Research, Society and Development, v. 15, n. 9, e3415951521, 2026 (CC BY 4.0) | ISSN 2525-3409 | DOI: http://dx.doi.org/10.33448/rsd-v15i9.51521 The use of Artificial Intelligence in Dentistry: Applications, challenges, and future perspectives A utilização da Inteligência Artificial na Odontologia: Aplicações, desafios e perspectivas futuras Uso de la Inteligencia Artificial en Odontología: Aplicaciones, desafíos y perspectivas futuras Received: 07/31/2026 | Accepted: 09/09/2026 | Published: 09/10/2026 Glayson Pereira Vitor ORCID: https://orcid.org/0000-0002-0618-9428 Faculdade Ciências Médicas de Minas Gerais, Brazil E-mail:glayson.vitor@cienciasmedicasmg.edu.br Abstract Background: Artificial intelligence [AI] has enhanced contemporary dental practice by providing advanced tools for diagnosis, treatment planning, and patient management. Objective: This narrative review examines the current applications of AI in dentistry, evaluates its diagnostic efficacy, identifies challenges for clinical implementation, and discusses future perspectives. Methods: A narrative literature review was conducted by searching PubMed, Scopus, Web of Science, SciELO, and LILACS for studies published between 2020 and 2026. Observational studies randomized clinical trials, systematic reviews, and methodological studies were included. DeCS/MeSH descriptors were combined using the Boolean operators AND and OR. Study selection was purposive, prioritizing recent publications with higher methodological quality and scientific relevance. Results: AI demonstrated high accuracy in detecting dental caries, periapical lesions, periodontal diseases, and other oral conditions. Applications span all dental specialties, including radiology, endodontics, orthodontics, periodontics, and oral and maxillofacial surgery. Despite these advancements, significant barriers persist, including ethical concerns regarding patient privacy, the need for rigorous clinical validation, and integration into existing clinical workflows. AI should be considered a complementary tool that enhances clinician capabilities rather than a substitute for clinical judgment. The future of dentistry will involve the integration of explainable AI systems, federated learning for data protection, and digital education for the dental workforce. Conclusion: AI holds transformative potential to improve access, quality, and efficiency in dental care, provided it is implemented with methodological rigor, continuous human oversight, and appropriate ethical considerations. Keywords: Artificial Intelligence; Dentistry; Machine learning; Dental diagnosis; Deep learning. Resumo A inteligência artificial (IA) tem impulsionada a prática odontológica contemporânea, oferecendo ferramentas avançadas para diagnóstico, planejamento de tratamento e gestão de pacientes. Objetivo: Esta revisão narrativa examina as aplicações atuais da IA na odontologia, sua eficácia diagnóstica, os desafios para implementação clínica e as perspectivas futuras. Métodos: foi realizada uma revisão narrativa da literatura por meio da busca de estudos publicados entre 2020 e 2026 nas bases de dados PubMed, Scopus, Web of Science, SciELO e LILACS. Foram incluídos estudos observacionais, ensaios clínicos randomizados, revisões sistemáticas e estudos metodológicos. Utilizou descritores DeCS/ MeSH combinados pelos operadores booleanos AND e OR, a seleção dos estudos foi intencional, priorizando publicações recentes de maior qualidade metodológica e relevância científica. Resultados: A IA demonstrou alta acurácia na detecção de cáries dentárias, lesões periapicais, doenças periodontais e outras condições orais. As aplicações abrangem todas as especialidades odontológicas, incluindo radiologia, endodontia, ortodontia, periodontia e cirurgia bucomaxilofacial. Apesar dos avanços, barreiras significativas persistem, incluindo questões éticas relacionadas à privacidade do paciente, necessidade de validação clínica rigorosa e integração aos fluxos de trabalho existentes. A IA deve ser considerada uma ferramenta complementar que aumenta as capacidades dos profissionais, não um substituto para o julgamento clínico. O futuro da odontologia envolverá a integração de sistemas de IA explicáveis, aprendizado federado para proteção de dados e educação digital da força de trabalho odontológica. Conclusão: IA possui potencial transformador para melhorar o acesso, qualidade e eficiência do cuidado odontológico, desde que implementada com rigor metodológico, supervisão humana contínua e considerações éticas apropriadas. Palavras-chave: Inteligência Artificial; Odontologia; Aprendizado de máquina; Diagnóstico dental; Aprendizado profundo. 