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.

Denture Plaque Biofilm Visual Assessment Methods: A Systematic Review.

Denture plaque, a biofilm that develops on denture surfaces, could contribute to many oral and systemic afflictions. Hence, a quantitative assessment of denture plaque is important to evaluate the denture hygiene of denture wearers, particularly to prevent plaque biofilm-associated diseases. The aim of this systematic review, therefore, was to review and summarize the visual denture hygiene assessment methods using denture plaque indices and with planimetries published in the literature. English language studies published up to March 2022 in four electronic databases, PubMed, Medline, Embase, and Cochrane Library, were searched, followed by a manual search of Google Scholar by two assessors. The review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) whenever possible. Details of the visual assessment methods, including the types of denture assessed, its materials and its surfaces, as well as the use of a disclosing agent, were the main outcomes. Of 492 screened studies, 74 were included per the inclusion and exclusion criteria. Of these, 60 studies utilized various denture plaque indices while 18 used planimetries. 43 out of 60 studies with indices and 17 out of 18 studies with planimetries used disclosing agents for visual evaluation of plaque. A total of 21 indices were described in the included studies, of which seven graded a divided denture surface, while the remainder graded entire denture surface. Of the 18 planimetric assessments, one study quantified squares of the disclosed plaques on denture images, 16 studies quantified such pixels with computer programs, and a single study quantified points, pixels, and contour of plaque areas. In summary, denture plaque indices appear to be popular in denture plaque assessment due to their simplicity. Computerized planimetric assessment, though more time-consuming, provides a more accurate assessment of plaque load as it is less prone to subjectivity and assessor errors.

Use of Digital Diagnostic Aids for Initial Caries Detection: A Review.

The advance in digital diagnostic technologies has significantly facilitated the detection of dental caries. Despite the increase in clinically available digital diagnostic aids for dental caries, there is yet to be a comprehensive summary of all available technology. This review aims to provide an overview of digital diagnostic aids for the clinical detection of dental caries, particularly those at an initial stage. Currently available digital diagnostic aids for caries detection can be classified into four categories according to the initial source of energy, including radiation-based aids, light-based aids, ultrasound-based aids, and electric-based aids. Radiation-based aids use ionizing radiation, normally X-ray, to produce images of dental structures. Radiation-based aids encompass digital bitewing radiography and cone beam computed tomography. Light-based aids employ light or laser to induce signals for the detection of the changes in the carious dental hard tissue. Common light-based aids include digital transillumination and light/laser-induced fluorescence. Ultrasound-based aids detect the signal of ultrasound waves to assess the acoustic impedance of the carious teeth. The ultrasound caries detector is an available ultrasound-based aid. Electric-based aids assess the changes in the electric current conductance or impedance of the teeth with caries. Available electric-based aids include electrical conductance measurement and alternating current impedance spectroscopy. Except for these clinically available digital diagnostic aids, many digital diagnostic aids for caries detection are still under development with promising results in laboratory settings.

Which clinical and laboratory procedures should be used to fabricate digital complete dentures? A systematic review.

STATEMENT OF PROBLEM: Digital workflows for digital complete denture fabrication have a variety of clinical and laboratory procedures, but their outcomes and associated complications are currently unknown. PURPOSE: The purpose of this systematic review was to evaluate the clinical and laboratory procedures for digital complete dentures, their outcomes, and associated complications. MATERIAL AND METHODS: Electronic literature searches were conducted on PubMed/Medline, Embase, and Web of Science for studies published from January 2000 to September 2022 and screened by 2 independent reviewers. Information on digital complete denture procedures, materials, their outcomes, and associated complications was extracted. RESULTS: Of 266 screened studies, 39 studies were included. While 26 assessed definitive complete dentures, 7 studies assessed denture bases, 2 assessed trial dentures, and 4 assessed the digital images only. Twenty-four studies used border molded impression technique, 3 studies used a facebow record, and 7 studies used gothic arch tracing. Only 13 studies performed trial denture placement. Twenty-one studies used milling, and 17 studies used 3D printing for denture fabrication. One study reported that the retention of maxillary denture bases fabricated from a border-molded impression (14.5 to 16.1 N) was statistically higher than the retention of those fabricated from intraoral scanning (6.2 to 6.6 N). The maximum occlusal force of digital complete denture wearers was similar across different fabrication procedures. When compared with the conventional workflow, digital complete dentures required statistically shorter clinical time with 205 to 233 minutes saved. Up to 37.5% of participants reported loss of retention and up to 31.3% required a denture remake. In general, ≥1 extra visit and 1 to 4 unscheduled follow-up visits were needed. The outcomes for patient satisfaction and oral health-related quality of life were similar between conventional, milled, and 3D-printed complete dentures. CONCLUSIONS: Making a border-molded impression is still preferred for better retention, and trial denture placement is still recommended to optimize the fabrication of definitive digital complete dentures.

