Gonuldas F, et al. J Adv Prosthodont. 2014 Aug;6(4):309-316. http://dx.doi.org/10.4047/jap.2014.6.4.309

Yılmaz K, et al. J Adv Prosthodont. 2014 Dec;6(6):427-433. http://dx.doi.org/10.4047/jap.2014.6.6.427

: It has been considered that the preclinical education may be inadequate in the development of preparation skills of dental students. With technological developments, there is an increase in the use of computer-aided simulations in dental education. Virtual reality (VR) patient simulators promise practice in a realistic environment with detailed, frequent and objective feedback, but it remains unclear whether these features lead to better or faster skill acquisition. This study aims to investigate the impact of virtual reality simulations on students’ clinical preparation skills. In this study, tooth preparation data of 100 fourth-year students who practiced preparation with a virtual reality device and had real patient experience, as well as a group of 100 fifth-year students who had no prior virtual reality experience but had real patient experience, were transferred to the exocad® DentalCAD program, a CAD software, for the measurement of TOC (Total Occlusal Convergence) angles. The data obtained from these measurements were analyzed using the SPSS program. In addition to this study, 25 random individuals from both groups underwent preparation in a phantom model in order to make a comparison between different experience environments. Finally, a questionnaire was administered to the group trained in the simulator to evaluate the students’ perspective on this new training method. Independent sample T test and single sample analysis of variance (ANOVA), which are parametric test methods, and Tukey HSD, which is a post hoc test, were used in statistical analyses. With the t test, which is used to investigate whether there is a difference between two sample groups in terms of averages, we aimed to investigate the significance between class level and tooth cutting surface by using group statistics and descriptive analysis data of the preparations. With the ANOVA test, which is a statistical analysis method used to compare the averages between at least three groups, we looked at whether the preparations we made in 3 different experience environments produced a significant result according to the tooth cutting surface, and then we investigated which experience group was the source of the significance with the tukey test. In the descriptive statistical analysis, it was determined that the average preparation angles of the 4th-year students were lower than those of the 5th-year students. Accordingly, it is possible to say that grade levels affect all surface preparation results in a statistically significant way. In descriptive statistics regarding patient preparation experience, the averages of the preparation angles taken according to the tooth surfaces of the 4th and 5th Grades are; The averages of the mesial, distal and buccal surfaces are close to each other, but only on the palatal surfaces, there is a significant difference between the averages of the 4th Grade (12.46) and the current average of the 5th Grade (15.22). The results of the Independent Samples T-Test conducted in the context of grade levels and four surface areas, is examined, it is seen that there are statistically significant differences between grade levels and the preparation results of all surfaces (p < 0.05). According to the results of this study, students who used virtual reality simulators were more successful in terms of tooth preparation angles compared to students who did not use virtual reality simulators. This study demonstrated that the use of virtual reality simulators contributes to tooth prepartion skills.

The effect of surface finishing techniques on machinable ceramics to obtain optimum smoothness is unclear. The aim of the study was to evaluate the effects of surface finishing techniques on machinable feldspathic and leucite-reinforced ceramics. Forty specimens were divided into four subgroups according to surface finishing techniques and ceramic structure. A profilometer was used to evaluate surface roughness. A spectrophotometer was used to obtain the CIE L*, a* and b* coordinates. All specimens were subjected to a threepoint bending test to determine flexural strength. All data were analyzed with two-way ANOVA and Tukey’s HSD tests (p<0.05). Polishing techniques were found to be more effective than the glazing method to obtain smooth surfaces. Glazing technique increased the flexural strength of leucite-reinforced ceramics. Finishing procedures have different effects on the success of the restorations and must be considered by the clinicians.

Artificial intelligence (AI), particularly large language models (LLMs) such as ChatGPT, has attracted attention for its potential to enhance diagnostic decision-making. This study aims to compare the decision-making tendencies of clinicians from different disciplines regarding implant planning with the approach of ChatGPT and to evaluate the potential integration of AI into clinical decision-making. This cross-sectional, survey-based study compared the implant planning decisions of prosthodontic and surgical residents with those of ChatGPT 4.0 and each other. Fourteen cases were presented to 20 prosthodontics, 20 oral and maxillofacial surgery residents, and ChatGPT. Participants selected the option they found most appropriate; responses were compared case by case using chi-square tests with p < 0.05. The responses of residents showed no statistically significant differences. However, comparisons between the AI and clinicians revealed significant differences in 11 of the scenarios. In clinical scenarios where no differences were found, both human and artificial intelligence tended to make the same choices on less complicated cases. While AI is increasingly advancing in clinical decision-making, its responses to clinical scenarios may show some inconsistencies. AI demonstrated similarity in simple cases but diverged in complex ones. While promising as a support, broader studies with diverse scenarios are necessary to enhance the integration potential of AI in clinical decision-making.

Background and Objectives: We aimed to develop a predictive model for the outcome of bruxism treatments using ultrasonography (USG)-based machine learning (ML) techniques. This study is a quantitative research study (predictive modeling study) in which different treatment methods applied to bruxism patients are evaluated through artificial intelligence. Materials and Methods: The study population comprised 102 participants with bruxism in three treatment groups: Manual therapy, Manual therapy and Kinesio Tape or Botulinum Toxin-A injection. USG imaging was performed on the masseter muscle to calculate muscle thickness, and pain thresholds were evaluated using an algometer. A radiomics platform was utilized to handle imaging and clinical data, as well as to perform a subsequent radiomics statistical analysis. Results: The area under the curve (AUC) values of all machine learning methods ranged from 0.772 to 0.986 for the training data and from 0.394 to 0.848 for the test data. The Support Vector Machine (SVM) led to excellent discrimination between bruxism and normal patients from USG images. Radiomics characteristics in pre-treatment ultrasound scans of patients, showing coarse and nonuniform muscles, were associated with a greater chance of less effective pain reduction outcomes. Conclusions: This study has introduced a machine learning model using SVM analysis on ultrasound (USG) images for bruxism patients, which can detect masseter muscle changes on USG. Support Vector Machine regression analysis showed the combined ML models can also predict the outcome of the pain reduction.