. Based on these findings, we have proposed a hypothetic diagram for the time-course bioprocess in OTM, which involves three phases containing sequential cellular and molecular components and their interplay network.

CONCLUSIONS

This work has further improved our understanding to the bioprocess of OTM, suggesting biomarkers as potential modulating targets to enhance OTM, mitigate adverse effects and support real-time monitoring and personalized orthodontic cycles.

Performance of Generative Artificial Intelligence in Dental Licensing Examinations

OBJECTIVES

Generative artificial intelligence (GenAI), including large language models (LLMs), has vast potential applications in health care and education. However, it is unclear how proficient LLMs are in interpreting written input and providing accurate answers in dentistry. This study aims to investigate the accuracy of GenAI in answering questions from dental licensing examinations.

METHODS

A total of 1461 multiple-choice questions from question books for the US and the UK dental licensing examinations were input into 2 versions of ChatGPT 3.5 and 4.0. The passing rates of the US and UK dental examinations were 75.0% and 50.0%, respectively. The performance of the 2 versions of GenAI in individual examinations and dental subjects was analysed and compared.

RESULTS

ChatGPT 3.5 correctly answered 68.3% (n = 509) and 43.3% (n = 296) of questions from the US and UK dental licensing examinations, respectively. The scores for ChatGPT 4.0 were 80.7% (n = 601) and 62.7% (n = 429), respectively. ChatGPT 4.0 passed both written dental licensing examinations, whilst ChatGPT 3.5 failed. ChatGPT 4.0 answered 327 more questions correctly and 102 incorrectly compared to ChatGPT 3.5 when comparing the 2 versions.

CONCLUSIONS

The newer version of GenAI has shown good proficiency in answering multiple-choice questions from dental licensing examinations. Whilst the more recent version of GenAI generally performed better, this observation may not hold true in all scenarios, and further improvements are necessary. The use of GenAI in dentistry will have significant implications for dentist-patient communication and the training of dental professionals.

Artificial intelligence and personalized diagnostics in periodontology: A narrative review

Periodontal diseases pose a significant global health burden, requiring early detection and personalized treatment approaches. Traditional diagnostic approaches in periodontology often rely on a "one size fits all" approach, which may overlook the unique variations in disease progression and response to treatment among individuals. This narrative review explores the role of artificial intelligence (AI) and personalized diagnostics in periodontology, emphasizing the potential for tailored diagnostic strategies to enhance precision medicine in periodontal care. The review begins by elucidating the limitations of conventional diagnostic techniques. Subsequently, it delves into the application of AI models in analyzing diverse data sets, such as clinical records, imaging, and molecular information, and its role in periodontal training. Furthermore, the review also discusses the role of research community and policymakers in integrating personalized diagnostics in periodontal care. Challenges and ethical considerations associated with adopting AI-based personalized diagnostic tools are also explored, emphasizing the need for transparent algorithms, data safety and privacy, ongoing multidisciplinary collaboration, and patient involvement. In conclusion, this narrative review underscores the transformative potential of AI in advancing periodontal diagnostics toward a personalized paradigm, and their integration into clinical practice holds the promise of ushering in a new era of precision medicine for periodontal care.

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.

[The challenges of artificial intelligence in odontology]

Artificial intelligence has numerous potential applications in dentistry, as these algorithms aim to improve the efficiency and safety of several clinical situations. While the first commercial solutions are being proposed, most of these algorithms have not been sufficiently validated for clinical use. This article describes the challenges surrounding the development of these new tools, to help clinicians to keep a critical eye on this technology.

Predicting sequenced dental treatment plans from electronic dental records using deep learning

BACKGROUND

Designing appropriate clinical dental treatment plans is an urgent need because a growing number of dental patients are suffering from partial edentulism with the population getting older.

OBJECTIVES

The aim of this study is to predict sequential treatment plans from electronic dental records.