A Systematic Review of the Use of mHealth in Oral Health Education among Older Adults.

Oral diseases are largely preventable. However, as the number of older adults is expected to increase, along with the high cost and various barriers to seeking continuous professional care, a sustainable approach is needed to assist older adults in maintaining their oral health. Mobile health (mHealth) technologies may facilitate oral disease prevention and management through oral health education. This review aims to provide an overview of existing evidence on using mHealth to promote oral health through education among older adults. A literature search was performed across five electronic databases. A total of five studies were identified, which provided low to moderate evidence to support using mHealth among older adults. The selected studies showed that mHealth could improve oral health management, oral health behavior, and oral health knowledge among older adults. However, more quality studies regarding using mHealth technologies in oral health management, oral health behavior, and oral health knowledge among older adults are needed.

Three-dimensional assessment of facial asymmetry in class III subjects, part 2: evaluating asymmetry index and asymmetry scores.

OBJECTIVES: To evaluate the outcomes of corrective surgical treatment for craniofacial asymmetry using four different methods with the aim of developing the best technique for craniofacial asymmetry assessment. MATERIALS AND METHODS: CBCT images of twenty-one class III subjects with surgically corrected craniofacial asymmetry and twenty-one matched controls were analyzed. Twenty-seven hard tissue landmarks were used to quantify asymmetry using the following methodologies: the asymmetry index (AI), asymmetry scores based on the clinically derived midline (CM), Procrustes analysis (PA), and modified Procrustes analysis (MPA). RESULTS: Modified Procrustes analysis successfully identified pre-operative asymmetry and revealed severe asymmetry at the mandibular regions compared to controls, which was comparable to the asymmetry index and clinically derived midline methods, while Procrustes analysis masked the asymmetric characteristics. Likewise, when comparing the post-surgical outcomes, modified Procrustes analysis not only efficiently determined the changes evidencing decrease in facial asymmetry but also revealed significant residual asymmetry in the mandible, which was congruent with the asymmetry index and clinically derived midline methods but contradictory to the results shown by Procrustes analysis. CONCLUSIONS: In terms of quantifying cranio-facial asymmetry, modified Procrustes analysis has evidenced to produce promising results that were comparable to the asymmetry index and the clinically derived midline, making it a more viable option for craniofacial asymmetry assessment. CLINICAL RELEVANCE: Modified Procrustes analysis is proficient in evaluating cranio-facial asymmetry with more valid clinical representation and has potential applications in assessing asymmetry in a wide spectrum of patients, including syndromic patients.

Comparison of the colour accuracy of a single-lens reflex camera and a smartphone camera in a clinical context.

OBJECTIVES: This study aimed to investigate the colour accuracy of digital photographs captured by a single-lens reflex (SLR) camera and a smartphone camera in a clinical setting. METHODS: Dentate subjects were recruited, and their maxillary anterior teeth were photographed along with a colour target and a dental shade guide. There were eight groups: Group 1: SLR camera with a 100 mm macro-lens and a ring-flash (SLRC); Group 2: SLRC with a polarizer; Group 3: SLRC with white-balance calibration; Group 4: SLRC with a polarizer and white-balance calibration. Groups 5 to 8 were similar to Groups 1 to 4, except a smartphone camera and an external light source (SC) were used. The CIE LAB coordinates of the colour target, shade guide, and centre of the maxillary right central incisor (tooth 11) in the digital photographs were retrieved. The colour difference ΔE=[(ΔL*)2+(Δa*)2+(Δb*)2]1/2 to the reference colour coordinates or the reading of the dental spectrophotometer was calculated. The results were analysed by the Kruskal-Wallis test at α=0.05 with Bonferroni correction. RESULTS: Thirty-nine subjects were photographed. SLRC with a polarizer showed the largest ΔE in this study (P<0.001). When capturing tooth 11, SLRC with calibrated white-balance resulted in the smallest ΔE in this study (P<0.001), and the use of a polarizer and/or calibrated white-balance did not result in a smaller ΔE than that of SC alone (P>0.001). CONCLUSION: Calibration for white-balance is recommended for the SLRC. The use of a polarizer does not show an improvement in colour accuracy. SC alone may be sufficient for intraoral photography. CLINICAL SIGNIFICANCE: When capturing intraoral photography using a single-lens reflex camera, it is recommended to calibrate the white-balance. The use of a polarizer does not significantly improve colour accuracy. However, a smartphone camera with an external light source can serve as a viable alternative.

