Deep learning and explainable artificial intelligence for investigating dental professionals' satisfaction with CAD software performance.

PURPOSE: This study aimed to examine the satisfaction of dental professionals, including dental students, dentists, and dental technicians, with computer-aided design (CAD) software performance using deep learning (DL) and explainable artificial intelligence (XAI)-based behavioral analysis concepts. MATERIALS AND METHODS: This study involved 436 dental professionals with diverse CAD experiences to assess their satisfaction with various dental CAD software programs. Through exploratory factor analysis, latent factors affecting user satisfaction were extracted from the observed variables. A multilayer perceptron artificial neural network (MLP-ANN) model was developed along with permutation feature importance analysis (PFIA) and the Shapley additive explanation (Shapley) method to gain XAI-based insights into individual factors' significance and contributions. RESULTS: The MLP-ANN model outperformed a standard logistic linear regression model, demonstrating high accuracy (95%), precision (84%), and recall rates (84%) in capturing complex psychological problems related to human attitudes. PFIA revealed that design adjustability was the most important factor impacting dental CAD software users' satisfaction. XAI analysis highlighted the positive impacts of features supporting the finish line and crown design, while the number of design steps and installation time had negative impacts. Notably, finish-line design-related features and the number of design steps emerged as the most significant factors. CONCLUSIONS: This study sheds light on the factors influencing dental professionals' decisions in using and selecting CAD software. This approach can serve as a proof-of-concept for applying DL-XAI-based behavioral analysis in dentistry and medicine, facilitating informed software selection and development.

What comes first: teeth or face? Recommendations for an interdisciplinary collaboration between facial esthetic surgery and dentistry.

OBJECTIVE: The aim of the present study was to provide recommendations in order to facilitate communication between dental professionals and surgeons who are collaborating in the field of dentofacial esthetics. CLINICAL CONSIDERATIONS: Smile esthetics are beyond the scope, both of the surgeons who are collaborating with facial esthetics and of the dentists, as a wide range of treatment options from both sides is available. It can be difficult for the surgeon or the dentist that first comes in contact with the patient to conduct an individualized global treatment plan, in order to find out how the various phases of the treatment can be sequenced, as a workflow for an efficient interaction between facial surgery and dentistry still does not exist in the scientific literature. CONCLUSIONS: Facial cosmetic procedures and dental treatment have to be planned as individual elements of the whole dentofacial esthetic rehabilitation. The treatment has to be initiated with the design of the smile and the intraoral mock-up, followed by the required surgical interventions, and to be finished with the delivery of the definitive dental restoration. CLINICAL SIGNIFICANCE: Dentofacial esthetics require comprehensive communication between surgeons and dentists. Following the proposed recommendations, an individualized interdisciplinary treatment plan can be conducted, defining the role of each specialty.

Accuracy of manual and artificial intelligence-based superimposition of cone-beam computed tomography with digital scan data, utilizing an implant planning software: A randomized clinical study.

OBJECTIVES: To investigate the accuracy of conventional and automatic artificial intelligence (AI)-based registration of cone-beam computed tomography (CBCT) with intraoral scans and to evaluate the impact of user's experience, restoration artifact, number of missing teeth, and free-ended edentulous area. MATERIALS AND METHODS: Three initial registrations were performed for each of the 150 randomly selected patients, in an implant planning software: one from an experienced user, one from an inexperienced operator, and one from a randomly selected post-graduate student of implant dentistry. Six more registrations were performed for each dataset by the experienced clinician: implementing a manual or an automatic refinement, selecting 3 small or 3 large in-diameter surface areas and using multiple small or multiple large in-diameter surface areas. Finally, an automatic AI-driven registration was performed, using the AI tools that were integrated into the utilized implant planning software. The accuracy between each type of registration was measured using linear measurements between anatomical landmarks in metrology software. RESULTS: Fully automatic-based AI registration was not significantly different from the conventional methods tested for patients without restorations. In the presence of multiple restoration artifacts, user's experience was important for an accurate registration. Registrations' accuracy was affected by the number of free-ended edentulous areas, but not by the absolute number of missing teeth (p < .0083). CONCLUSIONS: In the absence of imaging artifacts, automated AI-based registration of CBCT data and model scan data can be as accurate as conventional superimposition methods. The number and size of selected superimposition areas should be individually chosen depending on each clinical situation.

Accuracy of artificial intelligence-based segmentation of the mandibular canal in CBCT.