METHODS

We construct a clinical decision support model, MultiTP, explores the unique topology of teeth information and the variation of complicated treatments, integrates deep learning models (convolutional neural network and recurrent neural network) adaptively, and embeds the attention mechanism to produce optimal treatment plans.

RESULTS

MultiTP shows its promising performance with an AUC of 0.9079 and an F score of 0.8472 over five treatment plans. The interpretability analysis also indicates its capability in mining clinical knowledge from the textual data.

CONCLUSIONS

MultiTP's novel problem formulation, neural network framework, and interpretability analysis techniques allow for broad applications of deep learning in dental healthcare, providing valuable support for predicting dental treatment plans in the clinic and benefiting dental patients.

CLINICAL IMPLICATIONS

The MultiTP is an efficient tool that can be implemented in clinical practice and integrated into the existing EDR system. By predicting treatment plans for partial edentulism, the model will help dentists improve their clinical decisions.

Population-Based Applications and Analytics Using Patient-Reported Outcome Measures

The intersection of big data and artificial intelligence (AI) has resulted in advances in numerous areas, including machine learning, computer vision, and natural language processing. Although there are many potentially transformative applications of AI in health care, including precision medicine, this industry has been slow to adopt these technologies. At the same time, the operations of health care have historically been system-directed and physician-directed rather than patient-centered. The application of AI to patient-reported outcome measures (PROMs), which provide insight into patient-centered health outcomes, could steer research and healthcare delivery toward decisions that optimize outcomes important to patients. Historically, PROMs have only been collected within research registries. However, the increasing availability of PROMs within electronic health records has led to their inclusion in big data ecosystems, where they can inform or be informed by other data elements. The use of big data to analyze PROMs can help establish norms, evaluate data distribution, and determine proportions of patients achieving change or threshold standards. This information can be used for benchmarking, risk adjustment, predictive modeling, and ultimately improving the health of individuals and populations.

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.

Emergence angle: Comprehensive analysis and machine learning prediction for clinical application

PURPOSE

To analyze and compare the emergence angle (EA) using two measurement methods, conventional and modified (EA-GPT and EA-R), the EAs of all-natural teeth were evaluated and classified to derive a suitable and predictable clinically applicable measurement method.

METHODS

Natural human teeth (n=600) were classified, cleaned, and thoroughly inspected. Teeth were scanned using an intraoral scanner. The scanned data were analyzed using three-dimensional analysis software for both methods with several points per surface. A Bland-Altman analysis was used for statistical analysis and a heat map and a nonparametric density plot to assess the repetition and distribution. An XGBoost regression model was used for prediction.

RESULTS

The EA-R method showed significantly different values compared to the EA-GPT method, representing an increase of 17.5-20.7% for the proximal surfaces. An insignificant difference between the two methods was observed for other surfaces. Different teeth classes showed variation in the normal range, thereby resulting in a new classification of the EA for all-natural teeth based on the interquartile range. The machine learning gradient boosting model predicted conventional data with an average mean absolute error of 0.9.

CONCLUSIONS

Variations in the natural teeth EA and measurement methods, suggest a new classification for EA. The established artificial intelligence method demonstrated robust performance, which could aid in implementing EA measurement in prosthetic designs.

Aspects Regarding Sustainability among Private Dental Practitioners from Bucharest, Romania: A Pilot Study

Oral health professionals' knowledge of sustainability is essential for promoting environmental protection in dental healthcare. This pilot study involved an online survey addressed to 70 dental private practitioners from Bucharest, Romania, to evaluate their awareness of the concept of sustainability in dentistry. The performed statistical analysis revealed that 41.4% of the participants were well aware of sustainability in dentistry, with older participants demonstrating significantly higher levels of such awareness (p = 0.001). Sustainability awareness among participants correlates positively with their knowledge of the negative environmental impacts of dental activity (p < 0.001) and with the concern for sustainable dentistry implementation in their workplace (p = 0.037). Improper biohazardous waste disposal was identified as the primary cause of negative environmental impact of dental practices by 87.1% of participants. Installing high energy-efficient dental equipment was selected as the most important action to implement sustainability in participants' dental practices (64.3%). Overall, 51.4% of the participants reported that the COVID-19 pandemic had a medium impact on their dental activity in terms of sustainability. Our study found that participants have a moderate level of awareness regarding sustainability in dentistry, highlighting the need for education on sustainability for oral health professionals.

