Dashti M, et al. Imaging Sci Dent. 2024 Sep;54(3):271-275. https://doi.org/10.5624/isd.20240037

Objectives: The aim of this article is to establish a comprehensive nationwide prevalence of malocclusion traits on the sagittal, vertical, and transverse planes of space in the Turkish population.Material and Methods: A systematic search of PubMed, Scopus, and Web of Science was supplemented by manual searches of Google Scholar and the reference lists of included studies. Original Turkish health studies of any age were included. Strengthening the Reporting of Observational Studies in Epidemiology assessed study quality and bias (STROBE). Sagittal, vertical, and transverse malocclusion features were retrieved and gathered.Results: Eleven studies were selected from 434 titles. Two studies showed a high risk of bias, eight low and one moderate. Thirteen thousand two hundred seventy‐one individuals were investigated from early childhood to late adulthood. Most studies were sampled from universities and dental (nonorthodontic) clinics. The pooled malocclusion prevalence was 56% for Class I (95% confidence interval (CI): 44−68%), 31% for Class II (CI: 6–42%), and 11% for Class III (CI: 21–37%). The other common types of malocclusions were crowding (41%, CI: 18–65%), overjet (34%, CI: 21–50%), negative overjet (13%, CI: 7–20%), and crossbite (11%, CI: 7–15%). Additionally, there was no significant difference in Class I (relative risk [RR] = 1.00, [0.96–1.05]), Class II ([RR] = 0.97, [0.92–1.03]), and Class III ([RR] = 1.08, [0.96–1.225]) malocclusion by gender.Conclusions: This study showed Class I malocclusion has a high prevalence among the Turkish population followed by Class II and Class III malocclusions. In addition, crowding and overjet were the most prevalent malocclusions among Turkish individuals. There were no significant differences in the prevalence of malocclusions between males and females.

Artificial intelligence (AI), such as ChatGPT-4 from OpenAI, has the potential to transform medical education and assessment. However, its effectiveness in specialized fields like prosthodontics, especially when comparing base to fine-tuned models, remains underexplored. This study evaluates the performance of ChatGPT-4 on the US National Prosthodontic Resident Mock Exam in its base form and after fine-tuning. The aim is to determine whether fine-tuning improves the AI’s accuracy in answering specialized questions. An official sample questions from the 2021 US National Prosthodontic Resident Mock Exam was used, obtained from the American College of Prosthodontists. A total of 150 questions were initially considered, and resources were available for 106 questions. Both the base and fine-tuned models of ChatGPT-4 were tested under simulated exam conditions. Performance was assessed by comparing correct and incorrect responses. The Chi-square test was used to analyze accuracy, with significance set at p < 0.05. The Kappa coefficient was calculated to measure agreement between the models’ responses. The base model of ChatGPT-4 correctly answered 62.7% of the 150 questions. For the 106 questions with resources, the fine-tuned model answered 73.6% correctly. The Chi-square test showed a significant improvement in performance after fine-tuning (p < 0.001). The Kappa coefficient was 0.39, indicating moderate agreement between the models (p < 0.001). Performance varied by topic, with lower accuracy in areas such as Implant Prosthodontics, Removable Prosthodontics, and Occlusion, though the fine-tuned model consistently outperformed the base model. Fine-tuning ChatGPT-4 with specific resources significantly enhances its accuracy in answering specialized prosthodontic exam questions. While the base model provides a solid baseline, fine-tuning is essential for improving AI performance in specialized fields. However, certain topics may require more targeted training to achieve higher accuracy.

Dashti M, et al. Imaging Sci Dent. 2024 Sep;54(3):232-239. https://doi.org/10.5624/isd.20240038