OBJECTIVES: To investigate the accuracy of artificial intelligence (AI)-based segmentation of the mandibular canal, compared to the conventional manual tracing, implementing implant planning software. MATERIALS AND METHODS: Localization of the mandibular canals was performed for 104 randomly selected patients. A localization was performed by three experienced clinicians in order to serve as control. Five tracings were performed: One from a clinician with a moderate experience with a manual tracing (I1), followed by the implementation of an automatic refinement (I2), one manual from a dental student (S1), and one from the experienced clinician, followed by an automatic refinement (E). Subsequently, two fully automatic AI-driven segmentations were performed (A1,A2). The accuracy between each method was measured using root mean square error calculation. RESULTS: The discrepancy among the models of the mandibular canals, between the experienced clinicians and each investigated method ranged from 0.21 to 7.65 mm with a mean of 3.5 mm RMS error. The analysis of each separate mandibular canal's section revealed that mean RMS error was higher in the posterior and anterior loop compared to the middle section. Regarding time efficiency, tracing by experienced users required more time compared to AI-driven segmentation. CONCLUSIONS: The experience of the clinician had a significant influence on the accuracy of mandibular canal's localization. An AI-driven segmentation of the mandibular canal constitutes a time-efficient and reliable procedure for pre-operative implant planning. Nevertheless, AI-based segmentation results should always be verified, as a subsequent manual refinement of the initial segmentation may be required to avoid clinical significant errors.

Ceramic Implant Rehabilitation: Consensus Statements from Joint Congress for Ceramic Implantology.

The objectives of the study group focused on the following main topics related to the performance of one- and two-piece ceramic implants: defining bone-implant-contact percentages and its measurement methods, evaluating the pink esthetic score as an esthetic outcome parameter after immediate implantation, recognizing the different results of ceramic implant designs, as redefined by the German Association of Oral Implantology, incorporating the patient report outcome measure to include satisfaction and improvement in oral health-related quality of life, and conducting preclinical studies to address existing gaps in ceramic implants. During the Joint Congress for Ceramic Implantology (2022), the study group evaluated 17 clinical trials published between 2015 and 2021. After extensive discussions and multiple closed sessions, consensus statements and recommendations were developed, incorporating all approved modifications. A one-piece implant design features a coronal part that is fused to the implant body or interfaces with the post-abutment restoration platform, undergoing transmucosal healing. Long-term evaluations of this implant design have been supported by established favorable clinical evidence. Inaccuracies in the pink esthetic score and bone-implant-contact percentages were managed by establishing control groups for preclinical studies and randomizing clinical trials. The patient-reported outcome measures were adjusted to include an individual visual analog scale, collected from each clinical study, that quantified improved oral health and quality of life. Preclinical investigations should focus on examining the spread of ceramic debris and the impact of heat generation on tissue and cellular levels during drilling. Further technical advancements should prioritize wound management and developing safe drilling protocols.

Impact of scanning distance on the accuracy of a photogrammetry system.

PURPOSE: To measure the impact of the scanning distance on the accuracy of complete-arch implant scans acquired by using a photogrammetry (PG) system. MATERIAL AND METHODS: An edentulous cast with 6 implant abutment analogs was obtained. A brand new implant scan body was positioned on each implant abutment and digitized using an extraoral scanner (T710; Medit) and the reference file was obtained. Three groups were created based on the scanning distance used to acquire complete-arch implant scans by using a PG (PIC System; PIC Dental): 20 (20 group), 30 (30 group), and 35 cm (35 group). An optical marker (PIC Transfer, HC MUA Metal; PIC Dental) was placed on each implant abutment and a total of thirty scans per group were acquired. Euclidean linear and angular measurements were obtained on the reference file was obtained and used to compare the discrepancies with the same measurements obtained on each experimental scan. One-way ANOVA and Tukey tests were used to analyze trueness. The Levene test was used to analyze the precision values (α = 0.05). RESULTS: Significant linear (P < .001) and angular trueness (P < .001) discrepancies were found among the groups. For linear trueness, Tukey test showed that the 20 and 30 groups (P < .001) and 30 and 35 groups were different (P < .001). For angular trueness, the Tukey test revealed that 20 and 30 groups (P = .003), 20 and 35 (P < .001), and 30 and 35 groups were different (P < .001) The Levene test showed no significant linear precision (P = .197) and angular discrepancies (P = .229) among the groups. CONCLUSIONS: The scanning distance influenced the trueness of complete-arch implant scans obtained with the PG method tested. The maximum linear trueness mean discrepancy among the groups tested was 10 µm and the maximum angular trueness mean discrepancy among the groups tested was 0.02 .