1 Research, Society and Development, v. 15, n. 9, e3415951521, 2026 (CC BY 4.0) | ISSN 2525-3409 | DOI: http://dx.doi.org/10.33448/rsd-v15i9.51521 Resumen Antecedentes: La inteligencia artificial [IA] ha potenciado la práctica odontológica contemporánea al proporcionar herramientas avanzadas para el diagnóstico, la planificación del tratamiento y la gestión de pacientes. Objetivo: Esta revisión narrativa examina las aplicaciones actuales de la IA en odontología, evalúa su eficacia diagnóstica, identifica los desafíos para su implementación clínica y discute las perspectivas futuras. Métodos: Se realizó una revisión narrativa de la literatura mediante búsquedas en PubMed, Scopus, Web of Science, SciELO y LILACS para estudios publicados entre 2020 y 2026. Se incluyeron estudios observacionales, ensayos clínicos aleatorizados, revisiones sistemáticas y estudios metodológicos. Los descriptores DeCS/MeSH se combinaron utilizando los operadores booleanos AND y OR. La selección de estudios fue intencional, priorizando las publicaciones recientes con mayor calidad metodológica y relevancia científica. Resultados: La IA demostró una alta precisión en la detección de caries dentales, lesiones periapicales, enfermedades periodontales y otras afecciones orales. Las aplicaciones abarcan todas las especialidades odontológicas, incluyendo radiología, endodoncia, ortodoncia, periodoncia y cirugía bucal y maxilofacial. A pesar de estos avances, persisten barreras significativas, entre ellas las preocupaciones éticas respecto a la privacidad del paciente, la necesidad de una validación clínica rigurosa y la integración en los flujos de trabajo clínicos existentes. La IA debe considerarse una herramienta complementaria que potencia las capacidades del clínico, en lugar de un sustituto del juicio clínico. El futuro de la odontología implicará la integración de sistemas de IA explicable, aprendizaje federado para la protección de datos y educación digital para el personal odontológico. Conclusión: La IA posee un potencial transformador para mejorar el acceso, la calidad y la eficiencia en la atención odontológica, siempre que se implemente con rigor metodológico, supervisión humana continua y las consideraciones éticas pertinentes. Palabras clave: Inteligencia Artificial; Odontología; Aprendizaje automático; Diagnóstico dental; Prendizaje profundo. 1. Introduction Artificial Intelligence [AI] refers to the capability of machines to execute tasks that traditionally require human intelligence (Schwendicke et al., 2020). In healthcare, particularly in dentistry, AI has emerged as a transformative technology with the potential to revolutionize diagnosis, treatment planning, and patient management (Samaranayake et al., 2025; Shan et al., 2021). A core subdomain of AI is machine learning [ML], which teaches intrinsic statistical patterns within data to make predictions on unseen datasets (Schwendicke et al., 2020). Deep learning [DL], a subset of ML, utilizes multilayered mathematical operations to learn and infer from complex data structures, such as radiographic images (Schwendicke et al., 20201; Shan et al., 2021). While truly autonomous medical robotic systems remain beyond current reach, the virtual component of AI, namely software-based algorithms, constitutes the primary application currently used in dentistry (Shan et al., 2021). Recently, the evolution of Generative Artificial Intelligence [GAI], particularly through Large Language Models [LLMs], has significantly expanded the scope of AI applications in dentistry. Unlike traditional algorithms designed for image classification, these models support activities such as clinical documentation, education, patient communication, and scientific writing, although they have limitations in data reliability and traceability (Samaranayake et al., 2025). Dental professionals are increasingly relying on AI technology to assist in diagnosis, clinical decision-making, treatment planning, and prognostic prediction across ten dental specialties (Bonny et al., 2023). One of the most significant advantages of AI in dentistry is its ability to analyze large volumes of data rapidly and accurately, providing practitioners with valuable insights to enhance their decision-making processes (Bonny et al., 2023; Ahmed et al., 2021). Despite the growing volume of publications, there remains a shortage of reviews that critically integrate image-based AI advancements with emerging generative AI applications in dental practice. Therefore, this narrative review aims to examine the current applications of AI in dentistry, evaluate its diagnostic and therapeutic efficacy, identify challenges for clinical implementation, and discuss the future perspectives of this emerging technology. 2 Research, Society and Development, v. 15, n. 9, e3415951521, 2026 (CC BY 4.0) | ISSN 2525-3409 | DOI: http://dx.doi.org/10.33448/rsd-v15i9.51521 2. Methodology A study with a qualitative approach (Risemberg et al., 2026a; Pereira et al., 2018) was conducted as an exploratory study with limited systematization (Risemberg et al., 2026b). A narrative literature review (Ogassawara et al., 2025; Fernandes, Vieira & Castelhano, 2023) was conducted by searching the PubMed/MEDLINE, Scopus, and Web of Science databases using the descriptors "Artificial Intelligence", "Dentistry", "Machine Learning", and "Deep Learning", combined via the Boolean operators AND and OR. Articles published between January 2020 and June 2026 in English, Portuguese, and Spanish addressing clinical applications of artificial intelligence in dentistry were included. The study selection was purposive, prioritizing systematic reviews, meta-analyses, clinical validation studies, consensus documents, and recent high-impact articles relevant to AI applications in dentistry. Screening was conducted by evaluating titles, abstracts, and subsequently full-text articles. Selected studies were analyzed based on their methodological design and target population. This strategy allowed for the synthesis of high-impact scientific evidence and clinical relevance without attempting to exhaustively map the entire available literature. This study utilized ChatGPT [OpenAI (GPT-5.5)] as a supporting tool for text organization, grammatical review, and structural suggestions. The AI tool was not used to generate scientific content or interpret data. All scientific content was reviewed by the author and grounded exclusively in reliable bibliographical references. 