Alexander Maniangat Luke

Despite the growing availability of anonymized medical imaging datasets, dental data remains largely unavailable due to persistent concerns over person re-identification, posing a barrier to training large-scale models for dental tasks. Unlike commercial solutions, recent academic studies seldom attempt to compose a multi-purpose end-to-end dental framework, primarily due to this data scarcity and the complexity of combining diagnosis and treatment tasks. To address these issues, we present the Ajman University Orthopantomography (AU-OPG) Dataset, a panoramic X-ray dataset annotated for the tasks of teeth detection, diagnosis, and radiographic-evidence-based treatment planning. To the best of our knowledge, AU-OPG is the first publicly described dental dataset that combines diagnostic and treatment-planning labels, and the first to provide tooth-aligned oriented bounding boxes. We also propose a detection-then-classification framework that uses two Masked Autoencoders (MAEs) for tooth and neighborhood feature extraction, respectively. These are combined with a depth-wise neural network that takes three heterogeneous channel inputs, providing positional information that enables the model to implicitly utilize the location of a tooth for its class prediction. The proposed framework achieves competitive performance with test weighted F1-scores of 0.85 and 0.88 for diagnosis and treatment planning, respectively, although the minority treatment categories of filling and root canal remain challenging. This work provides a foundation for open-source radiographic decision-support tools that assist, rather than replace, the dentist’s broader clinical workflow. The dataset and source code are available at https://github.com/akvnn/guiding-neural-nets.

BACKGROUND AND AIM: This study explores the in vitro antitumor effects of clotrimazole, a well-established antifungal agent, on CAL-27 and UM 1 human OSCC cell lines. MATERIAL AND METHODS: Employing the MTT assay, we observed a dose-dependent reduction in cell viability following clotrimazole treatment, indicative of its potential cytotoxicity against OSCC cells. Results and conclusion: Flow cytometry analysis revealed a substantial increase in apoptotic cells, suggesting a pronounced pro-apoptotic effect. Concurrently, clotrimazole induced alterations in cell cycle progression, indicating a potential cytostatic impact on OSCC cells. Western blot analysis provided mechanistic insights, revealing changes in the expression of key regulatory proteins associated with apoptosis (e.g., caspases) and cell cycle control (e.g., cyclins and CDKs). Notably, clotrimazole exhibited a modulatory effect on signaling pathways implicated in cancer cell survival and proliferation, including the PI3K/Akt and MAPK pathways. These findings contribute to the growing body of evidence supporting clotrimazole's potential as an antitumor agent. The multifaceted impact of clotrimazole on OSCC cells, as demonstrated in this study, underscores its potential as a promising candidate for future OSCC therapeutic strategies.

Objective: The evidence on postoperative pain and clinical outcomes in patients receiving primary non-surgical root canal therapy with bioceramic vs. resin-based sealers was compiled in this comprehensive review from systematic reviews and meta-analyses. Methods: The review followed PRISMA 2020 guidelines and was registered in PROSPERO (CRD42023461029). Systematic reviews included randomized or quasi-randomized trials of adult patients having treatment with either sealer type for postoperative pain, and used validated scales. Screening, data extraction, and quality assessment by A MeaSurement Tool to Assess systematic Reviews 2 (AMSTAR-2) were completed independently by two reviewers and review overlap was measured with the Corrected Covered Area (CCA). Where feasible, de novo random-effects meta-analyses were conducted to estimate standardized mean differences (SMD) in pain at 24 and 48 h. Heterogeneity was measured using the I ² statistic and certainty of evidence with GRADE. Results: Seven reviews (2020–2024) met eligibility, five with quantitative synthesis. Pooled analyses showed no significant differences in pain between sealer types within the first 6–48 h. Detected differences were small and clinically negligible. Both sealers showed similar analgesic use and flare-up rates. Methodological quality ranged from moderate to low; certainty of evidence for early pain was moderate and low for pain at >48 h due to study inconsistency and imprecision. Conclusions: Bioceramic sealers offer only a minimal, clinically insignificant reduction in early postoperative pain compared to resin-based sealers. Both nevertheless remain suitable options for reducing patient discomfort. Future studies should standardize pain evaluation, include retreatment cases, and explain clinically significant findings. Systematic Review Registration: https://www.crd.york.ac.uk/PROSPERO/view/CRD42023461029 , PROSPERO CRD42023461029.