Protocol for developing a dashboard for interactive cohort analysis of oral health-related data

INTRODUCTION

A working knowledge of data analytics is becoming increasingly important in the digital health era. Interactive dashboards are a useful, accessible format for presenting and disseminating health-related information to a wide audience. However, many oral health researchers receive minimal data visualisation and programming skills.

OBJECTIVES

The objective of this protocols paper is to demonstrate the development of an analytical, interactive dashboard, using oral health-related data from multiple national cohort surveys.

METHODS

The flexdashboard package was used within the R Studio framework to create the structure-elements of the dashboard and interactivity was added with the Shiny package. Data sources derived from the national longitudinal study of children in Ireland and the national children's food survey. Variables for input were selected based on their known associations with oral health. The data were aggregated using tidyverse packages such as dplyr and summarised using ggplot2 and kableExtra with specific functions created to generate bar-plots and tables.

RESULTS

The dashboard layout is structured by the YAML (YAML Ain't Markup Language) metadata in the R Markdown document and the syntax from Flexdashboard. Survey type, wave of survey and variable selector were set as filter options. Shiny's render functions were used to change input to automatically render code and update output. The deployed dashboard is openly accessible at https://dduh.shinyapps.io/dduh/ . Examples of how to interact with the dashboard for selected oral health variables are illustrated.

CONCLUSION

Visualisation of national child cohort data in an interactive dashboard allows viewers to dynamically explore oral health data without requiring multiple plots and tables and sharing of extensive documentation. Dashboard development requires minimal non-standard R coding and can be quickly created with open-source software.

Artificial Intelligence in Medicine and Dentistry

INTRODUCTION

Artificial intelligence has been applied in various fields throughout history, but its integration into daily life is more recent. The first applications of AI were primarily in academia and government research institutions, but as technology has advanced, AI has also been applied in industry, commerce, medicine and dentistry.

OBJECTIVE

Considering that the possibilities of applying artificial intelligence are developing rapidly and that this field is one of the areas with the greatest increase in the number of newly published articles, the aim of this paper was to provide an overview of the literature and to give an insight into the possibilities of applying artificial intelligence in medicine and dentistry. In addition, the aim was to discuss its advantages and disadvantages.

CONCLUSION

The possibilities of applying artificial intelligence to medicine and dentistry are just being discovered. Artificial intelligence will greatly contribute to developments in medicine and dentistry, as it is a tool that enables development and progress, especially in terms of personalized healthcare that will lead to much better treatment outcomes.

Personalized dental medicine, artificial intelligence, and their relevance for dentomaxillofacial imaging

Personalized medicine refers to the tailoring of diagnostics and therapeutics to individuals based on one's biological, social, and behavioral characteristics. While personalized dental medicine is still far from being a reality, advanced artificial intelligence (AI) technologies with improved data analytic approaches are expected to integrate diverse data from the individual, setting, and system levels, which may facilitate a deeper understanding of the interaction of these multilevel data and therefore bring us closer to more personalized, predictive, preventive, and participatory dentistry, also known as P4 dentistry. In the field of dentomaxillofacial imaging, a wide range of AI applications, including several commercially available software options, have been proposed to assist dentists in the diagnosis and treatment planning of various dentomaxillofacial diseases, with performance similar or even superior to that of specialists. Notably, the impact of these dental AI applications on treatment decision, clinical and patient-reported outcomes, and cost-effectiveness has so far been assessed sparsely. Such information should be further investigated in future studies to provide patients, providers, and healthcare organizers a clearer picture of the true usefulness of AI in daily dental practice.