Teledentistry from research to practice: a tale of nineteen countries.

Aim: The COVID-19 pandemic has accelerated teledentistry research with great interest reflected in the increasing number of publications. In many countries, teledentistry programs were established although not much is known about the extent of incorporating teledentistry into practice and healthcare systems. This study aimed to report on policies and strategies related to teledentistry practice as well as barriers and facilitators for this implementation in 19 countries. Methods: Data were presented per country about information and communication technology (ICT) infrastructure, income level, policies for health information system (HIS), eHealth and telemedicine. Researchers were selected based on their previous publications in teledentistry and were invited to report on the situation in their respective countries including Bosnia and Herzegovina, Canada, Chile, China, Egypt, Finland, France, Hong Kong SAR, Iran, Italy, Libya, Mexico, New Zealand, Nigeria, Qatar, Saudi Arabia, South Africa, United Kingdom, Zimbabwe. Results: Ten (52.6%) countries were high income, 11 (57.9%) had eHealth policies, 7 (36.8%) had HIS policies and 5 (26.3%) had telehealth policies. Six (31.6%) countries had policies or strategies for teledentistry and no teledentistry programs were reported in two countries. Teledentistry programs were incorporated into the healthcare systems at national (n = 5), intermediate (provincial) (n = 4) and local (n = 8) levels. These programs were established in three countries, piloted in 5 countries and informal in 9 countries. Conclusion: Despite the growth in teledentistry research during the COVID-19 pandemic, the use of teledentistry in daily clinical practice is still limited in most countries. Few countries have instituted teledentistry programs at national level. Laws, funding schemes and training are needed to support the incorporation of teledentistry into healthcare systems to institutionalize the practice of teledentistry. Mapping teledentistry practices in other countries and extending services to under-covered populations increases the benefit of teledentistry.

Incidence and outcomes of acute kidney injury including hepatorenal syndrome in hospitalized patients with cirrhosis in the US.

BACKGROUND & AIMS: Acute kidney injury (AKI) in cirrhosis is common and associated with high morbidity, but the incidence rates of different etiologies of AKI are not well described in the US. We compared incidence rates, practice patterns, and outcomes across etiologies of AKI in cirrhosis. METHODS: We performed a retrospective cohort study of 11 hospital networks, including consecutive adult patients admitted with AKI and cirrhosis in 2019. The etiology of AKI was adjudicated based on pre-specified clinical definitions (prerenal/hypovolemic AKI, hepatorenal syndrome [HRS-AKI], acute tubular necrosis [ATN], other). RESULTS: A total of 2,063 patients were included (median age 62 [IQR 54-69] years, 38.3% female, median MELD-Na score 26 [19-31]). The most common etiology was prerenal AKI (44.3%), followed by ATN (30.4%) and HRS-AKI (12.1%); 6.0% had other AKI, and 7.2% could not be classified. In our cohort, 8.1% of patients received a liver transplant and 36.5% died by 90 days. The lowest rate of death was observed in patients with prerenal AKI (22.2%; p <0.001), while death rates were higher but not significantly different from each other in those with HRS-AKI and ATN (49.0% vs. 52.7%; p = 0.42). Using prerenal AKI as a reference, the adjusted subdistribution hazard ratio (sHR) for 90-day mortality was higher for HRS-AKI (sHR 2.78; 95% CI 2.18-3.54; p <0.001) and ATN (sHR 2.83; 95% CI 2.36-3.41; p <0.001). In adjusted analysis, higher AKI stage and lack of complete response to treatment were associated with an increased risk of 90-day mortality (p <0.001 for all). CONCLUSION: AKI is a severe complication of cirrhosis. HRS-AKI is uncommon and is associated with similar outcomes to ATN. The etiology of AKI, AKI stage/severity, and non-response to treatment were associated with mortality. Further optimization of vasoconstrictors for HRS-AKI and supportive therapies for ATN are needed. IMPACT AND IMPLICATIONS: Acute kidney injury (AKI) in cirrhosis carries high morbidity, and management is determined by the etiology of injury. However, a large and well-adjudicated multicenter database from US centers that uses updated AKI definitions is lacking. Our findings demonstrate that acute tubular necrosis and hepatorenal syndrome have similar outcomes (∼50% mortality at 90 days), though hepatorenal syndrome is uncommon (12% of all AKI cases). These findings represent practice patterns at US transplant/tertiary centers and can be used as a baseline, presenting the situation prior to the adoption of terlipressin in the US.