3. Results The search strategy identified many records across the databases consulted. Given the narrative nature of this review, a purposive selection of studies with the highest methodological relevance and scientific impact was performed, resulting in the inclusion of 31 articles that form the basis of this synthesis [Table 1]. Thus, the articles represent a qualitative sample of the primary available evidence rather than a quantitative mapping of total scientific production on the topic. High methodological heterogeneity was observed among the studies, particularly in the datasets used, validation criteria, algorithm types, and imaging modalities, which hindered direct comparisons of outcomes. Table 1. Studies on artificial intelligence applications in dentistry were published between 2020 and 2026. Author (Year) Study Design Dental Specialty AI Application Key Findings Limitations Shan et al. [2021] Narrative review General Machine Learning & Deep Learning CNNs exhibit high diagnostic performance in dental imaging. Shortage of multicenter studies. Bonny et al. [2023] Narrative review General Clinical applications AI improves diagnosis, treatment planning, and clinical management. Regulatory barriers. Ahmed et al. [2021] Systematic review General AI applications High diagnostic accuracy across several specialties. Substantial methodological heterogeneity. Zaborowicz et al. [2025] Systematic review Radiology Panoramic radiographs AI detects oral diseases with high precision. Need for standardization. Ezhov et al. [2021] Development study Radiology CBCT System performance is comparable to specialists. Retrospective database. Arzani et al. [2025] Umbrella review Radiology Caries Sensitivity ≈85%; specificity ≈90%. High heterogeneity. Surlari et al. [2023] Narrative review General Clinical applications Highlights scientific and technological challenges. Few prospective studies. Shujaat et al. [2025] Narrative review Radiology FDA-approved software Growth of commercial clinical AI. Limited clinical evidence. 3 Research, Society and Development, v. 15, n. 9, e3415951521, 2026 (CC BY 4.0) | ISSN 2525-3409 | DOI: http://dx.doi.org/10.33448/rsd-v15i9.51521 Sezen-Hulsmans et al. [2026] Scoping review Operative Dentistry Caries diagnosis AI assists in clinical decisionmaking. Need for clinical trials. Li et al. [2026] Review Public Health Oral health management AI improves public health decision-making. Ethical and regulatory barriers. Uribe et al. [2025] Scoping review Education Generative AI LLMs transform dental education. Few educational protocols. Thurzo et al. [2023] Review Education Dental curriculum AI promotes personalized learning. Need for faculty training. Schwendicke & Büttner [2023] Editorial General Advancements & challenges Critical discussion on benefits and risks. No primary data. Umer et al. [2024] Scoping review Generative AI LLMs Clinical documentation and education. Hallucinations and biases. Huo et al. [2025] Methodological guideline Research Reporting Generative AI studies Proposes recommendations for scientific transparency. Does not evaluate clinical performance. Ma et al. [2025] Review Generative AI Clinical applications Great potential in teaching, research, and healthcare. Ethical issues. Zhang et al. [2025] Systematic review Prosthodontics Patient instructions LLMs improve clinical communication. Requires clinical validation. Brozovic et al. [2024] Observational study Education Bing Chat Satisfactory performance on dental exams. Variable accuracy. Umer & Adnan [2024] Review Generative AI Synthetic data AI can generate research databases. Ethical questions and validation. Najeeb & Islam [2025] Narrative review Restorative Dentistry CAD/CAM, restorative planning AI increases restorative predictability. Need for clinical studies. Li et al. [2022] Validation study Endodontics/Ope rative Caries & apical periodontitis High diagnostic accuracy. External validation required. Pitchika et al. [2024] Narrative review Periodontics Personalized diagnosis AI enables risk stratification and prognosis. Few prospective studies. Vázquez-Sebrango et al. [2025] Systematic review Implantology Implant planning AI improves anatomical segmentation and planning. Clinical evidence remains limited. Gao et al. [2025] Narrative review General Diagnosis & treatment Updates diagnostic and therapeutic applications. Multicenter validation needed. Di Cosola et al. [2025] Narrative review General