Performance of an Artificial Intelligence-Based Chatbot (ChatGPT) Answering the European Certification in Implant Dentistry Exam.

PURPOSE: To compare the performance of licensed dentists and two software versions (3.5 legacy and 4.0) of an artificial intelligence (AI)-based chatbot (ChatGPT) answering the exam for the 2022 Certification in Implant Dentistry of the European Association for Osseointegration (EAO). MATERIALS AND METHODS: The 50-question, multiple-choice exam of the EAO for the 2022 Certification in Implant Dentistry was obtained. Three groups were created based on the individual or program answering the exam: licensed dentists (D group) and two software versions of an artificial intelligence (AI)-based chatbot (ChatGPT)-3.5 legacy (ChatGPT-3.5 group) and the 4.0 version (ChatGPT-4.0 group). The EAO provided the results of the 2022 examinees (D group). For the ChatGPT groups, the 50 multiple-choice questions were introduced into both ChatGBT versions, and the answers were recorded. Pearson correlation matrix was used to analyze the linear relationship among the subgroups. The inter- and intraoperator reliability was calculated using Cronbach's alpha coefficient. One-way ANOVA and Tukey post-hoc tests were used to examine the data (α = .05). RESULTS: ChatGPT was able to pass the exam for the 2022 Certification in Implant Dentistry of the EAO. Additionally, the software version of ChatGPT impacted the score obtained. The 4.0 version not only pass the exam but also obtained a significantly higher score than the 3.5 version and licensed dentists completing the same exam. CONCLUSIONS: The AIbased chatbot tested not only passed the exam but performed better than licensed dentists.

Influence of implant reference on the scanning accuracy of complete arch implant scans captured by using a photogrammetry system.

STATEMENT OF PROBLEM: Photogrammetry has been reported to be a reliable digital alternative for recording implant positions; however, the factors that may impact the accuracy of photogrammetry techniques remain unknown. PURPOSE: The purpose of this in vitro study was to assess the influence of the implant reference on the accuracy of complete arch implant scans acquired by using a photogrammetry system. MATERIAL AND METHODS: An edentulous cast with 6 implant abutment analogs (MultiUnit Abutment Plus Replica) was obtained and digitized by using a laboratory scanner (T710; Medit). A photogrammetry system (PIC System) was selected to obtain complete arch implant scans. An optical marker (PIC Transfer, HC MUA Metal; PIC Dental) was positioned on each implant abutment of the reference cast. Each optical marker code and position was determined in the photogrammetry software program. Three groups were created based on the implant reference selected before acquiring the photogrammetry scans: right first molar (IPR-3 group), left canine (IPR-11 group), and left first molar (IPR-14 group) (n=30). Euclidean linear and angular measurements were obtained on the digitized reference cast and used to compare the discrepancies with the same measurements obtained on each experimental scan. One-way ANOVA and the Tukey tests were used to analyze the trueness data. The Levene test was used to analyze the precision values (α=.05 for all tests). RESULTS: One-way ANOVA revealed significant linear (P=.003) and angular (P=.009) trueness differences among the groups tested. Additionally, the Tukey test showed that the IPR-11 and IPR-14 groups had significantly different linear (P<.001) and angular trueness (P<.001). The Levene test showed no significant precision linear (P=.197) and angular (P=.235) discrepancies among the groups tested. The IPR-3 group obtained the highest trueness (P<.001) and precision (P<.001) values among the groups tested. CONCLUSIONS: Implant reference impacted the accuracy of complete arch implant scans obtained by using the photogrammetry system tested. However, a trueness ±precision linear discrepancy of 6 ±3 µm and an angular discrepancy of 0.01 ±0.01 degrees were measured among the groups tested; therefore, the impact of the discrepancy measured should not be clinically significant.

Cephalometric analysis performance discrepancy between orthodontists and an artificial intelligence model using lateral cephalometric radiographs.

