Towards Trustworthy AI in Dentistry

Convolutional neural networks for accurate real-time diagnosis of oral epithelial dysplasia and oral squamous cell carcinoma using high-resolution in vivo confocal microscopy

Oral cancer detection is based on biopsy histopathology, however with digital microscopy imaging technology there is real potential for rapid multi-site imaging and simultaneous diagnostic analysis. Fifty-nine patients with oral mucosal abnormalities were imaged in vivo with a confocal laser endomicroscope using the contrast agents acriflavine and fluorescein for the detection of oral epithelial dysplasia and oral cancer. To analyse the 9168 images frames obtained, three tandem applied pre-trained Inception-V3 convolutional neural network (CNN) models were developed using transfer learning in the PyTorch framework. The first CNN was used to filter for image quality, followed by image specific diagnostic triage models for fluorescein and acriflavine, respectively. Images were categorised based on a histopathological diagnosis into 4 categories: no dysplasia, lichenoid lesions, low-grade dysplasia and high-grade dysplasia/oral squamous cell carcinoma (OSCC). The quality filtering model had an accuracy of 89.5%. The acriflavine diagnostic model performed well for identifying lichenoid (AUC = 0.94) and low-grade dysplasia (AUC = 0.91) but poorly for identifying no dysplasia (AUC = 0.44) or high-grade dysplasia/OSCC (AUC = 0.28). In contrast, the fluorescein diagnostic model had high classification performance for all diagnostic classes (AUC range = 0.90-0.96). These models had a rapid classification speed of less than 1/10th of a second per image. Our study suggests that tandem CNNs can provide highly accurate and rapid real-time diagnostic triage for in vivo assessment of high-risk oral mucosal disease.

Using AI in Optimizing Oral and Dental Diagnoses-A Narrative Review

Artificial intelligence (AI) is revolutionizing the field of oral and dental healthcare by offering innovative tools and techniques for optimizing diagnosis, treatment planning, and patient management. This narrative review explores the current applications of AI in dentistry, focusing on its role in enhancing diagnostic accuracy and efficiency. AI technologies, such as machine learning, deep learning, and computer vision, are increasingly being integrated into dental practice to analyze clinical images, identify pathological conditions, and predict disease progression. By utilizing AI algorithms, dental professionals can detect issues like caries, periodontal disease and oral cancer at an earlier stage, thus improving patient outcomes.

Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis

This systematic literature review examines state-of-the-art Explainable Artificial Intelligence (XAI) methods applied to medical image analysis, discussing current challenges and future research directions, and exploring evaluation metrics used to assess XAI approaches. With the growing efficiency of Machine Learning (ML) and Deep Learning (DL) in medical applications, there's a critical need for adoption in healthcare. However, their "black-box" nature, where decisions are made without clear explanations, hinders acceptance in clinical settings where decisions have significant medicolegal consequences. Our review highlights the advanced XAI methods, identifying how they address the need for transparency and trust in ML/DL decisions. We also outline the challenges faced by these methods and propose future research directions to improve XAI in healthcare. This paper aims to bridge the gap between cutting-edge computational techniques and their practical application in healthcare, nurturing a more transparent, trustworthy, and effective use of AI in medical settings. The insights guide both research and industry, promoting innovation and standardisation in XAI implementation in healthcare.

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.

Automatic detection and proximity quantification of inferior alveolar nerve and mandibular third molar on cone-beam computed tomography

OBJECTIVES

During mandibular third molar (MTM) extraction surgery, preoperative analysis to quantify the proximity of the MTM to the surrounding inferior alveolar nerve (IAN) is essential to minimize the risk of IAN injury. This study aims to propose an automated tool to quantitatively measure the proximity of IAN and MTM in cone-beam computed tomography (CBCT) images.

MATERIALS AND METHODS

Using the dataset including 302 CBCT scans with 546 MTMs, a deep-learning-based network was developed to support the automatic detection of the IAN, MTM, and intersection region IR. To ensure accurate proximity detection, a distance detection algorithm and a volume measurement algorithm were also developed.