Applications & challenges Broad discussion on ethical and technological aspects. Few clinical studies. Saikia et al. [2025] Overview of reviews General Evidence synthesis Confirms high diagnostic performance of AI. Methodological variability across reviews. Ma et al. [2026] Review Generative AI Future perspectives Consolidates clinical applications of LLMs. Rapidly evolving field. Khurshid et al. [2026] Review Methodology AI Guidelines Recommends checklists for AI research. Does not address clinical applications. Shariff et al. [2025] Review General Clinical applications Analyzes trends and gaps for future research. Shortage of prospective studies. Source: Prepared by the Author. The analyzed literature demonstrated a broad expansion of AI applications in dentistry, with a predominance of studies focused on diagnostic imaging, particularly dental radiology, alongside growing interest in applications for periodontics, implantology, dental education, and generative artificial intelligence. 4 Research, Society and Development, v. 15, n. 9, e3415951521, 2026 (CC BY 4.0) | ISSN 2525-3409 | DOI: http://dx.doi.org/10.33448/rsd-v15i9.51521 4. Discussion Recent literature demonstrates a significant expansion of AI applications across virtually all dental specialties, consolidating this technology as a promising tool for diagnostic support, therapeutic planning, and clinical monitoring (Cosola et al., 2025; Shan et al., 2021; Schwendicke et al., 20201). AI encompasses various computational approaches that simulate human cognitive functions such as learning, pattern recognition, and decision-making (Shan et al., 2021; Ezhov et al., 2021). Among these approaches, ML stands out as a paradigm in which algorithms are trained on data to identify patterns and generate predictions without explicit task-specific programming. A more advanced subset of ML is Deep Learning [DL], which is based on artificial neural networks composed of multiple processing layers (Samaranayake et al., 2025; Gao et al., 2025; Pitchika et al., 2024). This architecture allows the algorithm to automatically learn complex patterns from large datasets without requiring manual feature selection, making it exceptionally efficient for analyzing medical and dental images (Samaranayake et al., 2025; Gao et al., 2025; Shan et al., 2021). In dentistry, DL models known as Convolutional Neural Networks [CNNs]algorithms specialized in image analysis— have demonstrated high performance in detecting caries, periapical lesions, periodontal bone loss, fractures, and other abnormalities in radiographic and tomographic examinations, achieving accuracy comparable to specialists in several studies (Pitchika et al., 2024; Shan et al., 2021; Schwendicke et al., 2020). The evaluated studies show that DL-based algorithms, particularly CNNs, exhibit diagnostic performance comparable to that of experienced dental surgeons across various image interpretation tasks (Samaranayake et al., 2025; Schwendicke et al., 2020; Pitchika et al., 2024) Consequently, dental radiology currently represents the area of greatest AI development. Models trained on periapical, panoramic, and cone-beam computed tomography [CBCT] images have shown high capability in identifying carious lesions, periapical changes, periodontal bone loss, impacted teeth, and other maxillofacial pathologies. Beyond increasing diagnostic sensitivity, these systems help reduce inter-examiner variability and standardize image interpretation, promoting greater clinical reproducibility and serving as an important decision-support tool for the dentist (Samaranayake et al., 2025; Arzani et al., 2025; Zaborowicz et al., 2025; Shujaat et al., 2025). The detection of carious lesions represents another extensively studied application with advanced clinical maturity. Recent systematic reviews and meta-analyses demonstrate that DL algorithms, specifically CNNs, possess high diagnostic capacity for identifying caries across imaging modalities, with average sensitivities of approximately 85% and specificities of approximately 90%. These results highlight the potential of AI as a tool for early diagnosis, contributing to more standardized image interpretation and evidence-based treatment planning (Sezen-Hulsmans et al., 2026; Samaranayake et al., 2025; Arzani et al., 2025; Zaborowicz et al., 2025; Shujaat et al., 2025) Despite these promising results, the literature still highlights major methodological limitations that restrict widespread clinical implementation. Considerable heterogeneity exists across studies regarding the algorithms used, the size and representativeness of image repositories, diagnostic criteria, and model training and validation methods. These differences impede direct comparison of outcomes, compromise reproducibility, and limit the generalizability of algorithms to distinct populations, imaging equipment, and clinical contexts. This underscores the need for multicenter studies and standardized protocols for external validation before routine adoption in dental practice (Saikia et al., 2025; Pitchika et al., 2024; Ahmed et al., 2021; Surlari et al., 2023). Beyond radiology and cariology, consistent applications have been described in periodontics, endodontics, orthodontics, implantology, oral and maxillofacial surgery, forensic dentistry, and prosthodontics [Table 2]. 