PURPOSE: The purpose of the present clinical study was to compare the Ricketts and Steiner cephalometric analysis obtained by two experienced orthodontists and artificial intelligence (AI)-based software program and measure the orthodontist variability. MATERIALS AND METHODS: A total of 50 lateral cephalometric radiographs from 50 patients were obtained. Two groups were created depending on the operator performing the cephalometric analysis: orthodontists (Orthod group) and an AI software program (AI group). In the Orthod group, two independent experienced orthodontists performed the measurements by performing a manual identification of the cephalometric landmarks and a software program (NemoCeph; Nemotec) to calculate the measurements. In the AI group, an AI software program (CephX; ORCA Dental AI) was selected for both the automatic landmark identification and cephalometric measurements. The Ricketts and Steiner cephalometric analyses were assessed in both groups including a total of 24 measurements. The Shapiro-Wilk test showed that the data was normally distributed. The t-test was used to analyze the data (α = 0.05). RESULTS: The t-test analysis showed significant measurement discrepancies between the Orthod and AI group in seven of the 24 cephalometric parameters tested, namely the corpus length (p = 0.003), mandibular arc (p < 0.001), lower face height (p = 0.005), overjet (p = 0.019), and overbite (p = 0.022) in the Ricketts cephalometric analysis and occlusal to SN (p = 0.002) and GoGn-SN (p < 0.001) in the Steiner cephalometric analysis. The intraclass correlation coefficient (ICC) between both orthodontists of the Orthod group for each cephalometric measurement was calculated. CONCLUSIONS: Significant discrepancies were found in seven of the 24 cephalometric measurements tested between the orthodontists and the AI-based program assessed. The intra-operator reliability analysis showed reproducible measurements between both orthodontists, except for the corpus length measurement. CLINICAL SIGNIFICANCE: The artificial intelligence software program tested has the potential to automatically obtain cephalometric analysis using lateral cephalometric radiographs; however, additional studies are needed to further evaluate the accuracy of this AI-based system.

Influence of Polymerization Postprocessing Procedures on the Accuracy of Additively Manufactured Dental Model Material.

PURPOSE: To measure the influence of postpolymerization condition (dry and water-submerged) and time (2, 10, 20, and 40 minutes) on the accuracy of additively manufactured model material. MATERIALS AND METHODS: A bar standard tessellation language (STL) file was used to manufacture all the resin specimens using a 3D printer. Two groups (n = 80 each) were created based on postpolymerization condition: dry (D group) and water-submerged (W group). Each group was then divided into four subgroups (D1 to D4 and W1 to W4; n = 20 each), which were each assigned a postpolymerizing time (2, 10, 20, and 40 minutes). The specimens' dimensions were measured using a low-force digital caliper. The volume was calculated as follows: V = l × w × h. Shapiro-Wilk test revealed that the data were not normally distributed. Data were analyzed using Kruskal-Wallis and pairwise Mann-Whitney U tests (α = .05). RESULTS: Significant differences in length, width, height, and volume were found among the subgroups (P < .0018). In all groups, the width dimension (x-axis) presented less accuracy compared to height (z-axis) and length (y-axis) (P < .0018). The D2 and D4 subgroups obtained the closest dimensions to the virtual design, and there were no significant differences between these subgroups (P < .0018). The dry condition showed higher manufacturing accuracy than the water-submerged condition. In the water-submerged subgroups, the highest accuracy was obtained in the W2 and W4 subgroups (P < .0018). CONCLUSIONS: Postpolymerization condition and time influenced the accuracy of the material tested. The dry postpolymerization condition with times of 10 and 40 minutes obtained the highest accuracy.

An overview of the digital occlusion technologies: Intraoral scanners, jaw tracking systems, and computerized occlusal analysis devices.

OBJECTIVES: Within the development of digital technologies, dental professionals aim to integrate virtual diagnostic articulated casts obtained by using intraoral scanners (IOSs), the mandibular motion of the patient recorded by using an optical jaw tracking system, and the information provided by computerized occlusal analysis systems. This article describes the various digital technologies available for obtaining the digital occlusion of a patient and outlines its challenges and limitations. OVERVIEW: The factors that influence the accuracy of the maxillomandibular relationship of diagnostic casts obtained by using IOSs are reviewed, as well as the occurrence of occlusal collisions or mesh interpenetrations. Different jaw tracking systems with varying digital technologies including ultrasonic systems, photometric devices, and artificial intelligence algorithms are reviewed. Computerized occlusal analysis systems for detecting occlusal contacts in a time sequential manner with the pressure distribution on the occlusal surfaces are reviewed. CONCLUSIONS: Digital technologies provide powerful diagnostic and design tools for prosthodontic care. However, the accuracy of these digital technologies for acquiring and analyzing the static and dynamic occlusion need to be further analyzed. CLINICAL SIGNIFICANCE: Efficiently implementing digital technologies into dental practice requires an understanding of the limitations and state of current development of the digital acquisition methods for digitizing the static and dynamic occlusion of a patient by using IOSs, digital jaw trackers, and computerized occlusal analysis devices.

