Background/Aims: The aim of this study was to evaluate the effectiveness of large language model (LLM)-based chatbot systems in predicting bone age and identifying growth stages, and to explore their potential as practical, infrastructure-independent alternatives to conventional methods and convolutional neural network (CNN)-based deep learning models. Methods: This study evaluated the performance of three ChatGPT-based models (GPT-4o, GPT-o4-mini-high, and GPT-o1-pro) in predicting bone age and growth stage using 90 anonymized hand–wrist radiographs (30 from each growth stage—pre-peak, peak, and post-peak—with equal male and female distribution). Reference standards were ensured by expert orthodontists using Fishman’s Skeletal Maturity Indicators (SMI) system and the Greulich–Pyle Atlas, with each radiograph analyzed by three GPT models using standardized prompts. Model performances were evaluated through statistical analyses assessing agreement and prediction accuracy. Results: All models showed significant agreement with the reference values in bone age prediction (p < 0.001), with GPT-o1-pro having the highest concordance (Pearson r = 0.546). No statistically significant difference was observed in the mean absolute error (MAE) among the models (p > 0.05). The GPT-o4-mini-high model achieved an accuracy rate of 72.2% within a ±2 year deviation range for bone age prediction. The GPT-o1-pro and GPT-o4-mini-high models showed bias in the Bland–Altman analysis of bone age predictions; however, GPT-o1-pro yielded more reliable predictions with narrower limits of agreement. In terms of growth stage classification, the GPT-4o model achieved the highest agreement with the reference values (κ = 0.283, p < 0.001). Conclusions: This study shows that general-purpose GPT models can support bone age and growth stages prediction, with each model having distinct strengths. While GPT models do not replace clinical examination, their contextual reasoning and ability to perform preliminary assessments without domain-specific training make them promising tools, though further development is needed.

Background/Objectives: The aim of this study was to evaluate the accuracy of aesthetic assessments performed by artificial intelligence (AI)-based large language models (LLMs) using the Aesthetic Component of the Index of Orthodontic Treatment Need (IOTN-AC), which is widely applied to determine the need for orthodontic treatment. Methods: A total of 150 frontal intraoral photographs from patients in the permanent dentition, scored from 1 to 10 on the IOTN-AC, were assessed by two AI-based LLMs (ChatGPT-5 and ChatGPT-5 Pro). Two experienced clinicians independently scored all photographs, with one evaluator’s scores used as the reference (κ = 0.91, ICC = 0.88). Model performance was analyzed by comparing IOTN-AC scores and treatment need classifications. In addition, performance parameters such as accuracy, precision, specificity, and sensitivity were evaluated. Statistical analyses included Spearman correlation, Cohen’s Kappa, ICC, Mean Absolute Error (MAE), Wilcoxon signed-rank test, and Bland–Altman analysis. Results: Both models demonstrated positive and significant correlations with the reference values for scoring and classification (p < 0.001). Compared to GPT-5 Pro, the GPT-5 model exhibited superior performance, with a lower error rate (MAE = 1.47) and higher classification accuracy (66.7%). Bland–Altman analysis showed that most predictions fell within the 99% confidence interval, and regression analysis revealed no systematic bias (p > 0.05). Conversely, the models failed to achieve consistently high performance in each of the performance parameters. Conclusions: The findings revealed that although AI-based LLMs are promising, statistical accuracy alone is insufficient for safe clinical use, and they should demonstrate consistently high performance across all parameters.