5 Research, Society and Development, v. 15, n. 9, e3415951521, 2026 (CC BY 4.0) | ISSN 2525-3409 | DOI: http://dx.doi.org/10.33448/rsd-v15i9.51521 Table 2. Primary applications of Artificial Intelligence across dental specialties. Dental Specialty AI Applications AI Technology Application stage Radiology Caries and periapical lesion diagnosis CNN Consolidated Orthodontics Automated cephalometric analysis CNN Consolidated Endodontics Periapical lesion diagnosis Deep Learning Consolidated Periodontics Bone loss and prognostic assessment Deep Learning Expanding Implantology Surgical planning Deep Learning Expanding Restorative Dentistry CAD/CAM, material selection, and restorative planning Generative AI & Deep Learning Expanding Oral Pathology Lesion classification CNN Emerging Dental Education LLMs, clinical case simulation, and exam question generation Generative AI Emerging Clinical Management Clinical documentation and electronic health records [EHR] LLMs Emerging Note: The clinical application stage was classified by the author based on the literature synthesis, considering the quantity and consistency of published studies, the availability of systematic reviews and meta-analyses, the level of clinical validation of the algorithms, and the current level of technology adoption in dental practice. This classification is descriptive and does not align with formal evidence-level classification systems such as GRADE or the Oxford Center for Evidence-Based Medicine. Abbreviations: AI, Artificial Intelligence; ML, Machine Learning; DL, Deep Learning; CNN, Convolutional Neural Network; LLM, Large Language Model; CBCT, Cone-Beam Computed Tomography; CAD/CAM, Computer-Aided Design/Computer-Aided Manufacturing; FDA, Food and Drug Administration. Source: Prepared by the Author. 4.1 Generative Artificial Intelligence One of the major shifts observed in recent years involves the incorporation of Generative Artificial Intelligence [GAI] into dental practice. Unlike traditional AI models that predominantly focus on image classification and interpretation, Large Language Models [LLMs]—such as ChatGPT, Gemini, Claude, and Microsoft Copilot—perform tasks in natural language processing, clinical document generation, educational material development, scientific research support, and clinical decisionmaking assistance. This evolution has significantly expanded the potential applications of AI in dentistry, particularly in education, research, clinical management, and patient communication (SE et al., 2025; Umer et al., 2024; Brozovic et al., 2024). In dental education, these tools are being utilized to construct simulated clinical cases, generate examination questions, design educational materials, and personalize learning. Within the clinical environment, they show potential to optimize patient charting, summarize electronic health records, and facilitate interprofessional and patient-provider communication (Ma et al., 2026; Khurshid et al., 2026; Zhang et al., 2025). However, LLMs exhibit major limitations, including the generation of incorrect information ["hallucinations"], biases derived from training datasets, and a lack of source traceability to substantiate their outputs. Consequently, it is recommended that their use remain restricted to supporting professional activities and never replace clinical judgment or therapeutic decisionmaking (Khurshid et al., 2026; Najeeb & Islam, 2025) The findings of this review reinforce the view that artificial intelligence is one of the most promising technologies for transforming contemporary dental practice. However, while high diagnostic performance is frequently emphasized in literature, clinical implementation still faces scientific, technological, regulatory, and ethical challenges (Li et al., 2026; Cosola et al., 2025; Surlari et al., 2023; Ahmed et al., 2021; Schwendicke et al., 2020). Overall, the analyzed studies demonstrate that AI offers important benefits for diagnosis, treatment planning, education, and clinical management, but implementation remains constrained by data quality, clinical validation, algorithm interpretability, ethical issues, and regulation (Li et al., 2026; 6 Research, Society and Development, v. 15, n. 9, e3415951521, 2026 (CC BY 4.0) | ISSN 2525-3409 | DOI: http://dx.doi.org/10.33448/rsd-v15i9.51521 Saikia et al., 2025; Bonny et al., 2023; Ahmed et al., 2021; Surlari et al., 2023). The primary advantages and challenges identified in the literature are synthesized in Table 3. Table 3. Advantages and limitations of Artificial Intelligence in Dentistry. Advantages Limitations/Challenges Clinical Implications Key References High accuracy in detecting caries, periapical lesions, and periodontal bone loss. Performance depends on the quality and diversity of datasets. Can increase diagnostic precision and favor early detection, provided it is validated across diverse populations. (Di Cosola et al., 2025; Pitchika et al., 2024; Shan et al., 2021) Reduction of inter-examiner variability. Discrepancies between equipment and image acquisition