RESULTS

The deep learning-based model showed encouraging segmentation accuracy of the target structures (Dice similarity coefficient: 0.9531 ± 0.0145, IAN; 0.9832 ± 0.0055, MTM; 0.8336 ± 0.0746, IR). In addition, with the application of the developed algorithms, the distance between the IAN and MTM and the volume of the IR could be equivalently detected (90% confidence interval (CI): - 0.0345-0.0014 mm, distance; - 0.0155-0.0759 mm3, volume). The total time for the IAN, MTM, and IR segmentation was 2.96 ± 0.11 s, while the accurate manual segmentation required 39.01 ± 5.89 min.

CONCLUSIONS

This study presented a novel, fast, and accurate model for the detection and proximity quantification of the IAN and MTM on CBCT.

CLINICAL RELEVANCE

This model illustrates that a deep learning network may assist surgeons in evaluating the risk of MTM extraction surgery by detecting the proximity of the IAN and MTM at a quantitative level that was previously unparalleled.

Can deep learning-designed anterior tooth-borne crown fulfill morphologic, aesthetic, and functional criteria in clinical practice?

OBJECTIVES

This study aimed to compare the design outcomes of anterior crowns generated using deep learning (DL)-based software with those fabricated by a technician using conventional dental computer-assisted design (CAD) software without DL support, with a focus on the evaluation of crown morphology, function, and aesthetics.

METHODS

Twenty-five in vivo datasets comprising maxillary and mandibular arch scans of prepared maxillary central incisors were utilized to design anterior crowns by using three methods: 1) a DL-based method resulting in as-generated outcome (DB), 2) a DL-based method further optimized by a technician (DM), and 3) a conventional CAD-based method (NC, control). Evaluations were conducted for crown morphology (total discrepancy volume (TDV), root mean square (RMS), positive average (PA) and negative average (NA) deviations), functional aspects (incisal path: deviations, length, and mean inclination), and aesthetics (crown width, height, width-to-height ratio, angular radius of mesioincisal line angle, proximal contact length, and tooth axis angle).

RESULTS

Significant differences in TDV ratio were noted between the DB-NC (32.3 ± 8.5 %) and DM-NC (26.5 ± 5.4 %) pairs (P = 0.006). No significant differences were observed in TDV between the DB-NC (65.3 ± 24.4 mm3) and DM-NC (54.3 ± 21.0 mm3) pairs (P = 0.095). For the entire palatal surface, significant differences in RMS and PA values were observed between the DB-NC and DM-NC pairs (P < 0.037). Significant differences in RMS values for the incisal half (P = 0.021) and in PA values for the cervical half (P = 0.047) of the palatal surface were also noted between these pairs. Significant differences in the deviation of the incisal path were observed between the DB-NC (290.4 ± 212.4 μm) and DM-NC (132.0 ± 122.3 μm) pairs (P < 0.001). However, no significant differences were found among the groups (DB, DM, and NC) in terms of the length and mean inclination of incisal paths or in aesthetic outcomes.

CONCLUSIONS

A DL-based method can result in promising outcomes with clinically acceptable morphology and aesthetics for anterior crowns. Minor deviations in incisal path of the crowns may lead to anterior guidance discrepancies, which can be corrected by the dental technician at the design stage.

CLINICAL SIGNIFICANCE

With the potential of DL-based design methods in dental applications, integrating AI technology into dental CAD workflow can enhance the clinical efficiency and consistency of anterior crown design, although human intervention may be required to refine functional aspect.

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

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

Deep learning-designed implant-supported posterior crowns: Assessing time efficiency, tooth morphology, emergence profile, occlusion, and proximal contacts

OBJECTIVES

To compare implant supported crowns (ISCs) designed using deep learning (DL) software with those designed by a technician using conventional computer-aided design software.

METHODS

Twenty resin-based partially edentulous casts (maxillary and mandibular) used for fabricating ISCs were evaluated retrospectively. ISCs were designed using a DL-based method with no modification of the as-generated outcome (DB), a DL-based method with further optimization by a dental technician (DM), and a conventional computer-aided design method by a technician (NC). Time efficiency, crown contour, occlusal table area, cusp angle, cusp height, emergence profile angle, occlusal contacts, and proximal contacts were compared among groups. Depending on the distribution of measured data, various statistical methods were used for comparative analyses with a significance level of 0.05.