Artificial intelligence for sustainable oral healthcare

OBJECTIVES

Oral health is grounded in the United National (UN) 2030 Agenda for Sustainable Developement and its 17 Goals (SDGs), in particular SDG 3 (Ensure healthy lives and promote well-being for all at all ages). The World Health Organization (WHO) Global Strategy on Oral Health calls for prioritizing environmentally sustainable and less invasive oral health care, and planetary health. Artificial Intelligence (AI) has the potential to power the next generation of oral health services and care, however its relationship with the broader UN and WHO concepts of sustainability remains poorly defined and articulated. We review the double-edged relationships between AI and oral health, to suggest actions that promote a sustainable deployment of AI for oral health.

DATA

Concepts regarding AI, sustainability and sustainable development were identified and defined. A review of several double-edged relationship between AI and SDGs were exposed for the field of Oral Health.

SOURCES

Medline and international declarations of the WHO, the UN and the World Dental Federation (FDI) were screened.

STUDY SELECTION

One the one hand, AI may reduce transportation, optimize care delivery (SDG 3 "Good Health and Well-Being", SDG 13 "Climate Action"), and increase accessibility of services and reduce inequality (SDG 10 "Reduced Inequalities", SDG 4 "Quality Education"). On the other hand, the deployment, implementation and maintenance of AI require significant resources (SDG 12 "Responsible Consumption and Production"), and costs for AI may aggravate inequalities. Also, AI may be biased, reinforcing inequalities (SDG 10) and discrimination (SDG 5), and may violate principles of security, privacy and confidentiality of personal information (SDG 16).

CONCLUSIONS

Systematic assessment of the positive impact and adverse effects of AI on sustainable oral health may help to foster the former and curb the latter based on evidence.

CLINICAL SIGNIFICANCE

If sustainability imperatives are actively taken into consideration, the community of oral health professionals should then employ AI for improving effectiveness, efficiency, and safety of oral healthcare; strengthen oral health surveillance; foster education and accessibility of care; ensure fairness, transparency and governance of AI for oral health; develop legislation and infrastructure to expand the use of digital health technologies including AI.

Towards Trustworthy AI in Dentistry

Medical and dental artificial intelligence (AI) require the trust of both users and recipients of the AI to enhance implementation, acceptability, reach, and maintenance. Standardization is one strategy to generate such trust, with quality standards pushing for improvements in AI and reliable quality in a number of attributes. In the present brief review, we summarize ongoing activities from research and standardization that contribute to the trustworthiness of medical and, specifically, dental AI and discuss the role of standardization and some of its key elements. Furthermore, we discuss how explainable AI methods can support the development of trustworthy AI models in dentistry. In particular, we demonstrate the practical benefits of using explainable AI on the use case of caries prediction on near-infrared light transillumination images.

Analysis of Deep Learning Techniques for Dental Informatics: A Systematic Literature Review

Within the ever-growing healthcare industry, dental informatics is a burgeoning field of study. One of the major obstacles to the health care system’s transformation is obtaining knowledge and insightful data from complex, high-dimensional, and diverse sources. Modern biomedical research, for instance, has seen an increase in the use of complex, heterogeneous, poorly documented, and generally unstructured electronic health records, imaging, sensor data, and text. There were still certain restrictions even after many current techniques were used to extract more robust and useful elements from the data for analysis. New effective paradigms for building end-to-end learning models from complex data are provided by the most recent deep learning technology breakthroughs. Therefore, the current study aims to examine the most recent research on the use of deep learning techniques for dental informatics problems and recommend creating comprehensive and meaningful interpretable structures that might benefit the healthcare industry. We also draw attention to some drawbacks and the need for better technique development and provide new perspectives about this exciting new development in the field.