protocols. Promotes greater diagnostic standardization and improves exam reproducibility. (Umer et al., 2024; Uribe et al., 2025; Zhang et al., 2025) Speed in exam interpretation and treatment planning. Potential for false-positive and falsenegative results. Optimizes clinical workflow, but therapeutic decisions must remain the responsibility of the dentist. (Brozovic et al., 2024; Schwendicke & Büttner, 2023; Thurzo et al., 2023; Umer et al., 2024) Support for evidence-based clinical decision-making. Low interpretability of models ["black-box" systems]. Results must be critically interpreted and integrated into the professional's clinical evaluation. (Bonny et al., 2023; Surlari et al., 2023; Umer et al., 2024) Automation of clinical documentation and administrative tasks. Need for continuous human oversight. Reduces time spent on clinical charting, increasing care productivity. (Ahmed et al., 2021; Bonny et al., 2023; Shariff et al., 2025; Surlari et al., 2023) Personalization of dental education and development of instructional materials. Risks of "hallucinations," biases, and inaccurate information. Can enhance teaching, provided content is reviewed by faculty and experts. (Di Cosola et al., 2025; Khurshid et al., 2026; Pitchika et al., 2024; Schwendicke et al., 2020) Integration with electronic health records and decision support systems. Platform interoperability challenges. Supports integrated care and improves interprofessional communication. (Pitchika et al., 2024; Saikia et al., 2025; Samaranayake et al., 2025) Expanded access to specialized diagnosis. Implementation costs and required technological infrastructure. Can benefit regions with specialist shortages and strengthen tele dentistry. (Najeeb & Islam, 2025; Samaranayake et al., 2025) Development of a more personalized and predictive dentistry. Ethical issues, data privacy, and regulatory compliance [e.g., LGPD/GDPR]. Requires robust information security protocols, transparency, and data governance. (Di Cosola et al., 2025; Khurshid et al., 2026; Pitchika et al., 2024; Schwendicke et al., 2020) Continuous algorithm optimization through new data inputs. Shortage of prospective, multicenter, and cost-effectiveness studies. Definitive integration of AI will depend on demonstrating clinical and economic benefits in real-world scenarios. (Pitchika et al., 2024; Saikia et al., 2025; Samaranayake et al., 2025) Assistance in digital restorative planning and material selection. Need for clinical validation and integration with different digital dental systems. can increase the predictability of restorative treatments, reduce operational errors, and support personalized dentistry. (Najeeb & Islam, 2025; Samaranayake et al., 2025) Source: Prepared by the Author. Despite the high diagnostic performance demonstrated by AI algorithms, their widespread clinical translation depends on overcoming critical methodological obstacles (Li et al., 2026; Vázquez-Sebrango et al., 2025). A primary hurdle relates to the quality of training data. Many models are developed using retrospective image repositories obtained from single institutions with low demographic diversity. This narrow focus increases the risk of overfitting, reducing the generalizability of models when applied across different clinical settings (Ahmed et al., 2021; Pitchika et al., 2024; Saikia et al., 2025; Surlari et al., 2023). Another point of contention in the literature is the limited interpretability of deep learning algorithms. In many instances, models operate as "black boxes," preventing clinicians from understanding which specific image features led to a 7 Research, Society and Development, v. 15, n. 9, e3415951521, 2026 (CC BY 4.0) | ISSN 2525-3409 | DOI: http://dx.doi.org/10.33448/rsd-v15i9.51521 particular diagnostic output. In this context, the development of Explainable Artificial Intelligence (XAI) techniques has emerged as a fundamental strategy to enhance transparency, practitioner trust, and clinical safety (Di Cosola et al., 2025; Ezhov et al., 2021; Shan et al., 2021). From a regulatory standpoint, the rapid expansion of AI-driven solutions demands continuous updates to frameworks governing data protection, professional liability, and clinical validation. Compliance with legislation such as the General Data Protection Law (LGPD) and international standards is indispensable to guarantee the ethical utilization of these technologies (Li et al., 2022; Schwendicke & Büttner, 2023). Furthermore, most studies currently available focus on evaluating algorithmic diagnostic accuracy, leaving a noticeable gap in research on patient-centered clinical outcomes, cost-effectiveness, workflow impacts, and professional acceptability (Huo et al., 2025; Thurzo et al., 2023; Umer & Adnan, 2024). Prospective, multicenter clinical trials and implementation studies will be critical to determine the true utility of AI in dental practice (Ahmed et al., 2021; Pitchika et al., 2024; Saikia et al., 2025; Samaranayake et al., 2025; Surlari et al., 2023). Therefore, it must be emphasized that the integration of AI should not be viewed as a replacement for the dental surgeon, but rather as a complementary tool designed to enhance evidence-based decision-making (Di Cosola et al., 2025; Khurshid et al., 2026; Vázquez-Sebrango et al., 2025). The synergy between clinical expertise, scientific knowledge, and computational support represents the most promising pathway toward precise, personalized, and patient-centered dentistry (Bonny et al., 2023). 