Large Language Models (LLMs) are artificial intelligence (AI) systems that simulate human language processing through deep learning techniques and neural networks. They are increasingly utilized for clinical decision support, student training, and enhancing educational processes. However, the reliability of AI models, especially in answering various types of questions, remains a point of debate. Standard multiple-choice questions (MCQs) involve selecting one correct answer from five options, whereas combination-type MCQs (C-MCQs) identify all correct statements among several alternatives. This study aims to evaluate and compare the performance of various LLMs in answering MCQs and C-MCQs in endodontics. A total of 151 endodontic questions were identified through a comprehensive review of publicly available Dentistry Specialty Exams in Turkey conducted since 2012. The questions were presented to eight LLMs (ChatGPT-4o, ChatGPT-4, Gemini 1.5 Flash, Gemini 1.5 Pro, Gemini 2.0 Flash, Copilot, Deepseek-V3, and Qwen2.5-Max) in Turkish. Accuracy rates for both MCQs and C-MCQs were statistically analyzed using SPSS v23 (p < 0.05). ChatGPT-4o achieved the highest overall accuracy rate (81.5%), while Gemini 1.5 Flash had the lowest (57%). In standard MCQs, ChatGPT-4o significantly outperformed the other models (p < 0.001), but in C-MCQs, no significant difference was observed between the models (p = 0.179). Across all models, accuracy rates for C-MCQs were significantly lower than for MCQs (p < 0.05). Deepseek-V3 maintained a more balanced performance across question types than the other models. LLMs show promising potential as educational tools in endodontics. However, their accuracy varies by question type and model. They can support student learning and clinical decision-making but cannot yet be considered a fully reliable standalone source in endodontics.

Background: Oral and systemic health are strongly associated with individuals’ quality of life and sleep quality, both of which are increasingly recognized as important patient-reported outcomes in dentistry. Aim: This prospective longitudinal observational cohort study aimed to compare changes in oral health related quality of life (Oral Health Impact Profile-14; OHIP-14) and sleep quality (Pittsburgh Sleep Quality Index; PSQI) following endodontic and periodontal treatments. Methods: A total of 74 patients who received endodontic treatment and 90 who underwent periodontal treatment completed the OHIP-14 and PSQI questionnaires before and three weeks after treatment. Data were analyzed using the Wilcoxon signed-rank test for within-group comparisons and the Mann–Whitney U test on change scores (post−pre) for between-group comparisons, with Holm correction applied for multiple subdomain tests. ANCOVA was additionally performed as an exploratory sensitivity analysis because the homogeneity-of-regression-slopes assumption was violated for both outcomes (p < 0.05). Results: Both treatments significantly improved OHIP-14 scores and most PSQI components; however, no significant change was observed in sleep medication use in the periodontal group. Functional limitation improved more in the periodontal group, whereas handicap improved more in the endodontic group. Baseline PSQI scores were significantly higher in the endodontic group. PSQI subdomains improved in both groups, with no significant between-group differences after Holm correction. Similarly, no significant differences were found between groups in overall OHIP-14 and PSQI scores. Conclusions: Endodontic and periodontal treatments were associated with short-term improvements in individuals’ quality of life and sleep quality. While periodontal treatment may provide greater benefits in certain quality-of-life domains, endodontic treatment may offer advantages in others. Both treatments appear to support improvements in sleep-related outcomes. These findings may contribute to patient-centered clinical decision-making.

Endo-Periodontal Lesions (EPLs) are complex conditions that significantly affect tooth prognosis and require accurate diagnosis and coordinated endodontic-periodontal management. However, evidence regarding diagnostic awareness and knowledge related to EPLs among dental students and dentists remains limited. This study aimed to evaluate diagnostic awareness, disease-related knowledge, educational perceptions, and self-reported clinical practices regarding EPLs across different educational and professional levels. This cross-sectional study included 584 dental students and dentists who completed a 20-item online questionnaire regarding EPL-related awareness, knowledge, educational perceptions, and clinical practices. Comparisons were performed across educational and professional groups. Awareness, perceived knowledge, and self-reported clinical practices regarding EPLs varied across educational and professional levels. Clinical-stage students reported greater familiarity with EPL-related concepts and higher diagnostic confidence than preclinical students. Specialist dentists demonstrated greater clinical involvement with EPLs and greater familiarity with contemporary classification systems than general dentists. Clinical training stage remained independently associated with self-reported ability to identify EPLs. Self-reported awareness, perceived knowledge, and reported clinical practices regarding EPLs differ according to educational and professional experience. Clinical training appears to play an important role in improving diagnostic familiarity and confidence. These findings highlight the importance of structured and integrated educational approaches to improve the recognition and management of EPLs in both undergraduate and postgraduate dental training.

