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 base design on the manufacturing accuracy of vat-polymerized diagnostic casts: An in vitro study.

STATEMENT OF PROBLEM: Vat-polymerized casts can be designed with different bases, but the influence of the base design on the accuracy of the casts remains unclear. PURPOSE: The purpose of the present in vitro study was to evaluate the influence of various base designs (solid, honeycombed, and hollow) with 2 different wall thicknesses (1 mm and 2 mm) on the accuracy of vat-polymerized diagnostic casts. MATERIAL AND METHODS: A virtual maxillary cast was obtained and used to create 3 different base designs: solid (S group), honeycombed (HC group), and hollow (H group). The HC and H groups were further divided into 2 subgroups based on the wall thickness of the cast designed: 1 mm (HC-1 and H-1) and 2 mm (HC-2 and H-2) (N=50, n=10). All the specimens were manufactured with a vat-polymerized printer (Nexdent 5100) and a resin material (Nexdent Model Ortho). The linear and 3D discrepancies between the virtual cast and each specimen were measured with a coordinate measuring machine. Trueness was defined as the mean of the average absolute dimensional discrepancy between the virtual cast and the AM specimens and precision as the standard deviation of the dimensional discrepancies between the virtual cast and the AM specimens. The Kolmogorov-Smirnov and Shapiro-Wilk tests revealed that the data were not normally distributed. The data were analyzed with Kruskal-Wallis and Mann-Whitney U pairwise comparison tests (α=.05). RESULTS: The trueness ranged from 63.73 µm to 77.17 µm, and the precision ranged from 44.00 µm to 54.24 µm. The Kruskal-Wallis test revealed significant differences on the x- (P<.001), y- (P=.006), and z-axes (P<.001) and on the 3D discrepancy (P<.001). On the x-axis, the Mann-Whitney test revealed significant differences between the S and H-1 groups (P<.001), S and H-2 groups (P<.001), HC-1 and H-1 groups (P<.001), HC-1 and H-2 groups (P<.001), HC-2 and H-1 groups (P<.001), and HC-2 and H-2 groups (P<.001); on the y-axis, between the S and H-1 groups (P<.001), HC-1 and H-1 groups (P=.001), HC-1 and H-2 groups (P=.02), HC-2 and H-1 groups (P<.001), HC-2 and H-2 groups (P=.003); and on the z-axis, between the S and H-1 groups (P=.003). For the 3D discrepancy analysis, significant differences were found between the S and H-1 groups (P<.001), S and H-2 groups (P=.004), HC-1 and H-1 groups (P=.04), and HC-2 and H-1 groups (P=.002). CONCLUSIONS: The base designs tested influenced the manufacturing accuracy of the diagnostic casts fabricated with a vat-polymerization printer, with the solid and honeycombed bases providing the greatest accuracy. However, all the specimens were clinically acceptable.

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.

Influence of the base design on the accuracy of additive manufactured casts measured using a coordinate measuring machine.

PURPOSE: To measure the accuracy of the additively manufactured casts with 3 base designs: solid, honeycomb-structure, and hollowed bases. METHODS: A virtual cast was used to create different base designs: solid (S Group), honeycomb-structure (HC group), and hollowed (H group). Three standard tessellation language files were used to fabricate the specimens using a material jetting printer (J720 Dental; Stratasys) and a resin (VeroDent MED670; Stratasys) (n=15). A coordinate measuring machine was selected to measure the linear and 3D discrepancies between the virtual cast and each specimen. Shapiro-Wilk test revealed that all the data was not normally distributed (P<.05). Kruskal Wallis and Mann Whitney U tests were used (α=.05). RESULTS: The S group obtained a median ±interquartile range 3D discrepancy of 53.00 ±73.25 µm, the HC group of 58.00 ±67.25 µm, and the H group of 34.00 ±45.00 µm. Significant differences were found in the x- (P<.001), y- (P<.001), and z-axes (P<.001), and 3D discrepancies among the groups (P<.001). Significant differences were found between the S and H groups (P=.002) and HC and H groups (P<.001) on the x-axis; S and H groups (P<.001) and HC and H groups (P<.001) on the y-axis; S and H groups (P<.001) and HC and H groups (P<.001) on the z-axis; and S and H groups (P<.001) and HC and H groups (P<.001) on the 3D discrepancy. CONCLUSION: The base designs influenced on the accuracy of the casts but all the specimens obtained a clinically acceptable manufacturing range. The H group obtained the highest accuracy.

Efficacy of herbal- versus chlorhexidine-based mouthwashes towards oral hygiene maintenance in patients undergoing fixed orthodontic therapy: A systematic review and meta-analysis.