5. Future Perspectives AI-driven applications will optimize dental care by relieving the workforce of laborious, routine tasks, thereby improving health outcomes at lower cost for a broader population and ultimately facilitating personalized, predictive, preventive, and participatory dentistry (Ezhov et al., 2021; Schwendicke et al., 2020; Umer et al., 2024). In oral health management, AI technology spans diverse applications, including oral health education and counseling, monitoring, screening, diagnosis, treatment, follow-up of oral diseases, and health data collection and management (Li et al., 2026; Ma et al., 2026; Shujaat et al., 2025). By raising public awareness of oral health and improving self-management capabilities, AI can enhance diagnostic accuracy, facilitate tailored treatments, support teledentistry, optimize dental resource allocation, and provide early warning systems for oral pathologies (Li et al., 2026; Najeeb & Islam, 2025; Shariff et al., 2025). Dental education will need to adapt alongside the introduction of clinical AI solutions, fostering digital literacy across the future dental workforce (Schwendicke et al., 2020; Thurzo et al., 2023). Currently, the primary contemporary applications of AI in dentistry remain rooted in undergraduate dental education and academic research (Pitchika et al., 2024; Surlari et al., 2023; Zhang et al., 2025). 6. Conclusion Artificial intelligence represents a highly promising technology for dentistry, with applications spanning diagnosis, therapeutic planning, education, and clinical management. The current evidence demonstrates its high potential to improve diagnostic precision and optimize decision-making, particularly in image-based analyses. However, challenges regarding clinical validation, data quality, ethical aspects, and regulatory compliance still limit its widespread implementation. Thus, AI must be used as a tool that complements the dentist's clinical judgment, contributing to a more efficient, personalized, and evidence-based practice. The advancement of artificial intelligence will likely reshape dental practice profoundly in the coming years. Nevertheless, its incorporation must occur ethically and transparently, and be based on robust scientific evidence, preserving the central role of the dental surgeon’s clinical judgment. 8 Research, Society and Development, v. 15, n. 9, e3415951521, 2026 (CC BY 4.0) | ISSN 2525-3409 | DOI: http://dx.doi.org/10.33448/rsd-v15i9.51521 References Ahmed, N., Abbasi, M. S., Zuberi, F. et al. (2021). Artificial Intelligence Techniques: Analysis, Application, and Outcome in Dentistry—A Systematic Review. BioMed Res Int 2021:9751564. https://doi.org/10.1155/2021/9751564. Arzani, S., Karimi, A., Iranmanesh, P. et al. (2025). Examining the Diagnostic Accuracy of Artificial Intelligence for Detecting Dental Caries Across a Range of Imaging Modalities: An Umbrella Review With Meta-Analysis. PLoS One. 20:e0329986. https://doi.org/10.1371/journal.pone.0329986. Bonny, T., Al Nassan, W., Obaideen, K. et al. (2023). Contemporary Role and Applications of Artificial Intelligence in Dentistry. F1000Research. 12:1179. https://doi.org/10.12688/f1000research.140204.1. Bonny, T., Al Nassan, W., Obaideen, K. et al. (2023). Contemporary Role and Applications of Artificial Intelligence in Dentistry. F1000Research. 12:1179. https://doi.org/10.12688/f1000research.140204. Brozovic, J., Mikulic, B., Tomas, M., Juzbasic, M. & Blaskovic, M. (2024). Assessing the performance of Bing Chat artificial intelligence: dental exams, clinical guidelines, and patients' frequent questions. J Dent. 144:104927. https://doi.org/10.1016/j.jdent.2024.104927. Di Cosola, M., Ballini, A., Prencipe, F. A. et al. (2025). Artificial intelligence in dentistry: a narrative review of applications, challenges, and future directions. Minerva Dent Oral Sci. 74:337-348. https://doi.org/10.23736/S2724-6329.25.05217-9. Ezhov, M., Gusarev, M., Golitsyna, M. et al. (2021). Clinically Applicable Artificial Intelligence System for Dental Diagnosis With CBCT. Sci Rep. 11:15006. https://doi.org/10.1038/s41598-021-94093-9. Gao, S., Wang, X., Xia, Z. et al. (2025). Artificial Intelligence in Dentistry: A Narrative Review of Diagnostic and Therapeutic Applications. Med Sci Monit. 