A qualitative analysis of patient's lived experience on their treatment journey with nasopharyngeal carcinoma.

OBJECTIVE: To explore and analyse the perspective of patients undergoing and recovering from nasopharyngeal carcinoma (NPC) therapy. METHODS: Thirty-three NPC patients at different stages of treatment were enroled. Seven were actively undergoing treatment, 13 were immediately post-treatment, and 13 were long-term. Patients were interviewed using a structured questionnaire based on a review of the literature that covered different phases of their treatment journey. The interview was recorded and transcribed for qualitative data analysis using a thematic inductive-deductive approach. RESULTS: Three main domains embracing aspects of NPC patients' experiences were identified; side effects, psychosocial well-being, and the role and support of healthcare workers. Side effects were experienced orally, locally, and systemically. Oral side effects (oral mucositis, xerostomia, altered taste, dysphagia) were the most significant challenge experienced by NPC patients. Locally, skin injury (desquamation, fibrosis, darkening of the skin, erythema, pruritus, and swelling around the neck region) and hair loss, resolved after cessation of therapy. Systemic side effects from the treatment were related to general weakness, weight loss and nausea. The psychosocial well-being of NPC patients was influenced by a range of issues including support (healthcare workers and family), pain management, functional limitations, nutritional needs, perceived level of information, emotion, and finances. CONCLUSION: NPC patients were significantly impacted based on the diagnosis, treatment and recovery phase affecting them locally, systemically, and psychologically. The role of family and healthcare staff was also influential in the overall treatment experience, and they have key roles to play in facilitating patients along their treatment journey. CLINICAL SIGNIFICANCE: Oral and general side effects from NPC treatment have significant impact on patients physical and emotional well-being. It is important for healthcare providers to have insights of these so as to understand and support patients during their treatment journey and recovery and be able to empathetically facilitate their clinical management.

A novel glass ionomer cement with silver zeolite for restorative dentistry.

OBJECTIVE: To develop an antimicrobial silver zeolite glass ionomer cement (SZ-GIC) and determine its biocompatibility, physical, adhesive and antibacterial properties. METHODS: Silver nitrate and sodium zeolite were used to synthesize silver zeolite (SZ). SZ-GICs were prepared by incorporating SZ into GIC at 5% (SZ-GIC5), 2% (SZ-GIC2), or 1% (SZ-GIC1) by weight, respectively. The SZ-GICs were characterized by evaluating surface morphology, topography and elemental composition. SZ-GICs' biocompatibility was assessed by evaluating cell cytotoxicity. Their physical properties were determined by testing setting time, compressive strength, flexural strength, water sorption and solubility. Their adhesive property was assessed by evaluating micro-tensile bond strength. Their antibacterial properties were assessed by evaluating biofilm growth kinetic, metabolic activity, viability and morphology. GIC was used as a control. RESULTS: SZ was a three-dimensional crystalline mineral. SZ-GICs (including SZ-GIC 5, 2 and 1) showed similar surface morphology and topography to GIC. SZ-GIC1 and GIC had no difference in cell cytotoxicity (p>0.05). SZ-GICs and GIC showed no difference in setting time (p>0.05). SZ-GICs had higher compressive and flexural strength than GIC (p<0.05). SZ-GIC2 and SZ-GIC1 showed lower water sorption and solubility than GIC (p<0.05). SZ-GICs had higher micro-tensile bond strength than GIC (p<0.05). Biofilms on SZ-GICs' surfaces showed lower colony-forming units, decreased metabolic activities, higher percentages of dead cells and more ruptured bacterial cells compared with those on GIC. CONCLUSION: SZ-GIC with silver zeolite at 1% by weight are as biocompatible as conventional GIC. The SZ-GICs have enhanced physical, adhesive and antibacterial properties than GIC. CLINICAL SIGNIFICANCE: A silver zeolite glass ionomer cement was developed. The SZ-GICs have great potential for caries prevention and management.