Effect of Hydrogen Peroxide on the Surface and Attractiveness of Various Zirconia Implant Materials on Human Osteoblasts: An In Vitro Study.

The aim of this in vitro study was to investigate the effect of hydrogen peroxide (H2O2) on the surface properties of various zirconia-based dental implant materials and the response of human alveolar bone osteoblasts. For this purpose, discs of two zirconia-based materials with smooth and roughened surfaces were immersed in 20% H2O2 for two hours. Scanning electron and atomic force microscopy showed no topographic changes after H2O2-treatment. Contact angle measurements (1), X-ray photoelectron spectroscopy (2) and X-ray diffraction (3) indicated that H2O2-treated surfaces (1) increased in hydrophilicity (p < 0.05) and (2) on three surfaces the carbon content decreased (33-60%), while (3) the monoclinic phase increased on all surfaces. Immunofluorescence analysis of the cell area and DNA-quantification and alkaline phosphatase activity revealed no effect of H2O2-treatment on cell behavior. Proliferation activity was significantly higher on three of the four untreated surfaces, especially on the smooth surfaces (p < 0.05). Within the limitations of this study, it can be concluded that exposure of zirconia surfaces to 20% H2O2 for 2 h increases the wettability of the surfaces, but also seems to increase the monoclinic phase, especially on roughened surfaces, which can be considered detrimental to material stability. Moreover, the H2O2-treatment has no influence on osteoblast behavior.

Effect of supramucosal height of a scan body and implant angulation on the accuracy of intraoral scanning: An in vitro study.

STATEMENT OF PROBLEM: Intraoral scanners (IOSs) provide a digital alternative to conventional implant impression techniques. However, the effect of the supramucosal height of the scan body and implant angulation on the accuracy of IOSs remains unclear. PURPOSE: The purpose of this in vitro study was to measure the impact of the supramucosal height of the scan body and implant angulation on the accuracy (trueness and precision) of intraoral digital implant scans in partially edentulous models. MATERIAL AND METHODS: Two maxillary partially edentulous casts with 4 implant analogs were fabricated, 1 with 4 parallel implants (P-groups) and 1 with 2 implants distally inclined 18 degrees (A-groups). An implant scan body was positioned on each implant analog (CARES RC Mono Scanbody). For each cast, 3 subgroups were determined based on the soft tissue moulage fabricated for each reference cast exposing 3 mm (P-3 and A-3 subgroups), 5 mm (P-5 and A-5 subgroups), and 7 mm (P-7 and A-7 subgroups) of the implant scan bodies. The 2 reference casts were registered by using a coordinate measurement machine and desktop scanner (7 Series Dental Wings) and then scanned using an IOS (TRIOS 4) (n=15). Linear and angular discrepancy values and root mean square (RMS) error values between the implant scan bodies measured on the reference and experimental scans were computed with an inspection software program (Geomagic). Mann-Whitney U tests with Bonferroni correction were applied for planned comparisons (α=.05/9 ≈ .006). RESULTS: For linear discrepancies, statistically significant differences were found between groups P-3 and A-3 (P=.004) and between P-7 and A-7 (P=.005). For angular discrepancies, statistically significant differences were found between groups A-3 and A-5 (P=.002) and between P-7 and A-7 (P=.003). The RMS error analysis found no statistically significant differences among the groups. CONCLUSIONS: Implant angulation of 18 degrees did not significantly affect the accuracy of the intraoral scans in terms of 6 of the 9 planned comparisons, although the angled groups had lower mean values. Also, the supramucosal height of the scan body did not significantly affect the accuracy of the intraoral scans in terms of 17 of the 18 planned comparisons. Results may vary with different implant scan body designs.

Prevention of peri-implant disease in edentulous patients with fixed implant rehabilitations.