Large language models (LLMs) are increasingly used to provide health-related information, yet their clinical reliability remains uncertain. This study aimed to evaluate the accuracy, comprehensiveness, and readability of AI-based LLMs in providing evidence-based guidance on early maxillary expansion for children in the primary and mixed dentition phases, assessing their potential as trustworthy resources for parental decision-making. Eight LLMs (DeepSeek V3, Gemini 2.5 Flash, Claude 4.5 Sonnet, MediSearch, Copilot, GPT-5, GPT-4o, and Grok) were tasked with responding to a total of 20 questions reflecting common parental concerns about early maxillary expansion, with 10 questions assigned to each dentition phase (primary and mixed). Responses were evaluated for accuracy and comprehensiveness, and readability was assessed using the Flesch Reading Ease Score (FRES) and Flesch-Kincaid Grade Level (FKGL). Statistical analyses included descriptive statistics and appropriate parametric and non-parametric tests based on data distribution, with significance set at p < 0.05. Significant differences were observed among the LLMs in terms of accuracy, comprehensiveness, and readability (p < 0.001). DeepSeek V3 and Grok achieved the highest scores for both accuracy and comprehensiveness across both dentition phases, with DeepSeek V3 also demonstrating the highest readability in the mixed dentition phase. Copilot, GPT-5, and GPT-4o produced the most readable outputs, as indicated by their highest FRES and lowest FKGL scores, though their content accuracy was comparatively lower. In contrast, MediSearch, Gemini 2.5 Flash, and Claude 4.5 Sonnet showed consistently weaker performance across all evaluated criteria. This study concluded that, although some LLMs can offer reliable and understandable information about early maxillary expansion, none consistently excel across all evaluated criteria. In healthcare contexts, integrating scientific accuracy with readability is crucial for supporting informed parental decision-making, enhancing overall health literacy, and strengthening patient–clinician communication. These findings highlight that AI-based LLMs should serve as supplementary tools that support, rather than replace, professional orthodontic guidance.

Objective: The objective of this study was to systematically analyze the cleft lip and/or palate (CL/P) literature published between 2000 and 2025 to identify dominant research themes, temporal trends, and potential gaps by applying a natural language processing-based topic modeling approach. Design: We analyzed articles retrieved from the Scopus database and identified thematic clusters using the BERTopic algorithm, which integrates BERT embeddings, Uniform Manifold Approximation and Projection dimensionality reduction, and Hierarchical Density-Based Spatial Clustering of Applications with Noise clustering. Setting: This study exclusively examined articles related to CL/P. Patients/Participants: This study involved no patients or participants. Interventions: Not applicable as this is a BERTopic-based analysis. Main Outcome Measures: Outcomes included identifying dominant research topics, trend analysis, distribution across countries and journals, and classifying topics as “hot” or “cold” based on temporal trends. Results: We identified 29 thematic clusters. The most common topics included “Velopharyngeal Dysfunction and Fistula Repair,” “Nonsyndromic Cleft Lip and Palate and Genetic Associations,” and “Unilateral Cleft Lip and Palate and Maxillofacial Asymmetry.” “Quality of Life and Psychosocial Impact in Children,” “Surgical Repair Approaches,” and “Presurgical Nasoalveolar Molding Techniques” emerged as “hot topics.” The United States led in publication volume, while certain topics dominated in specific countries. The Cleft Palate-Craniofacial Journal published the most articles. Conclusions: This study provides a comprehensive thematic map of CL/P research, highlighting strengths and underexplored areas. BERTopic offers an efficient, scalable method for analyzing large-scale scientific literature and identifying future research priorities.

The aim of this study was to compare the response capabilities of generative pre-trained transformers (GPTs) for identical lateral cephalograms (LCs) based on text- and image-based prompts, using the newly developed Artificial Intelligence Based Diagnosis and Treatment Planning Index (AIDTI). A total of 90 LCs from 30 cases each with skeletal Class I, II, and III malocclusions were included. The LCs were presented to GPT-4o, GPT-o3 pro, GPT-5, and GPT-5 pro in two different formats: text-based (numerical data including cephalometric analysis measurements) and image-based (direct image upload) prompts. The responses of the GPTs were evaluated using the newly developed AIDTI, scored on a 0-10 scale and consisting of five criteria: diagnostic accuracy, capability for differential diagnosis, clinical appropriateness of the proposed treatment plan, disclosure of risks and complications associated with the treatment plan, and ability to offer alternative treatment options. Higher performance was observed in text-based prompts, with the highest score achieved by GPT-5 pro (9.62 ± 1.13). By contrast, the performance of all GPTs on image-based prompts was notably lower, with the highest score being 4.16 ± 4.12 for GPT-o3 pro. Additionally, all models showed a tendency to randomly categorize malocclusions as Class II, suggesting systematic bias in their predictions. AIDTI provides a structured and multidimensional framework for the concise, balanced, and clinically meaningful interpretation of GPT performance. Because GPTs are unable to directly analyze LCs, their use as independent or reliable supportive tools in orthodontics remains limited at this stage. GPTs may contribute more reliably to orthodontic practice only when orthodontists prompt the model with text-based cephalometric measurement data. Not applicable.