Accuracy of Artificial Intelligence-Based Photographic Detection of Gingivitis.

OBJECTIVES: Gingivitis is one of the most prevalent plaque-initiated dental diseases globally. It is challenging to maintain satisfactory plaque control without continuous professional advice. Artificial intelligence may be used to provide automated visual plaque control advice based on intraoral photographs. METHODS: Frontal view intraoral photographs fulfilling selection criteria were collected. Along the gingival margin, the gingival conditions of individual sites were labelled as healthy, diseased, or questionable. Photographs were randomly assigned as training or validation datasets. Training datasets were input into a novel artificial intelligence system and its accuracy in detection of gingivitis including sensitivity, specificity, and mean intersection-over-union were analysed using validation dataset. The accuracy was reported according to STARD-2015 statement. RESULTS: A total of 567 intraoral photographs were collected and labelled, of which 80% were used for training and 20% for validation. Regarding training datasets, there were total 113,745,208 pixels with 9,270,413; 5,711,027; and 4,596,612 pixels were labelled as healthy, diseased, and questionable respectively. Regarding validation datasets, there were 28,319,607 pixels with 1,732,031; 1,866,104; and 1,116,493 pixels were labelled as healthy, diseased, and questionable, respectively. AI correctly predicted 1,114,623 healthy and 1,183,718 diseased pixels with sensitivity of 0.92 and specificity of 0.94. The mean intersection-over-union of the system was 0.60 and above the commonly accepted threshold of 0.50. CONCLUSIONS: Artificial intelligence could identify specific sites with and without gingival inflammation, with high sensitivity and high specificity that are on par with visual examination by human dentist. This system may be used for monitoring of the effectiveness of patients' plaque control.

Accuracy of artificial intelligence-designed single-molar dental prostheses: A feasibility study.

STATEMENT OF PROBLEM: Computer-aided design and computer-aided manufacturing (CAD-CAM) technology has greatly improved the efficiency of the fabrication of dental prostheses. However, the design process (CAD stage) is still time-consuming and labor intensive. PURPOSE: The purpose of this feasibility study was to investigate the accuracy of a novel artificial intelligence (AI) system in designing biomimetic single-molar dental prostheses by comparing and matching them to the natural molar teeth. MATERIAL AND METHODS: A total of 169 maxillary casts were obtained from healthy dentate participants. The casts were digitized, duplicated, and processed with the removal of the maxillary right first molar. A total of 159 pairs of original and processed casts were input into the Generative Adversarial Networks (GANs) for training. In validation, 10 sets of processed casts were input into the AI system, and 10 AI-designed teeth were generated through backpropagation. Individual AI-designed teeth were then superimposed onto each of the 10 original teeth, and the morphological differences in mean Hausdorff distance were measured. True reconstruction was defined as correct matching between the AI-designed and original teeth with the smallest mean Hausdorff distance. The ratio of true reconstruction was calculated as the Intersection-over-Union. The reconstruction performance of the AI system was determined by the Hausdorff distance and Intersection-over-Union. RESULTS: Data of validation showed that the mean Hausdorff distance ranged from 0.441 to 0.752 mm and the Intersection-over-Union of the system was 0.600 (60%). CONCLUSIONS: This study demonstrated the feasibility of AI in designing single-molar dental prostheses. With further training and optimization of algorithms, the accuracy of biomimetic AI-designed dental prostheses could be further enhanced.

Topical Agents for Nonrestorative Management of Dental Erosion: A Narrative Review.