OBJECTIVES: To provide an overview about the current approaches to prevent peri-implant diseases in edentulous patients with complete-arch implant-supported prostheses, and to review the clinical applications of the latest digital technologies for implant prosthodontics. METHODS: A review of the guidelines to prevent peri-implant diseases in patient's receiving complete-arch implant-supported prostheses including facially driven treatment planning procedures using either conventional or digital methods, computer-aided implant planning procedures, and prosthodontic design variables including the optimal number and distribution of dental implants, implant to abutment connection type, implant or abutment level design, screw- or cement-retained alternatives, prostheses contours, and material selection is provided. Furthermore, an outline of the current therapeutic management approaches to address peri-implant diseases is reviewed. CONCLUSIONS: Clinicians should understand and know different planning and design-related variables that can affect biological and mechanical complication rates of complete-arch implant-supported prostheses. Maintenance protocols are fundamental for minimizing biological and mechanical complications.

Prosthetic articulator-based implant rehabilitation virtual patient: A technique bridging implant surgery and reconstructive dentistry.

This technique report describes a fully digital workflow to create a prosthetic articulator-based implant rehabilitation (PAIR) virtual patient for complete-arch or complete-mouth implant rehabilitation. This workflow uses a custom gothic arch tracer during the cone beam computed tomography (CBCT) scan and a 3-dimensional virtual facebow when superimposing data. The PAIR virtual patient possesses reliable centric relation and vertical dimension of occlusion and is compatible with virtual articulators. Computer-aided implant planning and a digital prosthetic design can be seamlessly integrated by using this virtual patient.

Trueness and precision of complete-arch photogrammetry implant scanning assessed with a coordinate-measuring machine.

STATEMENT OF PROBLEM: Photogrammetry technology has been used for the digitalization of multiple dental implants, but its trueness and precision remain uncertain. PURPOSE: The purpose of this in vitro investigation was to compare the accuracy (trueness and precision) of multisite implant recordings between the conventional method and a photogrammetry dental system. MATERIAL AND METHODS: A definitive cast of an edentulous maxilla with 6 implant abutment replicas was tested. Two different recording methods were compared, the conventional technique and a photogrammetry digital scan (n=10). For the conventional group, the impression copings were splinted to an additively manufactured cobalt-chromium metal with autopolymerizing acrylic resin, followed by recording the maxillary edentulous arch with an elastomeric impression using an additively manufactured open custom tray. For the photogrammetry group, a scan body was placed on each implant abutment replica, followed by the photogrammetry digital scan. A coordinate-measuring machine was selected to assess the linear, angular, and 3-dimensional discrepancies between the implant abutment replica positions of the reference cast and the specimens by using a computer-aided design program. The Shapiro-Wilk test showed that the data were not normally distributed. The Mann-Whitney U test was used to analyze the data (α=.05). RESULTS: The conventional group obtained an overall accuracy (trueness ±precision) value of 18.40 ±6.81 µm, whereas the photogrammetry group showed an overall scanning accuracy value of 20.15 ±25.41 µm. Significant differences on the discrepancies on the x axis (U=1380.00, P=.027), z axis (U=601.00, P<.001), XZ angle (U=869.00, P<.001), and YZ angle (U=788.00, P<.001) were observed when the measurements of the 2 groups were compared. Furthermore, significant 3-dimensional discrepancy for implant 1 (U=0.00, P<.001), implant 2 (U=0.00, P<.001), implant 3 (U=6.00, P<.001), and implant 6 (U=9.00, P<.001) were computed between the groups. CONCLUSIONS: The conventional method obtained statistically significant higher overall accuracy values compared with the photogrammetry system tested, with a trueness difference of 1.8 µm and a precision difference of 18.6 µm between the systems. The conventional method transferred the implant abutment positions with a uniform 3-dimensional discrepancy, but the photogrammetry system obtained an uneven overall discrepancy among the implant abutment positions.

Artificial intelligence models for tooth-supported fixed and removable prosthodontics: A systematic review.

