Background/Objectives: The aim of this study was to assess the diagnostic capabilities of three large language model-based artificial intelligence chatbots (ChatGPT 4.0, Gemini 2.5, and Microsoft Copilot) in the radiographic evaluation of jaw lesions on panoramic images with different densities (mixed, radiolucent, and radiopaque). Methods: 120 panoramic radiographs showing jaw lesions with varying radiographic appearances were independently analyzed using three artificial intelligence chatbot systems. Each model was provided with the same single-round prompt and a standardized diagnostic scoring framework encompassing lesion structure, configuration, border characteristics, morphology, relationship with teeth, effects on adjacent structures, biological behavior indicators, and total diagnostic scores. Descriptive statistics were reported as mean ± standard deviation and median (minimum-maximum). Differences between LLM scores were analyzed using the Kruskal–Wallis test, followed by Bonferroni-corrected post hoc comparisons. The statistical significance level was set at p < 0.05. Results: Significant differences were observed among the LLMs across multiple diagnostic categories, including lesion structure, configuration, border characteristics, and total scores (p < 0.05). Gemini achieved the highest total scores in radiolucent (11.49 ± 4.97) and mixed lesions (9.01 ± 5.78), whereas ChatGPT showed slightly higher performance in radiopaque lesions (10.93 ± 2.88). Copilot demonstrated the lowest overall performance across all lesion categories. Conclusions: Large language model–based artificial intelligence chatbots showed variable performance in the panoramic radiographic evaluation of jaw lesions with radiolucent, radiopaque, and mixed patterns, suggesting potential utility as supportive tools. However, further validation studies are required before routine clinical implementation.
Background and Objectives: The objective was to evaluate the association between serum 25-hydroxyvitamin D [25(OH)D] measured before functional loading and long-term peri-implant marginal bone loss (MBL). Materials and Methods: This retrospective study included 60 systemically healthy patients with 136 implants. Patients were classified as vitamin D-deficient (<20 ng/mL; n = 30) or -sufficient (≥20 ng/mL; n = 30). MBL was calculated from periapical radiographs obtained at prosthetic delivery and final follow-up (mean, 39.46 months; range, 34–48 months). Clinical parameters and implant loss were secondary outcomes. Between-group comparisons used the Mann–Whitney U and Fisher’s exact tests; associations were examined using Spearman’s rank correlation. Results: MBL was greater in the deficient group than in the sufficient group (0.98 ± 0.25 mm vs. 0.42 ± 0.32 mm; p < 0.001). Serum 25(OH)D was inversely correlated with MBL in the deficient group (rs = −0.720), sufficient group (rs = −0.604), and overall sample (rs = −0.862; all p < 0.001). No statistically significant between-group differences were detected in the clinical parameters (all p > 0.05). Conclusions: Lower baseline serum 25(OH)D was associated with greater long-term MBL, while clinical parameters and patient-level implant loss did not differ between groups.