31:e946676. https://doi.org/10.12659/MSM.946676. Huo, B., Collins, G. S., Cacciamani, G. E. & Guyatt, G. (2025) Reporting guidelines for studies involving generative artificial intelligence applications: what do I use, and when? NPJ Digit Med. 8:646. https://doi.org/10.1038/s41746-025-02113-z. Khurshid, Z., Osathanon, T., Shire, M. A., Schwendicke, F. & Samaranayake, L. (2026). Artificial Intelligence in Dentistry: A Concise Review of Reporting Checklists and Guidelines. Int Dent J. 76:109322. https://doi.org/10.1016/j.identj.2025.109322. Li, H., Chen, S., Chang, B. et al. (2026). Application of Artificial Intelligence in Oral Health Management: Challenges and Opportunities. Front Med. 13:1700529. https://doi.org/10.3389/fmed.2026.1700529. Li, S., Liu, J., Zhou, Z. et al. (2022). Artificial intelligence for caries and periapical periodontitis detection. J Dent. 122:104107. https://doi.org/10.1016/j.jdent.2022.104107. Ma, Z., Du, C., Lao, Q. & Xie, X. (2026) Generative Artificial Intelligence: Applications and Future Prospects in Dentistry. Int Dent J. 76:108276. https://doi.org/10.1016/j.identj.2025.108276. Najeeb, M. & Islam, S. (2025) Artificial intelligence [AI] in restorative dentistry: current trends and future prospects. BMC Oral Health. 25:592. https://doi.org/10.1186/s12903-025-05989-1. Ogassawara, D. et al. (2025). Trilhas metodológicas para a revisão narrativa: orientações pragmáticas para sua elaboração. Ensino & Pesquisa. 23(3). DOI: Pereira, A. S. et al. (2018). Metodologia da pesquisa científica. [free ebook]. Santa Maria: Editora da UFSM. Pitchika, V., Büttner, M. & Schwendicke, F. (2024) Artificial intelligence and personalized diagnostics in periodontology: A narrative review. Periodontology 2000 95:220-231. https://doi.org/10.1111/prd.12586. Risemberg, R. I. C. et al. (2026a). Qualitativa, quantitativa ou quali-quantitativa: Como identificar de modo rápido a abordagem de um artigo científico? EAcadêmica, 7(2), e0172702. DOI: https://doi.org/10.52076/eacad-v7i2.702. Risemberg, R. I. C., Wakin, M., & Shitsuka, R. (2026b). A importância da metodologia científica no desenvolvimento de artigos científicos. E-Acadêmica, 7(1), e0171675. https://eacademica.org/eacademica/article/view/675. Saikia, A., Kvist, T., Fawzy, A. & Anthonappa, R. (2025) Artificial Intelligence in dentistry: an overview of systematic reviews and meta-analysis. Evid Based Dent. 26:180. https://doi.org/10.1038/s41432-025-01190-z. Samaranayake, L., Tuygunov, N., Schwendicke, F. et al. (2025). The Transformative Role of Artificial Intelligence in Dentistry: A Comprehensive Overview. Part 1: Fundamentals of AI, and Its Contemporary Applications in Dentistry. Int Dent J. 75:383-96. https://doi.org/10.1016/j.identj.2025.02.005. Schwendicke, F. & Büttner, M. (2023) Artificial intelligence: advances and pitfalls. Br Dent J 234:749–750. https://doi.org/10.1038/s41415-023-5855-0 Schwendicke, F., Samek, W. & Krois, J. (2020) Artificial Intelligence in Dentistry: Chances and Challenges. J Dent Res 99:769-74. https://doi.org/10.1177/0022034520915714. Sezen-Hulsmans, D., Pereira-Cenci, T., Sonneveld, R. E., Loomans, B. A. C., Cenci, M. S. (2026) Assessing the Role of Artificial Intelligence in Caries Detection and Clinical Decision-Making: A Scoping Review. Caries Res 1-20. https://doi.org/10.1159/000550238 Shan, T., Tay, F. R. & Gu, L. (2021) Application of Artificial Intelligence in Dentistry. J Dent Res. 100:232-244. https://doi.org/10.1177/0022034520969115. Shariff, A., Patil, S. & Freitas, C. M. T. (2025) An Analysis of Artificial Intelligence Studies in Dentistry: Clinical Applications and Next Steps. J Contemp Dent Pract. 26:526-32. https://doi.org/10.5005/jp-journals-10024-3867. 9 Research, Society and Development, v. 15, n. 9, e3415951521, 2026 (CC BY 4.0) | ISSN 2525-3409 | DOI: http://dx.doi.org/10.33448/rsd-v15i9.51521 Shujaat, S., Aljadaan, H., Alrashid, H., Aboalela, A. A. & Riaz, M. (2025). FDA-Approved AI Solutions in Dental Imaging: A Narrative Review of Applications, Evidence, and Outlook. Int Dent J. 76:109315. https://doi.org/10.1016/j.identj.2025.109315. Surlari, Z., Budală, D. G., Lupu, C. I. et al. (2023). Current Progress and Challenges of Using Artificial Intelligence in Clinical Dentistry—A Narrative Review. J Clin Med. 12:7378. https://doi.org/10.3390/jcm12237378. Thurzo, A., Strunga, M., Urban, R., Surovková, J. & Afrashtehfar, K. I. (2023) Impact of Artificial Intelligence on Dental Education: A Review and Guide for Curriculum Update. Educ Sci. 13:150. https://doi.org/10.3390/educsci13020150. Umer, F. & Adnan, N. (2024) Generative artificial intelligence: synthetic datasets in dentistry. BDJ Open. 10:13. https://doi.org/10.1038/s41405-024-00198-4. Umer, F., Batool, I. & Naved, N. (2024) Innovation and application of Large Language Models [LLMs] in dentistry – a scoping review. BDJ Open. 10:90. https://doi.org/10.1038/s41405-024-00277-6 Uribe, S. E., Maldupa, I. & Schwendicke, F. (2025) Integrating Generative AI in Dental Education: A Scoping Review of Current Practices and Recommendations. Eur J Dent Educ 29:341-355. https://doi.org/10.1111/eje.13074. Vázquez-Sebrango G, Anitua E, Macía I, Arganda-Carreras I (2025) The role of artificial intelligence in implant dentistry: a systematic review. Int J Oral Maxillofac Surg. 54:1098-1122. https://doi.org/10.1016/j.ijom.2025.04.005 Zaborowicz, K., Zaborowicz, M., Cieślińska, K. et al (2025). Artificial Intelligence Methods in the Detection of Oral Diseases on Pantomographic Images—A Systematic Narrative Review. J Clin Med. 14:3262. https://doi.org/10.3390/jcm14093262. Zhang, R., Pan, Y., Liu, Y., Deng, Y. & Pow, E. H. N. (2025) Leveraging large language models for patient instructions in dentistry—A systematic review and meta-analysis. J Prosthodont. https://doi.org/10.1111/jopr.70068 10