RESULTS

ISCs in the DB group showed a significantly higher efficiency than those in the DM and NC groups (P ≤ 0.001). ISCs in the DM group exhibited significantly smaller volume deviations than those in the DB group when superimposed on ISCs in the NC group (DB-NC vs. DM-NC pairs, P ≤ 0.008). Except for the number and intensity of occlusal contacts (P ≤ 0.004), ISCs in the DB and DM groups had occlusal table areas, cusp angles, cusp heights, proximal contact intensities, and emergence profile angles similar to those in the NC group (P ≥ 0.157).

CONCLUSIONS

A DL-based method can be beneficial for designing posterior ISCs in terms of time efficiency, occlusal table area, cusp angle, cusp height, proximal contact, and emergence profile, similar to the conventional human-based method.

CLINICAL SIGNIFICANCE

A deep learning-based design method can achieve clinically acceptable functional properties of posterior ISCs. However, further optimization by a technician could improve specific outcomes, such as the crown contour or emergence profile angle.

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.

Revolutionizing CAD/CAM-based restorative dental processes and materials with artificial intelligence: a concise narrative review

Artificial intelligence (AI) is increasingly prevalent in biomedical and industrial development, capturing the interest of dental professionals and patients. Its potential to improve the accuracy and speed of dental procedures is set to revolutionize dental care. The use of AI in computer-aided design/computer-aided manufacturing (CAD/CAM) within the restorative dental and material science fields offers numerous benefits, providing a new dimension to these practices. This study aims to provide a concise overview of the implementation of AI-powered technologies in CAD/CAM restorative dental procedures and materials. A comprehensive literature search was conducted using keywords from 2000 to 2023 to obtain pertinent information. This method was implemented to guarantee a thorough investigation of the subject matter. Keywords included; "Artificial Intelligence", "Machine Learning", "Neural Networks", "Virtual Reality", "Digital Dentistry", "CAD/CAM", and "Restorative Dentistry". Artificial intelligence in digital restorative dentistry has proven to be highly beneficial in various dental CAD/CAM applications. It helps in automating and incorporating esthetic factors, occlusal schemes, and previous practitioners' CAD choices in fabricating dental restorations. AI can also predict the debonding risk of CAD/CAM restorations and the compositional effects on the mechanical properties of its materials. Continuous enhancements are being made to overcome its limitations and open new possibilities for future developments in this field.

The association between dental and dentoalveolar arch forms of children with normal occlusion and malocclusion: a cross-sectional study

BACKGROUND

Symmetrical and coordinated dental and alveolar arches are crucial for achieving proper occlusion. This study aimed to explore the association between dental and dentoalveolar arch forms in children with both normal occlusion and malocclusion.

METHODS

209 normal occlusion subjects (5-13 years, mean 8.48 years) and 199 malocclusion subjects (5-12 years, mean 8.19 years) were included. The dentoalveolar arch form was characterized by the smoothest projected curve representing the layered contour of the buccal alveolar bone, referred to as the LiLo curve. Subsequently, a polynomial function was utilized to assess dental and dentoalveolar arch forms. To facilitate separate analyses of shape (depth/width ratio) and size (depth and width), the widths of dental and dentoalveolar arch forms were normalized. The normalized dental and dentoalveolar arch forms (shapes) were further classified into 6 groups, termed dental/dentoalveolar arch clusters, using the k-means algorithm.

RESULTS

The association between dental and dentoalveolar arch clusters was found to be one-to-many rather than one-to-one. The mismatch between dental and dentoalveolar arch forms is common in malocclusion, affecting 11.4% of the maxilla and 9.2% of the mandible, respectively.

CONCLUSIONS

There are large individual variations in the association between dental and dentoalveolar arch forms. Early orthodontic treatment may play an active role in coordinating the relationship between the dental and dentoalveolar arch forms.

Research and application of artificial intelligence in dentistry from lower-middle income countries - a scoping review

Artificial intelligence (AI) has been integrated into dentistry for improvement of current dental practice. While many studies have explored the utilization of AI in various fields, the potential of AI in dentistry, particularly in low-middle income countries (LMICs) remains understudied. This scoping review aimed to study the existing literature on the applications of artificial intelligence in dentistry in low-middle income countries. A comprehensive search strategy was applied utilizing three major databases: PubMed, Scopus, and EBSCO Dentistry & Oral Sciences Source. The search strategy included keywords related to AI, Dentistry, and LMICs. The initial search yielded a total of 1587, out of which 25 articles were included in this review. Our findings demonstrated that limited studies have been carried out in LMICs in terms of AI and dentistry. Most of the studies were related to Orthodontics. In addition gaps in literature were noted such as cost utility and patient experience were not mentioned in the included studies.