A nonrestorative approach to the management of dental erosion is the foremost option: controlling dental erosion. The objectives of this study are to provide an overview and to summarise the effects and properties of topical anti-erosive agents as a nonrestorative treatment of dental erosion. A literature search was conducted on five databases of peer-reviewed literature-Cochrane Library, EMBASE, PubMed, Scopus and Web of Science-to recruit articles published between 1 January 2000 and 31 December 2021. The literature search identified 812 studies; 95 studies were included. Topical anti-erosive agents can be broadly categorised as fluorides, calcium phosphate-based agents, organic compounds and other anti-erosive agents. In the presence of saliva, fluorides promote the formation of fluorapatite on teeth through remineralisation. Calcium phosphate-based agents supply the necessary minerals that are lost due to the acid challenge of erosion. Some organic compounds and other anti-erosive agents prevent or control dental erosion by forming a protective layer on the tooth surface, by modifying salivary pellicle or by inhibiting the proteolytic activity of dentine collagenases. Topical anti-erosive agents are promising in managing dental erosion. However, current evidence shows inconsistent or limited results for supporting the use of these agents in clinical settings.

Microleakage assessment of CAD-CAM Cobalt-Chrome and Zirconia abutments on a conical connection dental implant: A comparative in vitro study.

OBJECTIVE: To assess the marginal and bacterial microleakage in zirconia and CAD-CAM or cast Co-Cr implant abutments. METHODS: Sixty-four conical connection implants with their respective abutments were divided into four groups (Co-Cr (milled, laser-sintered, and cast) and Zirconia (milled)). All specimens were subjected to a chewing simulation and thermocycling. After aging process, specimens were submerged in a 0.2% methylene blue solution with Porphyromonas gingivalis (P.g) for 48 h. The marginal microleakage was measured using a 40× optical microscopy at the internal part of the implant, and when positive microleakage was observed, a DNA isolation with a polymerase chain reaction (PCR) test was used. The microbiological assessment was based on colony forming units (CFUs). RESULTS: Thirty (47%) implant-abutments presented microleakage and the PCR was performed on those specimens (1 Zirconia, 1 Co-Cr milled, 14 Co-Cr laser-sintered and 14 cast). Seven specimens (1 Co-Cr laser-sintered and six cast) presented values below the PCR detection limit (< 100 CFUs). The lowest CFUs count occurred in the Co-Cr milled group (5.17E+02 CFUs/ml) followed by zirconia (7.70E+03 CFUs/ml). The Co-Cr cast (9.39E+03 CFUs/ml) and laser-sintered (2.4E+05 CFUs/ml) groups had higher bacterial count. The CFU count comparison performed between Co-Cr cast and laser-sintered resulted in a statistically significant differences in favor of Co-CrCL (p < .05). CONCLUSIONS: The abutment material and fabrication technique affected the implant-abutment microleakage. Although the CAD-CAM abutments presented favorable results, all tested groups presented microleakage.

Artificial intelligence-designed single molar dental prostheses: A protocol of prospective experimental study.

BACKGROUND: Dental prostheses, which aim to replace missing teeth and to restore patients' appearance and oral functions, should be biomimetic and thus adopt the occlusal morphology and three-dimensional (3D) position of healthy natural teeth. Since the teeth of an individual subject are controlled by the same set of genes (genotype) and are exposed to mostly identical oral environment (phenotype), the occlusal morphology and 3D position of teeth of an individual patient are inter-related. It is hypothesized that artificial intelligence (AI) can automate the design of single-tooth dental prostheses after learning the features of the remaining dentition. MATERIALS AND METHODS: This article describes the protocol of a prospective experimental study, which aims to train and to validate the AI system for design of single molar dental prostheses. Maxillary and mandibular dentate teeth models will be collected and digitized from at least 250 volunteers. The (original) digitized maxillary teeth models will be duplicated and processed by removal of right maxillary first molars (FDI tooth 16). Teeth models will be randomly divided into training and validation sets. At least 200 training sets of the original and the processed digitalized teeth models will be input into 3D Generative Adversarial Network (GAN) for training. Among the validation sets, tooth 16 will be generated by AI on 50 processed models and the morphology and 3D position of AI-generated tooth will be compared to that of the natural tooth in the original maxillary teeth model. The use of different GAN algorithms and the need of antagonist mandibular teeth model will be investigated. Results will be reported following the CONSORT-AI.

The cumulative effect of error in the digital workflow for complete-arch implant-supported frameworks: An in vitro study.