Background: Artificial intelligence (AI), mainly AI‐driven chatbots and large language models (LLMs) is reshaping dental education through adaptive, interactive, and simulation‐based learning. While the transition in technology has been rapid, the evidence about the educational effectiveness of these technologies is still very diverse and not entirely directed. Aim: To analyze the roles, educational effectiveness, and impact of integrating AI‐driven chatbots and LLMs in dental education at the university level with a focus on learning outcomes and implementation practices. Methods: The researchers conducted a thorough search of the electronic databases PubMed/MEDLINE, Scopus, Web of Science, and Embase for articles published from January 2018 to November 2025. This review met the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses (PRISMA) 2020 criteria and was made up of original research articles on dental studentsand educators who were using AI‐based chatbots as interventions. The outcomes measured were knowledge gain, clinical reasoning, diagnostic accuracy, communication skills, and engagement of learners. Due to the differences in the methodologies used the authors opted for a narrative synthesis approach. Results: Six studies met the eligibility criteria and showed potential benefits of AI‐driven chatbots and LLMs for diagnostic reasoning, learning performance, engagement, and individualized feedback although methodological and outcome heterogeneity limited direct comparison. Conclusion: AI‐driven chatbots and LLMs may complement university‐level dental education, but their effectiveness and safe implementation require further rigorous evaluation.

Background: Artificial intelligence (AI) is unraveling new paths for dentistry by improving diagnostic accuracy. This is streamlining treatment planning and optimizing clinical workflows. Yet, its integration brings forth crucial ethical, legal, and regulatory challenges, which range from safeguarding patient autonomy and data privacy to addressing algorithmic bias, ensuring transparency, and maintaining professional accountability. Objective: This systematic review brings together existing evidence on the ethical and legal aspects of technology‐driven dentistry. Methods: In accordance with Preferred Reporting Items for Systematic Reviews and Meta‐Analyses (PRISMA) 2020 guidelines, five electronic databases, along with official sources (FDA, EU Commission, and FDI) published from 2019 to August 2025. Eligible studies focused on the ethical, legal, or regulatory dimensions of digital technologies in dentistry. Data were extracted and thematically organized into five domains: patient autonomy and informed consent, data privacy and security, bias and fairness, transparency and accountability, and regulatory/legal frameworks. The Mixed Methods Appraisal Tool (MMAT) was used to evaluate the risk of bias. Results: A total of 16 records met the inclusion criteria, and the findings emphasize the need to protect patient rights, ensure clinician readiness, and align with international and regional regulations (EU AI Act, FDA, and FDI). Policy frameworks offered reliable guidance, while surveys and commentaries carried moderate bias. Conclusion: The use of digital technologies in dentistry requires a balanced approach with clear frameworks, global guidelines, and targeted clinician training that are essential to ensure patient‐centered, fair, and legally compliant adoption in modern dental care.