Natural Language Processing: Chances and Challenges in Dentistry

INTRODUCTION

Natural language processing (NLP) is an intersection between Computer Science and Linguistic which aims to enable machines to process and understand human language. We here summarized applications and limitations of NLP in dentistry.

DATA AND SOURCES

Narrative review.

FINDINGS

NLP has evolved increasingly fast. For the dental domain, relevant NLP applications are text classification (e.g., symptom classification) and natural language generation and understanding (e.g., clinical chatbots assisting professionals in office work and patient communication). Analyzing large quantities of text will allow understanding diseases and their trajectories and support a more precise and personalized care. Speech recognition systems may serve as virtual assistants and facilitate automated documentation. However, to date, NLP has rarely been applied in dentistry. Existing research focuses mainly on rule-based solutions for narrow tasks. Technologies such as Recurrent Neural Networks and Transformers have been shown to surpass the language processing capabilities of such rule-based solutions in many fields, but are data-hungry (i.e., rely on large amounts of training data), which limits their application in the dental domain at present. Technologies such as federated or transfer learning or data sharing concepts may allow to overcome this limitation, while challenges in terms of explainability, reproducibility, generalizability and evaluation of NLP in dentistry remain to be resolved for enabling approval of such technologies in medical devices and services.

CONCLUSIONS

NLP will become a cornerstone of a number of applications in dentistry. The community is called to action to improve the current limitations and foster reliable, high-quality dental NLP.

CLINICAL SIGNIFICANCE

NLP for text classification (e.g., dental symptom classification) and language generation and understanding (e.g., clinical chatbots, speech recognition) will support administrative tasks in dentistry, provide deeper insights for clinicians and support research and education.

[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.

Preinterventional Third-Molar Assessment Using Robust Machine Learning

Machine learning (ML) models, especially deep neural networks, are increasingly being used for the analysis of medical images and as a supporting tool for clinical decision-making. In this study, we propose an artificial intelligence system to facilitate dental decision-making for the removal of mandibular third molars (M3M) based on 2-dimensional orthopantograms and the risk assessment of such a procedure. A total of 4,516 panoramic radiographic images collected at the Center of Dental Medicine at the University of Zurich, Switzerland, were used for training the ML model. After image preparation and preprocessing, a spatially dependent U-Net was employed to detect and retrieve the region of the M3M and inferior alveolar nerve (IAN). Image patches identified to contain a M3M were automatically processed by a deep neural network for the classification of M3M superimposition over the IAN (task 1) and M3M root development (task 2). A control evaluation set of 120 images, collected from a different data source than the training data and labeled by 5 dental practitioners, was leveraged to reliably evaluate model performance. By 10-fold cross-validation, we achieved accuracy values of 0.94 and 0.93 for the M3M-IAN superimposition task and the M3M root development task, respectively, and accuracies of 0.9 and 0.87 when evaluated on the control data set, using a ResNet-101 trained in a semisupervised fashion. Matthew's correlation coefficient values of 0.82 and 0.75 for task 1 and task 2, evaluated on the control data set, indicate robust generalization of our model. Depending on the different label combinations of task 1 and task 2, we propose a diagnostic table that suggests whether additional imaging via 3-dimensional cone beam tomography is advisable. Ultimately, computer-aided decision-making tools benefit clinical practice by enabling efficient and risk-reduced decision-making and by supporting less experienced practitioners before the surgical removal of the M3M.

Current Progress and Challenges of Using Artificial Intelligence in Clinical Dentistry-A Narrative Review

The concept of machines learning and acting like humans is what is meant by the phrase "artificial intelligence" (AI). Several branches of dentistry are increasingly relying on artificial intelligence (AI) tools. The literature usually focuses on AI models. These AI models have been used to detect and diagnose a wide range of conditions, including, but not limited to, dental caries, vertical root fractures, apical lesions, diseases of the salivary glands, maxillary sinusitis, maxillofacial cysts, cervical lymph node metastasis, osteoporosis, cancerous lesions, alveolar bone loss, the need for orthodontic extractions or treatments, cephalometric analysis, age and gender determination, and more. The primary contemporary applications of AI in the dental field are in undergraduate teaching and research. Before these methods can be used in everyday dentistry, however, the underlying technology and user interfaces need to be refined.