PURPOSE: To investigate the error accumulation and distribution through various stages of the digital workflow for complete-arch implant-supported framework fabrication. MATERIALS AND METHODS: A resin model of edentulous maxilla with 6 dental implants was scanned using an intraoral scanner for 10 times (Complete-digital group). Ten conventional gypsum casts were made and digitized by a laboratory scanner (Analogue-digital group). Five implant frameworks were designed and milled using CAD-CAM technique for each workflow. Inter-implant distances and angles of the resin model (reference) and frameworks were measured by a coordinate measuring machine, while the scans and virtual frameworks were examined by an inspection software. Effect of type of workflow and the individual stage on the accuracy of the frameworks were analysed by Two-way ANOVA. RESULTS: The expanded uncertainty of both workflows was ~150 µm and ~ 0.8°. The accuracy of the CAD stage was the highest. In the complete-digital workflow, the greatest distortion was found in the data acquisition stage, while in the analogue-digital workflow, it was found in the CAM stage. Compared with the analogue-digital group, the complete-digital group showed a significant higher precision in the first quadrant, but lower trueness in the second quadrant in data acquisition, and a significantly lower precision in the second quadrant at the CAD stage. CONCLUSIONS: Linear distortions of the complete-digital and analogue-digital workflows were clinically acceptable, while angular distortions were not. Distortions were generally derived from data acquisition and CAM stage. The CAD precision depended on the distortions derived from data acquisition. The complete-digital workflow was not as accurate as the analogue-digital in complete-arch implant rehabilitation.

Novel technical and privacy-preserving technology for artificial intelligence in ophthalmology.

PURPOSE OF REVIEW: The application of artificial intelligence (AI) in medicine and ophthalmology has experienced exponential breakthroughs in recent years in diagnosis, prognosis, and aiding clinical decision-making. The use of digital data has also heralded the need for privacy-preserving technology to protect patient confidentiality and to guard against threats such as adversarial attacks. Hence, this review aims to outline novel AI-based systems for ophthalmology use, privacy-preserving measures, potential challenges, and future directions of each. RECENT FINDINGS: Several key AI algorithms used to improve disease detection and outcomes include: Data-driven, imagedriven, natural language processing (NLP)-driven, genomics-driven, and multimodality algorithms. However, deep learning systems are susceptible to adversarial attacks, and use of data for training models is associated with privacy concerns. Several data protection methods address these concerns in the form of blockchain technology, federated learning, and generative adversarial networks. SUMMARY: AI-applications have vast potential to meet many eyecare needs, consequently reducing burden on scarce healthcare resources. A pertinent challenge would be to maintain data privacy and confidentiality while supporting AI endeavors, where data protection methods would need to rapidly evolve with AI technology needs. Ultimately, for AI to succeed in medicine and ophthalmology, a balance would need to be found between innovation and privacy.

Three-dimensional assessment of facial asymmetry in Class III subjects. Part 1: a retrospective study evaluating postsurgical outcomes.

OBJECTIVE: The present study aimed to determine the site and severity of maxillomandibular asymmetry before and after orthognathic surgery in asymmetric patients. MATERIALS AND METHODS: Presurgery and postsurgery cone beam computed tomography (CBCT) data of 21 facial asymmetry patients (7 males and 14 females, mean age: 23.0 ± 3.36 years) with soft tissue chin deviation ≥ 3 mm who had undergone bimaxillary surgery were evaluated. Seven midline and twenty bilateral hard tissue landmarks were identified for the evaluation of facial asymmetry and outcomes were assessed against age- and gender-matched control subjects. RESULTS: In the asymmetry group, bilateral landmarks exhibited significant deviation in the mandible and midface regions. Before surgery, asymmetry was more severe at the mandibular midline and sites close to it, in the asymmetry group. Bimaxillary surgery proved to be highly effective, with a significant correction of the menton to a clinically normal value (2.90 mm, p < 0.001). After surgery, significant residual asymmetry was observed at the mental foramen (p = 0.001) in the R-L direction. Moreover, significant asymmetry persisted at the sigmoid notch (p = 0.001) in the S-I direction. CONCLUSIONS: Mandibular midline landmarks and chin peripheral regions contribute significantly to overall facial asymmetry characteristics. Despite significant correction after bimaxillary surgery, asymmetry persisted at several sites, thereby requiring secondary correction. Comprehensive 3D presurgical planning is central for asymmetry correction in a single surgery. CLINICAL RELEVANCE: The present study specifies the location of residual asymmetry sites and advocates the correction of those sites during initial surgery.