BACKGROUND AND OBJECTIVE: The review aims to fill the gap in literature by comparing the efficacy of herbal and chlorhexidine-based mouthwashes towards oral hygiene maintenance (OHM) in patients undergoing fixed orthodontic treatment (OT). METHODS: Indexed databases were searched electronically to include randomized controlled trials (RCTs) for data gathering. The protocol was registered in PROSPERO (CRD42020182497). Risk of bias assessment, quality of evidence investigation and meta-analysis were performed to evaluate reported OHM-related parameters at time points before and after the use of chlorhexidine (control group) and herbal mouthwashes (intervention group). With 95% confidence intervals, mean difference (MD) or standardized mean difference (SMD) was used to estimate effect size. RESULTS: Out of eight RCTs, results from one RCT favoured chlorhexidine and the results from a second RCT favoured herbal mouthwashes. Results from three RCTs showed comparable effects for the respective investigated OHM-related parameters. Chlorhexidine demonstrated higher antimicrobial efficacy against Streptococcus mutans (S. mutans) in two studies, and one RCT found comparable antimicrobial efficacies. Risk of bias was low in two studies, and moderate and high in two studies each. Quality of evidence was very low to moderate for the respective investigated parameters. Sub-group analysis for parameters colony forming units (CFU) {SMD (0.40) [95% CI (-0.22, 1.03)], gingival index (GI) {MD (0.06) [95% CI (-0.08, 0.20)]}, plaque index (PI) {SMD 0.22 [95% CI (-0.23, 0.67)]} before the use of chlorhexidine and herbal mouthwashes remained inconclusive. CONCLUSION: The comparison between efficacy of herbal and chlorhexidine towards OHM in patients undergoing fixed OT remains debatable.

Facial scanning accuracy depending on the alignment algorithm and digitized surface area location: An in vitro study.

OBJECTIVES: To measure the accuracy (trueness and precision) of a facial scanner depending on the alignment method and the digitized surface area location. METHODS: Fourteen markers were adhered on a head mannequin and digitized using an industrial scanner (GOM Atos Q 3D 12 M; Carl Zeiss Industrielle Messtechnik GmbH). A control mesh was acquired. Subsequently, the mannequin was digitized using a facial scanner (Arc4; Bellus3D) (n = 30). The control mesh was delineated into 10 areas. Based on the alignment procedures, two groups were created: reference best fit (RBF group) and landmark-based best fit (LA group). The root mean square was used to calculate the discrepancy between the control mesh and each facial scan. A 2-way ANOVA and Tukey pairwise comparison tests were used to compare trueness and precision between the 2 groups across 10 areas (α = .05). RESULTS: Both alignment algorithms (P = .007) and digitized area (P < .001) were significant predictors of trueness with a significant interaction between the two predictors (F (9, 580) =25.13, P < .001). Tukey pairwise comparison showed that there was a significant difference between mean trueness values of RBF (mean=0.53 mm) and LA (mean=0.55 mm) groups. Moreover, a significant difference was detected among the trueness values across surface areas. The A9-area (left tragus area) had the highest and A5-area (right cheek area) had the lowest mean trueness. Both alignment algorithm (P < .001) and digitized surface area (P < .001) were significant predictors of precision with a significant interaction between the two predictors (F (9, 580) =14.34, P < .001). Tukey pairwise comparison showed that there was a significant difference between mean precision values of RBF (mean=0.38 mm) and LA (mean=0.35 mm) groups. Moreover, a significant difference was detected among the precision values across surface areas. Comparing the surface areas, A9-area had the highest and A10-area (forehead area) had the lowest mean precision. CONCLUSIONS: Alignment procedures influenced on the scanning trueness and precision mean values, but the facial scanner accuracy values obtained were within the clinically acceptable accuracy threshold of less or equal than 2 mm. Furthermore, the scanning accuracy (for both trueness and precision) depended on the location of the scanned surface area, being more accurate on the middle of the face than on the sides of the face.

Digital and analog vertical dimension measurements: A clinical observational study.

PURPOSE: To compare the rest vertical dimension (RVD) and occlusal vertical dimension (OVD) measurements obtained using a facial scanner with conventional methods and to evaluate the influence of the file format on the accuracy of the digital calculations. MATERIALS AND METHODS: Participants (N = 30) received marks on the glabella (Gb), tip of the nose (TN), and pogonion (Pg). Interlandmark distances Gb-TN and TN-Pg in the OVD and RVD positions were recorded by two operators conventionally (manual group) and digitally (digital group). For the manual group, measurements were obtained using a caliper. For the digital group, 10 scans in each position were obtained using a facial scanner (Face Camera Pro, Bellus3D) and exported in tessellation with polygonal faces (OBJ) and standard tessellation language (STL) file formats. Digital measurements were performed using both facial scan file formats and a software (Matera 2.4, exocad). The interocclusal rest distance (IRD) and the intraclass correlation coefficient were calculated. Shapiro-Wilk test was used to determine normal distribution. An independent samples t test, one-way analysis of variance, and post hoc Tukey test were used for analyses (± = .05). RESULTS: No significant differences were found between the manual and digital measurements using the OBJ files or digital measurements using the STL files (P > .05). The IRD ranged from 0.72 ± 0.48 mm to 5.00 ± 1.34 mm. The inter- and intra-operator reliability were significant (P < .001), with a Cronbach's alpha value ranging from .994 to .997. CONCLUSION: No difference was found between manual and digital measurements. A high measurement consistency was encountered for each operator and between the operators. The facial scan file format did not influence the digital measurements.