The use of artificial intelligence to aid in oral hygiene education: A scoping review

OBJECTIVES

Artificial intelligence (AI) has the potential to aid in constant, non-invasive monitoring of daily oral hygiene practices, potentially on behalf of a dentist or healthcare provider. This review summarises the evidence around the use of AI in the context of oral hygiene education.

DATA & SOURCES

This scoping review was developed according to the Joanna Briggs Institute scoping review protocol guidelines and the PRISMA-ScR guidelines. Publications that involved the use of AI for oral hygiene education in any population and setting were included. A systematic electronic database search (MEDLINE via PubMed, EMBASE, Web of Science, Scopus, Cochrane Library, and IEEE Xplore, arXiv, Proquest, Google Scholar, ClinicalTrials.gov, and PROSPERO) up to, and including 4 February 2023 was carried out. Citation searching from the full-text of included publications was also performed.

RESULTS

Of the 3215 publications screened, 20 were selected for qualitative synthesis. These were broadly divided into two categories of AI-assisted feedback: (1) synchronous and (2) asynchronous monitoring. There is a lack of high-quality studies, scarce reflection on possible ethical concerns on AI, and of studies comparing qualitative feedback to quantitative clinical outcomes with a control. Barriers to adoption of AI technologies, patient privacy, and specific areas for improvement were identified.

CONCLUSION

Within the limitations of this study, the use of AI to modify oral hygiene behaviour is promising. Further work is required in generating higher quality intra-oral images for dental biofilm detection, and in developing more personalised feedback for users.

CLINICAL SIGNIFICANCE

This is the first review to map out the available literature on AI in providing oral hygiene education. It may be useful to dental researchers in appraising AI-assisted technologies in the context of oral health.

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.

Classification of Maxillofacial Morphology by Artificial Intelligence Using Cephalometric Analysis Measurements

The characteristics of maxillofacial morphology play a major role in orthodontic diagnosis and treatment planning. While Sassouni's classification scheme outlines different categories of maxillofacial morphology, there is no standardized approach to assigning these classifications to patients. This study aimed to create an artificial intelligence (AI) model that uses cephalometric analysis measurements to accurately classify maxillofacial morphology, allowing for the standardization of maxillofacial morphology classification. This study used the initial cephalograms of 220 patients aged 18 years or older. Three orthodontists classified the maxillofacial morphologies of 220 patients using eight measurements as the accurate classification. Using these eight cephalometric measurement points and the subject's gender as input features, a random forest classifier from the Python sci-kit learning package was trained and tested with a k-fold split of five to determine orthodontic classification; distinct models were created for horizontal-only, vertical-only, and combined maxillofacial morphology classification. The accuracy of the combined facial classification was 0.823 ± 0.060; for anteroposterior-only classification, the accuracy was 0.986 ± 0.011; and for the vertical-only classification, the accuracy was 0.850 ± 0.037. ANB angle had the greatest feature importance at 0.3519. The AI model created in this study accurately classified maxillofacial morphology, but it can be further improved with more learning data input.

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.

Machine Learning in Predicting Tooth Loss: A Systematic Review and Risk of Bias Assessment

Predicting tooth loss is a persistent clinical challenge in the 21st century. While an emerging field in dentistry, computational solutions that employ machine learning are promising for enhancing clinical outcomes, including the chairside prognostication of tooth loss. We aimed to evaluate the risk of bias in prognostic prediction models of tooth loss that use machine learning. To do this, literature was searched in two electronic databases (MEDLINE via PubMed; Google Scholar) for studies that reported the accuracy or area under the curve (AUC) of prediction models. AUC measures the entire two-dimensional area underneath the entire receiver operating characteristic (ROC) curves. AUC provides an aggregate measure of performance across all possible classification thresholds. Although both development and validation were included in this review, studies that did not assess the accuracy or validation of boosting models (AdaBoosting, Gradient-boosting decision tree, XGBoost, LightGBM, CatBoost) were excluded. Five studies met criteria for inclusion and revealed high accuracy; however, models displayed a high risk of bias. Importantly, patient-level assessments combined with socioeconomic predictors performed better than clinical predictors alone. While there are current limitations, machine-learning-assisted models for tooth loss may enhance prognostication accuracy in combination with clinical and patient metadata in the future.