Deep Learning-Based Prediction of the 3D Postorthodontic Facial Changes

With the increase of the adult orthodontic population, there is a need for an accurate and evidence-based prediction of the posttreatment face in 3 dimensions (3D). The objectives of this study are 1) to develop a 3D postorthodontic face prediction method based on a deep learning network using the patient-specific factors and orthodontic treatment conditions and 2) to validate the accuracy and clinical usability of the proposed method. Paired sets (n = 268) of pretreatment (T1) and posttreatment (T2) cone-beam computed tomography (CBCT) of adult patients were trained with a conditional generative adversarial network to generate 3D posttreatment facial data based on the patient's gender, age, and the changes of upper (ΔU1) and lower incisor position (ΔL1) as input. The accuracy was calculated with prediction error and mean absolute distances between real T2 (T2) and predicted T2 (PT2) near 6 perioral landmark regions, as well as percentage of prediction error less than 2 mm using test sets (n = 44). For qualitative evaluation, an online survey was conducted with experienced orthodontists as panels (n = 56). Overall, PT2 indicated similar 3D changes to the T2 face, with the most apparent changes simulated in the perioral regions. The mean prediction error was 1.2 ± 1.01 mm with 80.8% accuracy. More than 50% of the experienced orthodontists were unable to distinguish between real and predicted images. In this study, we proposed a valid 3D postorthodontic face prediction method by applying a deep learning algorithm trained with CBCT data sets.

Dentistry and Interoperability

Information has become the vital commodity of exchange in recent decades. Medicine is no exception; the importance of patient information in the digital form has been recognized by organizations and health care facilities. Almost all patient information, including medical history, radiographs, and feedback, can be digitally recorded synchronously and asynchronously. Nevertheless, patient information that could be shared and reused to enhance care delivery is not readily available in a format that could be understood by the systems in recipient health care facilities. The systems used in medical and dental clinics today lack the ability to communicate with each other. The critical information is stagnant in isolated silos, unable to be shared, analyzed, and reused. In this article, we propose enabling interoperability in health care systems that could facilitate communication across systems for the benefit of patients and caregivers. We explain in this article the importance of interoperable data, the international interoperability standards available, and the range of benefits and opportunities that interoperability can create in dentistry for providers and patients alike.

Dental Research Data Availability and Quality According to the FAIR Principles

According to the FAIR principles, data produced by scientific research should be findable, accessible, interoperable, and reusable-for instance, to be used in machine learning algorithms. However, to date, there is no estimate of the quantity or quality of dental research data evaluated via the FAIR principles. We aimed to determine the availability of open data in dental research and to assess compliance with the FAIR principles (or FAIRness) of shared dental research data. We downloaded all available articles published in PubMed-indexed dental journals from 2016 to 2021 as open access from Europe PubMed Central. In addition, we took a random sample of 500 dental articles that were not open access through Europe PubMed Central. We assessed data sharing in the articles and compliance of shared data to the FAIR principles programmatically. Results showed that of 7,509 investigated articles, 112 (1.5%) shared data. The average (SD) level of compliance with the FAIR metrics was 32.6% (31.9%). The average for each metric was as follows: findability, 3.4 (2.7) of 7; accessibility, 1.0 (1.0) of 3; interoperability, 1.1 (1.2) of 4; and reusability, 2.4 (2.6) of 10. No considerable changes in data sharing or quality of shared data occurred over the years. Our findings indicated that dental researchers rarely shared data, and when they did share, the FAIR quality was suboptimal. Machine learning algorithms could understand 1% of available dental research data. These undermine the reproducibility of dental research and hinder gaining the knowledge that can be gleaned from machine learning algorithms and applications.