Objectives: Traumatic dental injuries (TDIs) are frequent in clinical practice and require rapid, guideline‐based decisions, yet accessing accurate and reliable information may be challenging. Large language models (LLMs) such as ChatGPT, Gemini, DeepSeek, and Qwen are increasingly used as quick online information tools; however, evidence regarding their accuracy, consistency, and the influence of different user interfaces is limited. This study aimed to evaluate the performance of several LLMs in answering TDI‐related questions through both web‐based interfaces and mobile phone applications. Material and Methods: Twenty questions were prepared according to the 2020 International Association of Dental Traumatology (IADT) guidelines, including 10 open‐ended and 10 yes–no items. Four LLMs (ChatGPT‐4o, DeepSeek‐V3, Gemini 2.0 Flash, Qwen2.5‐Max) were queried simultaneously via web and mobile interfaces over five consecutive days, generating 800 responses. Open‐ended answers were assessed using the Global Quality Score (GQS) and modified DISCERN (mDISCERN), while yes–no responses were compared with a predetermined answer key. Statistical analyses were performed using IBM SPSS v23.0, with significance set at p < 0.05. Results: Qwen2.5‐Max demonstrated comparatively higher GQS and mDISCERN scores across both interfaces. Accuracy for yes–no questions ranged from 86% to 91% without significant differences among models. Interface comparisons showed that ChatGPT‐4o generated comparatively higher‐quality responses on the web, whereas Qwen2.5‐Max performed better on mobile. Over the 5‐day period, Qwen2.5‐Max showed relatively higher temporal consistency, while DeepSeek‐V3 exhibited notable day‐to‐day variation. Conclusions: LLMs may serve as useful supplementary tools for providing guideline‐based information on TDIs, especially for straightforward, closed‐ended clinical questions. However, their performance varies by model, interface, and question type. Qwen2.5‐Max demonstrated comparatively higher performance across several evaluated measures. Despite these results, LLM‐generated information should be interpreted cautiously and verified by dental professionals before being used in clinical decision‐making.

Conventional root canal treatment eliminates infection in necrotic permanent teeth but does not restore the dentin–pulp complex. The clinical predictability of regenerative endodontic treatment in mature teeth remains uncertain. This study evaluated the clinical and radiographic outcomes of an injectable platelet-rich fibrin (i-PRF)-supported regenerative protocol in mature necrotic teeth. This retrospective two-center cohort study included mature permanent teeth presenting with pulp necrosis, closed apices, and periapical lesions with a periapical index (PAI) score ≥ 3 treated between 2022 and 2025 using a standardized i-PRF–supported regenerative endodontic treatment protocol. Periapical healing was assessed using PAI scores, with cone-beam computed tomography (CBCT) images serving as supplementary three-dimensional illustrations. Postoperative pain was recorded using the Visual Analog Scale (VAS). Statistical analysis was performed using the Wilcoxon signed-rank test, Friedman test with Dunn post hoc analysis, logistic regression, and receiver operating characteristic (ROC) curve analysis. A total of 27 teeth were included, with a mean follow-up of 22.5 months. Clinical success was achieved in 24 teeth (88.9%). Mean PAI scores decreased significantly from 4.3 ± 0.78 preoperatively to 1.07 ± 1.57 at follow-up (p < 0.001). CBCT images showed radiographic evidence of three-dimensional periapical healing. Postoperative pain was minimal, with median scores reaching zero within 72 h and no need for analgesic medication. No significant predictors of treatment failure were identified. Within the limitations of this two-center retrospective study, i-PRF–supported regenerative endodontic treatment in mature necrotic teeth demonstrated favorable clinical outcomes, periapical healing, and low postoperative pain, suggesting its potential as a biologically based management approach.

Endo-perio lesions (EPLs), arising from the close anatomical and pathophysiological relationship between pulpal and periodontal tissues, may markedly impai