Short-chain fatty acids (SCFAs), primarily acetate (C2), propionate (C3), and butyrate (C4), are crucial microbial metabolites formed by the fermentation of dietary fibers by gut microbiota in the colon. These SCFAs, characterized by fewer than six carbon atoms, serve as an essential energy source for colonic epithelial cells and contribute approximately 10% of the body's total energy requirement. They are central to maintaining gut health through multiple mechanisms, including reinforcing intestinal barrier function, exerting anti-inflammatory effects, regulating glucose and lipid metabolism, and influencing host immune responses. Butyrate, in particular, plays a pivotal role in protecting the gut mucosa and modulating inflammatory processes. Beyond their intestinal functions, SCFAs affect systemic metabolic outcomes such as body weight regulation and appetite control by modulating the secretion of gut hormones and interacting with G-protein coupled receptors. Despite strong experimental evidence, mainly from animal models, clinical applications of SCFA modulation remain in preliminary stages, with limited translational findings in human therapeutics.In parallel, the oral microbiome also produces SCFAs, such as propionic, butyric, isobutyric, and isovaleric acids, as metabolic by-products in biofilm ecosystems like dental plaque. These acids contribute to interspecies communication, “cross-feeding” dynamics, and possibly biofilm stability or pathogenicity, especially in caries and periodontal disease. SCFAs in the oral cavity may act as signaling molecules or competitive factors, modulating microbial behavior and ecological balance within the oral niche. Collectively, these insights highlight SCFAs as integral to host-microbiota interactions, both in the gut and oral environments, with potential implications for targeted microbiome-based therapies in health and disease.

Purpose Differences in enamel density and thickness influence caries risk, emphasising their role in targeted early childhood caries (ECC) prevention. This study aims to compare the enamel thickness and density of unaffected enamel in primary teeth with ECC to that of caries-free (non-ECC) primary teeth using micro-computed tomography. Methods A total of 128 primary teeth were analysed and divided into two groups: Group I (unaffected surface of the enamel of primary teeth with ECC) and Group II (healthy teeth). Enamel thickness and density of healthy surfaces of both groups were measured using a μCT 100 system, and differences between groups were statistically evaluated using the Mann–Whitney U test. Results Enamel thickness was significantly higher in Group I (0.973 mg HA/ccm) compared to Group II (0.553 mg HA/ccm), with a statistically significant difference (p = 0.001). The mean enamel density in Group I was 2255.75 µm compared to 2294.71 µm in Group II (p = 0.001). In both the maxilla and mandible, Group II (healthy teeth) surfaces had higher enamel density (p = 0.001), whilst enamel thickness showed no significant difference. Amongst anterior teeth, Group II teeth surfaces exhibited significantly higher enamel density (p = 0.003). Conclusion Enamel density, more than enamel thickness, emerges as a key indicator of ECC risk, enabling paediatric dentists to more accurately predict and identify vulnerable tooth surfaces before the onset of visible caries.

Chronic kidney disease (CKD) is a universal health concern, with CBD- 28k (calbindin-D28k) being 1 alpha, 25-dihydroxyvitamin D3-dependent calcium-binding protein, playing a role in kidney function. Renal dialysis may alter calbindin-D28k levels, impacting oral health and periodontal health. Understanding these impacts is crucial for managing CKD. This study aimed to explore the potential of salivary calbindin-D28k as a predictor of oral health in subjects with CKD. This case–control study involved 200 individuals aged 24 to 77 years, out of which 100 were undergoing CKD treatment. Biochemical parameters were recorded, and unstimulated saliva samples were collected. Decayed, Missing and Filled Teeth and periodontal scores were noted after clinical examination. Salivary calbindin-D28k level was estimated by immunosorbent assay (enzyme-linked immunosorbent assay). A two-tailed test of p-value of < 0.05 was used to determine statistics. Demographic parameters showed a significant age and gender difference between the groups. Significant variation in the level of hematological and biochemical parameters between the groups was observed. Renal function test and liver function test levels varied significantly in CKD patients. Notable difference in the level of salivary calbindin-D28k levels and periodontal scores revealed poor oral health. The best cutoff value for calbindin-D28k was obtained from the receiver operating characteristic curve indicating a risk of poor oral health in CKD subjects. Additionally, salivary calbindin-D28k levels and oral health showed significant association and correlation. The current research findings suggest that monitoring salivary calbindin-D28k levels could serve as an important predictor of oral health in CKD subjects highlighting the importance of complete oral health management in subjects with CKD.