Self-Supervised Learning Methods for Label-Efficient Dental Caries Classification

High annotation costs are a substantial bottleneck in applying deep learning architectures to clinically relevant use cases, substantiating the need for algorithms to learn from unlabeled data. In this work, we propose employing self-supervised methods. To that end, we trained with three self-supervised algorithms on a large corpus of unlabeled dental images, which contained 38K bitewing radiographs (BWRs). We then applied the learned neural network representations on tooth-level dental caries classification, for which we utilized labels extracted from electronic health records (EHRs). Finally, a holdout test-set was established, which consisted of 343 BWRs and was annotated by three dental professionals and approved by a senior dentist. This test-set was used to evaluate the fine-tuned caries classification models. Our experimental results demonstrate the obtained gains by pretraining models using self-supervised algorithms. These include improved caries classification performance (6 p.p. increase in sensitivity) and, most importantly, improved label-efficiency. In other words, the resulting models can be fine-tuned using few labels (annotations). Our results show that using as few as 18 annotations can produce ≥45% sensitivity, which is comparable to human-level diagnostic performance. This study shows that self-supervision can provide gains in medical image analysis, particularly when obtaining labels is costly and expensive.

Automated detection of posterior restorations in permanent teeth using artificial intelligence on intraoral photographs

OBJECTIVES

Intraoral photographs might be considered the machine-readable equivalent of a clinical-based visual examination and can potentially be used to detect and categorize dental restorations. The first objective of this study was to develop a deep learning-based convolutional neural network (CNN) for automated detection and categorization of posterior composite, cement, amalgam, gold and ceramic restorations on clinical photographs. Second, this study aimed to determine the diagnostic accuracy for the developed CNN (test method) compared to that of an expert evaluation (reference standard).

METHODS

The whole image set of 1,761 images (483 of unrestored teeth, 570 of composite restorations, 213 of cements, 278 of amalgam restorations, 125 of gold restorations and 92 of ceramic restorations) was divided into a training set (N=1,407, 401, 447, 66, 231, 93, and 169, respectively) and a test set (N=354, 82, 123, 26, 47, 32, and 44). The expert diagnoses served as a reference standard for cyclic training and repeated evaluation of the CNN (ResNeXt-101-32x8d), which was trained by using image augmentation and transfer learning. Statistical analysis included the calculation of contingency tables, areas under the receiver operating characteristic curve and saliency maps.

RESULTS

After training was complete, the CNN was able to categorize restorations correctly with the following diagnostic accuracy values: 94.9% for unrestored teeth, 92.9% for composites, 98.3% for cements, 99.2% for amalgam restorations, 99.4% for gold restorations and 97.8% for ceramic restorations.

CONCLUSIONS

It was possible to categorize different types of posterior restorations on intraoral photographs automatically with a good diagnostic accuracy.

CLINICAL SIGNIFICANCE

Dental diagnostics might be supported by artificial intelligence-based algorithms in the future. However, further improvements are needed to increase accuracy and practicability.

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.

Augmented, Virtual and Mixed Reality in Dentistry: A Narrative Review on the Existing Platforms and Future Challenges

The recent advancements in digital technologies have led to exponential progress in dentistry. This narrative review aims to summarize the applications of Augmented Reality, Virtual Reality and Mixed Reality in dentistry and describes future challenges in digitalization, such as Artificial Intelligence and Robotics. Augmented Reality, Virtual Reality and Mixed Reality represent effective tools in the educational technology, as they can enhance students’ learning and clinical training. Augmented Reality and Virtual Reality and can also be useful aids during clinical practice. Augmented Reality can be used to add digital data to real life clinical data. Clinicians can apply Virtual Reality for a digital wax-up that provides a pre-visualization of the final post treatment result. In addition, both these technologies may also be employed to eradicate dental phobia in patients and further enhance patient’s education. Similarly, they can be used to enhance communication between the dentist, patient, and technician. Artificial Intelligence and Robotics can also improve clinical practice. Artificial Intelligence is currently developed to improve dental diagnosis and provide more precise prognoses of dental diseases, whereas Robotics may be used to assist in daily practice.