Objectives: To verify medication-related osteonecrosis of the jaw (MRONJ) frequency among patients with plasma cell myeloma (PCM) that had been treated with bisphosphonates, to identify predisposing factors that could influence the development of osteonecrosis. Methods: This observational retrospective study was performed at the Department of Hematology of Hospital Center of Porto (CHUP), Portugal. Results: The study population (n = 112) had a 15.2% (n = 17) prevalence of osteonecrosis. Clinically, bone exposure was the most frequently observed sign, present in 100% (n = 17) of the patients, followed by inflammation in 82.4% (n = 14), orofacial pain in 70.6% (n = 12), suppuration in 47.1% (n = 8), and intra or extra-oral fistula in 17.6% (n = 3) of the cases. The most frequent triggering local factor was dental extraction (82.4%). There was a dependence between the presence of extractions and the development of MRONJ (p < 0.001) but not with the time elapsed from the initiation of infusions with BPs and dental extractions (p = 0.499). In the sample of patients with multiple myeloma (MM), 13.8% were found to be more likely to develop MRONJ after an extraction. Conclusions: The most common local predisposing factor was dental extraction. No dependence was observed between the development of osteonecrosis and the time elapsed from the beginning of treatment with bisphosphonates infusions to surgical procedures.

Background: Artificial intelligence (AI) is expected to play an increasingly important role in medicine and dentistry. While its diagnostic potential has been tested in various medical fields, limited research exists on its applications within oral medicine diagnoses using clinical images. Objective: This pilot study aimed to evaluate the diagnostic accuracy of ChatGPT, Gemini, and Copilot in identifying benign, potentially malignant, and malignant oral lesions. Methods: A cross-sectional study was conducted using clinical images from three categories: benign oromucosal conditions, oral potentially malignant disorders, and malignant oral lesions. Results: ChatGPT evaluated all images and consistently outperformed Copilot—and in some cases Gemini—across multiple diagnostic questions, with statistically significant advantages particularly in the cancer subgroup. Copilot showed the weakest performance, with high rates of missing evaluations and significantly lower proportions of correct responses in several analyses. Across both full-dataset and adjusted analyses, ChatGPT demonstrated the highest diagnostic performance overall. Diagnostic accuracy metrics for malignancy suspicion was similar for ChatGPT and Gemini. Several limitations such as sample size, lack of reproducibility testing and inability of some AI models to process images must be taken into account when interpreting the results. Conclusions: AI tools show promise but cannot yet replace clinical expertise. Further research and development are needed to improve the accuracy and applicability of AI diagnostic tools.

Tumor-associated macrophages are key components of the tumor microenvironment in oral carcinogenesis; however, their role is not yet fully understood. We aimed to characterize the expression of macrophage (M) markers across the spectrum of oral carcinogenesis, including oral leukoplakias (OL) and oral squamous cell carcinomas (OSCCs). This immunohistochemical study analyzed the macrophage density (cells/mm²) based on the expression of CD68 (pan-macrophage), CD163 (M2), and CD80 (M1) in 81 samples, including healthy mucosa (n = 16), OL (n = 30), and OSCC (n = 35), in both epithelial and subepithelial compartments. All markers showed a progressive increase across the study groups, with significantly higher densities in OSCC than in healthy mucosa (p < 0.001), consistently higher in the subepithelial compartment. CD163 was the most expressed marker (increasing from 78.96 cells/mm² in healthy mucosa to 300.56 cells/mm² in OSCC), whereas CD80 was the least abundant, particularly in OSCC (35.66 cells/mm² in healthy tissue to 188.49 cells/mm² in OSCC). No significant associations were observed between biomarker expression and clinicopathological variables. These results support the involvement of macrophages during oral carcinogenesis, particularly CD163+ (M2) cells, and highlight the potential prognostic and therapeutic relevance of these markers.