STATEMENT OF PROBLEM: Artificial intelligence applications are increasing in prosthodontics. Still, the current development and performance of artificial intelligence in prosthodontic applications has not yet been systematically documented and analyzed. PURPOSE: The purpose of this systematic review was to assess the performance of the artificial intelligence models in prosthodontics for tooth shade selection, automation of restoration design, mapping the tooth preparation finishing line, optimizing the manufacturing casting, predicting facial changes in patients with removable prostheses, and designing removable partial dentures. MATERIAL AND METHODS: An electronic systematic review was performed in MEDLINE/PubMed, EMBASE, Web of Science, Cochrane, and Scopus. A manual search was also conducted. Studies with artificial intelligence models were selected based on 6 criteria: tooth shade selection, automated fabrication of dental restorations, mapping the finishing line of tooth preparations, optimizing the manufacturing casting process, predicting facial changes in patients with removable prostheses, and designing removable partial dentures. Two investigators independently evaluated the quality assessment of the studies by applying the Joanna Briggs Institute Critical Appraisal Checklist for Quasi-Experimental Studies (nonrandomized experimental studies). A third investigator was consulted to resolve lack of consensus. RESULTS: A total of 36 articles were reviewed and classified into 6 groups based on the application of the artificial intelligence model. One article reported on the development of an artificial intelligence model for tooth shade selection, reporting better shade matching than with conventional visual selection; 14 articles reported on the feasibility of automated design of dental restorations using different artificial intelligence models; 1 artificial intelligence model was able to mark the margin line without manual interaction with an average accuracy ranging from 90.6% to 97.4%; 2 investigations developed artificial intelligence algorithms for optimizing the manufacturing casting process, reporting an improvement of the design process, minimizing the porosity on the cast metal, and reducing the overall manufacturing time; 1 study proposed an artificial intelligence model that was able to predict facial changes in patients using removable prostheses; and 17 investigations that developed clinical decision support, expert systems for designing removable partial dentures for clinicians and educational purposes, computer-aided learning with video interactive programs for student learning, and automated removable partial denture design. CONCLUSIONS: Artificial intelligence models have shown the potential for providing a reliable diagnostic tool for tooth shade selection, automated restoration design, mapping the preparation finishing line, optimizing the manufacturing casting, predicting facial changes in patients with removable prostheses, and designing removable partial dentures, but they are still in development. Additional studies are needed to further develop and assess their clinical performance.

Influence of ambient temperature changes on intraoral scanning accuracy.

STATEMENT OF PROBLEM: Different variables that decrease the accuracy of intraoral scanners (IOSs) have been identified. Ambient temperature changes can occur in the dental environment, but the impact of ambient temperature changes on intraoral scanning accuracy is unknown. PURPOSE: The purpose of this in vitro study was to assess the impact of ambient temperature changes on the accuracy (trueness and precision) of an IOS. MATERIAL AND METHODS: A complete arch maxillary dentate Type IV stone cast was obtained. Four 6-mm-diameter gauge balls were added to the maxillary cast to aid future evaluation measurements. The maxillary cast was digitized by using an industrial scanner (GOM Atos Q 3D 12M). The manufacturer's recommendations were followed in obtaining a reference scan. Then, the maxillary cast was digitized by using an IOS (TRIOS 4) according to the scanning protocol recommended by the manufacturer. Four groups were created depending on the ambient temperature change assessed: 24 °C or room temperature (24-D or control group), 19 °C or a 5-degree temperature drop (19-D group), 15 °C or a 9-degree temperature drop (15-D group), and 29 °C or a 5-degree temperature rise (29-D group). The Shapiro-Wilk and Kolmogorov-Smirnov tests revealed that the data were not normally distributed (P<.05). For trueness, the nonparametric Kruskal-Wallis followed by the Dwass-Steel-Critchlow-Fligner pairwise comparison tests were used. Precision analysis was obtained by using the Levene test based on the comparison of the standard deviations of the 4 groups with 95% Bonferroni confidence intervals for standard deviations (α=.05). RESULTS: The Kruskal-Wallis test revealed significant differences in the trueness values among all 4 groups (P<.001). Furthermore, significant differences between the linear discrepancy medians between the control and 19-D groups (P<.001), control and 15-D groups (P=.002), control and 29-D groups (P<.001), 19-D and 29-D groups (P=.003), and 15-D and 29-D groups (P<.001) were found. The Levene test for the comparison of the variances among the 4 groups did not detect a significant difference (P>.999), indicating that precision wise the 4 groups were not significantly different from each other. CONCLUSIONS: Ambient temperature changes had a detrimental effect on the accuracy (trueness and precision) of the IOS tested. Ambient temperature changes significantly decreased the scanning accuracy of the IOS system tested. Increasing the ambient temperature has a greater influence on the intraoral scanning accuracy of the IOS selected when compared with decreasing the ambient temperature.

Influence of the Number of Teeth and Location of the Virtual Occlusal Record on the Accuracy of the Maxillo-Mandibular Relationship Obtained by Using An Intraoral Scanner.

