The term “artificial intelligence” (AI) refers to the idea of machines being capable of performing human tasks. A subdomain of AI is machine learning (ML), which “learns” intrinsic statistical patterns in data to eventually cast predictions on unseen data. Deep learning is a ML technique using multi-layer mathematical operations for learning and inferring on complex data like imagery. This succinct narrative review describes the application, limitations and possible future of AI-based dental diagnostics, treatment planning, and conduct, for example, image analysis, prediction making, record keeping, as well as dental research and discovery. AI-based applications will streamline care, relieving the dental workforce from laborious routine tasks, increasing health at lower costs for a broader population, and eventually facilitate personalized, predictive, preventive, and participatory dentistry. However, AI solutions have not by large entered routine dental practice, mainly due to 1) limited data availability, accessibility, structure, and comprehensiveness, 2) lacking methodological rigor and standards in their development, 3) and practical questions around the value and usefulness of these solutions, but also ethics and responsibility. Any AI application in dentistry should demonstrate tangible value by, for example, improving access to and quality of care, increasing efficiency and safety of services, empowering and enabling patients, supporting medical research, or increasing sustainability. Individual privacy, rights, and autonomy need to be put front and center; a shift from centralized to distributed/federated learning may address this while improving scalability and robustness. Lastly, trustworthiness into, and generalizability of, dental AI solutions need to be guaranteed; the implementation of continuous human oversight and standards grounded in evidence-based dentistry should be expected. Methods to visualize, interpret, and explain the logic behind AI solutions will contribute (“explainable AI”). Dental education will need to accompany the introduction of clinical AI solutions by fostering digital literacy in the future dental workforce.

Government and nongovernmental organizations need national and global estimates on the descriptive epidemiology of common oral conditions for policy planning and evaluation. The aim of this component of the Global Burden of Disease study was to produce estimates on prevalence, incidence, and years lived with disability for oral conditions from 1990 to 2017 by sex, age, and countries. In addition, this study reports the global socioeconomic pattern in burden of oral conditions by the standard World Bank classification of economies as well as the Global Burden of Disease Socio-demographic Index. The findings show that oral conditions remain a substantial population health challenge. Globally, there were 3.5 billion cases (95% uncertainty interval [95% UI], 3.2 to 3.7 billion) of oral conditions, of which 2.3 billion (95% UI, 2.1 to 2.5 billion) had untreated caries in permanent teeth, 796 million (95% UI, 671 to 930 million) had severe periodontitis, 532 million (95% UI, 443 to 622 million) had untreated caries in deciduous teeth, 267 million (95% UI, 235 to 300 million) had total tooth loss, and 139 million (95% UI, 133 to 146 million) had other oral conditions in 2017. Several patterns emerged when the World Bank’s classification of economies and the Socio-demographic Index were used as indicators of economic development. In general, more economically developed countries have the lowest burden of untreated dental caries and severe periodontitis and the highest burden of total tooth loss. The findings offer an opportunity for policy makers to identify successful oral health strategies and strengthen them; introduce and monitor different approaches where oral diseases are increasing; plan integration of oral health in the agenda for prevention of noncommunicable diseases; and estimate the cost of providing universal coverage for dental care.

Dental caries is the most prevalent disease worldwide, with the majority of caries lesions being concentrated in few, often disadvantaged social groups. We aimed to systematically assess current evidence for the association between socioeconomic position (SEP) and caries. We included studies investigating the association between social position (determined by own or parental educational or occupational background, or income) and caries prevalence, experience, or incidence. Risk of bias was assessed using the Newcastle-Ottawa Scale for observational studies. Reported differences between the lowest and highest SEP were assessed and data not missing at random imputed. Random-effects inverse-generic meta-analyses were performed, and subgroup and meta-regression analyses were used to control for possible confounding. Publication bias was assessed via funnel plot analysis and the Egger test. From 5539 screened records, 155 studies with mostly low or moderate quality evaluating a total of 329,798 individuals were included. Studies used various designs, SEP measures, and outcome parameters. Eighty-three studies found at least one measure of caries to be significantly higher in low-SEP compared with high-SEP individuals, while only 3 studies found the opposite. The odds of having any caries lesions or caries experience (decayed missing filled teeth [DMFT]/dmft > 0) were significantly greater in those with low own or parental educational or occupational background or income (between odds ratio [95% confidence interval] = 1.21 [1.03–1.41] and 1.48 [1.34–1.63]. The association between low educational background and having DMFT/dmft > 0 was significantly increased in highly developed countries ( R² = 1.32 [0.53–2.13]. Publication bias was present but did not significantly affect our estimates. Due to risk of bias in included studies, the available evidence was graded as low or very low. Low SEP is associated with a higher risk of having caries lesions or experience. This association might be stronger in developed countries. Established diagnostic and treatment concepts might not account for the unequal distribution of caries (registered with PROSPERO [CRD42013005947]).

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

We applied deep convolutional neural networks (CNNs) to detect periodontal bone loss (PBL) on panoramic dental radiographs. We synthesized a set of 2001 image segments from panoramic radiographs. Our reference test was the measured % of PBL. A deep feed-forward CNN was trained and validated via 10-times repeated group shuffling. Model architectures and hyperparameters were tuned using grid search. The final model was a seven-layer deep neural network, parameterized by a total number of 4,299,651 weights. For comparison, six dentists assessed the image segments for PBL. Averaged over 10 validation folds the mean (SD) classification accuracy of the CNN was 0.81 (0.02). Mean (SD) sensitivity and specificity were 0.81 (0.04), 0.81 (0.05), respectively. The mean (SD) accuracy of the dentists was 0.76 (0.06), but the CNN was not statistically significant superior compared to the examiners (p = 0.067/t-test). Mean sensitivity and specificity of the dentists was 0.92 (0.02) and 0.63 (0.14), respectively. A CNN trained on a limited amount of radiographic image segments showed at least similar discrimination ability as dentists for assessing PBL on panoramic radiographs. Dentists’ diagnostic efforts when using radiographs may be reduced by applying machine-learning based technologies.