PURPOSE: To assess the influence of the number of teeth (2, 3, or 4) and location (molars, molar and premolar, or premolars and canines) of the bilateral virtual occlusal record on the accuracy of the virtual maxillo-mandibular relationship acquired by an intraoral scanner (IOS). MATERIAL AND METHODS: Diagnostic casts mounted on a semi-adjustable articulator were obtained. Four markers were adhered on the facial surfaces of the first molars and canines. The mounted casts were digitized using an extraoral scanner. Maxillary and mandibular intraoral digital scans were obtained using an intraoral scanner (TRIOS 4). The maxillary and mandibular digital scans were duplicated 105 times and divided into 7 groups based on the number of teeth (2, 3, or 4) and location (molar, molar and premolar, or premolars and canines) of the bilateral virtual occlusal records (n = 15). The alignment of the scans was automatically performed after the acquisition of the corresponding occlusal records by the IOS program. Eight linear distances between the gauge balls were computed on the reference scan and on the 105 digital scans. The distances obtained on the reference scan were used to calculate the discrepancies with the distances obtained on each experimental scan. The Shapiro-Wilk test showed that the data was normally distributed. The trueness and precision data were analyzed using 2-way ANOVA followed by pairwise comparison Tukey tests (α = 0.05). RESULTS: Two-way ANOVA showed that the number of teeth (p < 0.001) and the position of the virtual occlusal record (p < 0.001) were significant factors on the accuracy of the maxillo-mandibular relationship. Tukey test showed significant overall mean differences between the different groups tested: the 4-teeth group obtained the highest trueness, and the 2-teeth group showed the lowest trueness values (p < 0.001). Tukey test showed significant trueness differences between the virtual occlusal record locations. The 2-teeth record located more posteriorly obtained the lowest trueness. Significant differences in precision values were found among the subgroups tested (p < 0.001). The 2-teeth group obtained significantly more precision values than the 3- and 4-teeth groups. Additionally, there was a significant difference in precision values between the subgroup tested in which the first molar and second premolar location had the highest precision, while the first and second premolar's location obtained the lowest precision. CONCLUSIONS: The number of teeth and the location of the bilateral virtual occlusal record influenced the accuracy of the virtual maxillo-mandibular relationship obtained by the intraoral scanner tested. The more teeth included in the bilateral virtual occlusal record, the higher the accuracy of the maxillo-mandibular relationship. Additionally, the more anteriorly located the virtual bilateral occlusal record involving 2 or 3 teeth was, the higher the accuracy mean value.

Artificial intelligence applications in implant dentistry: A systematic review.

STATEMENT OF PROBLEM: Artificial intelligence (AI) applications are growing in dental implant procedures. The current expansion and performance of AI models in implant dentistry applications have not yet been systematically documented and analyzed. PURPOSE: The purpose of this systematic review was to assess the performance of AI models in implant dentistry for implant type recognition, implant success prediction by using patient risk factors and ontology criteria, and implant design optimization combining finite element analysis (FEA) calculations and AI models. MATERIAL AND METHODS: An electronic systematic review was completed in 5 databases: MEDLINE/PubMed, EMBASE, World of Science, Cochrane, and Scopus. A manual search was also conducted. Peer-reviewed studies that developed AI models for implant type recognition, implant success prediction, and implant design optimization were included. The search strategy included articles published until February 21, 2021. Two investigators independently evaluated the quality of the studies by applying the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Quasi-Experimental Studies (nonrandomized experimental studies). A third investigator was consulted to resolve lack of consensus. RESULTS: Seventeen articles were included: 7 investigations analyzed AI models for implant type recognition, 7 studies included AI prediction models for implant success forecast, and 3 studies evaluated AI models for optimization of implant designs. The AI models developed to recognize implant type by using periapical and panoramic images obtained an overall accuracy outcome ranging from 93.8% to 98%. The models to predict osteointegration success or implant success by using different input data varied among the studies, ranging from 62.4% to 80.5%. Finally, the studies that developed AI models to optimize implant designs seem to agree on the applicability of AI models to improve the design of dental implants. This improvement includes minimizing the stress at the implant-bone interface by 36.6% compared with the finite element model; optimizing the implant design porosity, length, and diameter to improve the finite element calculations; or accurately determining the elastic modulus of the implant-bone interface. CONCLUSIONS: AI models for implant type recognition, implant success prediction, and implant design optimization have demonstrated great potential but are still in development. Additional studies are indispensable to the further development and assessment of the clinical performance of AI models for those implant dentistry applications reviewed.