Educational Applications of ChatGPT in University‐Based Dental Education. A Systematic Review - PMC Skip to main content An official website of the United States government Here's how you know Here's how you know Official websites use .gov A .gov website belongs to an official government organization in the United States. Secure .gov websites use HTTPS A lock ( Lock Locked padlock icon ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites. Search Log in Dashboard Publications Account settings Log out Search… Search NCBI Primary site navigation Search Logged in as: Dashboard Publications Account settings Log in Search PMC Full-Text Archive Search in PMC Journal List User Guide PERMALINK Copy As a library, NLM provides access to scientific literature. Inclusion in an NLM database does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: PMC Disclaimer | PMC Copyright Notice Eur J Dent Educ . 2025 Jul 3;30(2):644–660. doi: 10.1111/eje.70011 Search in PMC Search in PubMed View in NLM Catalog Add to search Educational Applications of ChatGPT in University‐Based Dental Education. A Systematic Review Juan Ignacio Aura‐Tormos Juan Ignacio Aura‐Tormos 1 Department of Dentistry, Faculty of Medicine and Dentistry, University of Valencia, Valencia, Spain Find articles by Juan Ignacio Aura‐Tormos 1, ✉ , Maria Llacer‐Martinez Maria Llacer‐Martinez 2 Private, Valencia, Spain Find articles by Maria Llacer‐Martinez 2 , Ines Torres‐Osca Ines Torres‐Osca 2 Private, Valencia, Spain Find articles by Ines Torres‐Osca 2 Author information Article notes Copyright and License information 1 Department of Dentistry, Faculty of Medicine and Dentistry, University of Valencia, Valencia, Spain 2 Private, Valencia, Spain * Correspondence: Juan Ignacio Aura‐Tormos ( [email protected] ) ✉ Corresponding author. Revised 2025 Jun 5; Received 2025 Mar 27; Accepted 2025 Jun 17; Issue date 2026 May. © 2025 The Author(s). European Journal of Dental Education published by John Wiley & Sons Ltd. This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc-nd/4.0/ License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made. PMC Copyright notice PMCID: PMC13090418 PMID: 40609986 ABSTRACT Background The emergence of ChatGPT has sparked growing interest in its application within university‐based dental education. As a conversational large language model (LLM), ChatGPT offers unique opportunities for content explanation, exam simulation and learner support. However, its educational utility, limitations and ethical implications remain underexplored. Objective This systematic review aims to synthesise existing evidence on the pedagogical uses, perceived benefits, limitations and curricular integration of ChatGPT in dental education at the undergraduate and postgraduate levels. Material and Methods A comprehensive search was conducted across PubMed, Scopus and Web of Science. After screening and applying eligibility criteria, studies which met the eligibility criteria were included for full analysis. Thematic synthesis was performed across six domains: perceptions, educational uses, perceived benefits, risks and limitations, curricular integration and model comparison. Results After completing the database search, 60 studies were identified. ChatGPT was predominantly perceived as useful, especially in enhancing autonomous learning, exam preparation and understanding clinical concepts. Most studies highlighted GPT‐4's superior performance compared to GPT‐3.5. Nevertheless, concerns regarding misinformation, overreliance and reduced critical thinking were frequently reported. Integration into curricula remained informal and complementary, with limited structured implementation. Study quality was heterogeneous, and many reports lacked methodological transparency. Conclusions ChatGPT shows promise as a supportive tool in dental education, but its integration requires ethical and pedagogical oversight. Future research should use standardised frameworks to assess its effectiveness and risks. Keywords: artificial intelligence, ChatGPT, curriculum integration, dental education, educational technology, generative AI, GPT‐4 1. Introduction The term ‘artificial intelligence’ (AI) was first introduced in 1956 at Dartmouth University, where it was defined as a computerised simulation of human cognitive functions [ 1 ]. Since then, AI has expanded exponentially across various fields [ 2 , 3 ]. However, despite significant technological advancements and their clinical impact in medicine, its integration into dental science remains comparatively limited [ 4 , 5 ]. For clinical AI applications in dentistry, a mixture of advanced dental technologies and a full digital workflow transformation are necessary [ 6 , 7 , 8 , 9 , 10 , 11 ]. Some dental areas have introduced AI as X‐ray diagnosis and other methods of dental caries diagnosis [ 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 ], in dental implants [ 20 , 21 ], photography analysis [ 18 , 22 , 23 ], proactive management, tele‐dentistry, patient coaching [ 24 , 25 , 26 , 27 ] and clinical predictions (virtual simulation, aging, growth) [ 5 , 28 , 29 , 30 ]. Over the past two decades, AI has undergone significant technological advancements with increasing clinical relevance in various medical fields [ 31 ]. Indeed, the COVID‐19 pandemic accelerated the adoption of digital tools in healthcare, many of which incorporated artificial intelligence. This evolution includes a wide range of applications developed before and beyond the emergence of more recent tools such as ChatGPT, which, although notable, represents only one aspect of a much broader and ongoing integration of AI into the field [ 32 ]. ChatGPT is a conversational artificial intelligence tool developed by OpenAI and released publicly on November 30, 2022. Built on a large language model (LLM) architecture, ChatGPT is designed to generate human‐like responses by interpreting natural language prompts and drawing on a vast corpus of text data. Within just a few days of its release, the platform gained widespread public attention, amassing over one million users in less than a week, reflecting the growing societal interest in generative AI [ 33 ]. At its core, ChatGPT employs transformer‐based neural networks to produce coherent, contextually relevant and conversational outputs, enabling applications across a wide array of domains, including healthcare and education [ 34 ]. As a versioned implementation of OpenAI's GPT architecture, ChatGPT evolves through successive models—such as GPT‐3.5 and GPT‐4—each representing a distinct iteration with progressively enhanced capabilities in reasoning, accuracy and language generation. While its integration into dental education is still in the early stages, preliminary research and expert commentary suggest its potential for use in interactive learning, patient communication, clinical simulation and personalised tutoring [ 35 , 36 , 37 , 38 ]. Continued investigation is required to determine best practices and ethical guidelines for its use in dental academic settings. Although several large language models have been released by major technology companies—including Google's Gemini and Microsoft's integration of OpenAI's models into Copilot—this review focuses specifically on ChatGPT due to its early release, widespread adoption, and dominant presence in the literature at the time of the review. ChatGPT has been the most frequently examined LLM in the context of dental education, with GPT‐4 receiving substantial scholarly attention. Its consistent architecture, transparent development history, and stand‐alone accessibility make it a unique and traceable subject for systematic educational evaluation. The aim of this systematic review is to examine and synthesise the current scientific literature on the use of ChatGPT in university‐based dental education. Specifically, the study focuses on how ChatGPT is being applied in the training of dental students and related health professionals within higher education institutions, with an emphasis on its educational roles, perceived benefits, risks and levels of curricular integration. In addition, this review also analyses the methodological and contextual characteristics of the included studies to map research trends and study quality. 2. Material and Methods A comprehensive bibliographic search was conducted to identify all studies related to the use of ‘ChatGPT’ in dental education. The search strategy, including specific queries and predefined inclusion and exclusion criteria, was systematically applied across selected databases to ensure the retrieval of relevant and high‐quality literature. 2.1. Databases PubMed, Scopus (Dentistry) and Web of Science (WOS). 2.2. Search Strategy The search strategies were adapted to each platform's syntax and indexing system, while maintaining conceptual consistency. The search terms targeted both the artificial intelligence model of interest (ChatGPT and related large language models) and its application in academic dental education. No other filters were applied. PubMed. ○ ("ChatGPT" OR "GPT‐4" OR "Generative Pre‐trained Transformer") AND ("dental education" OR "dental student" OR "dental teaching" OR "dentistry education") Scopus. ○ ("ChatGPT" OR "GPT‐4" OR "Generative Pre‐trained Transformer") AND ("dental education" OR "dental student" OR "dentistry education" OR "dental teaching") Web of Science (WOS) ○ Initial search. ("ChatGPT" OR "GPT‐4" OR "Generative Pre‐trained Transformer") AND ("dental education" OR "dental student" OR "dentistry education" OR "dental teaching") ○ Alternative expanded query. ("ChatGPT" OR "GPT‐4" OR "large language model") AND ("dental education" OR "dental student" OR "dental curriculum" OR "dentistry education") 2.3. Inclusion and Exclusion Criteria Eligibility criteria were defined to guide the selection of relevant studies. The review included peer‐reviewed original articles, reviews, conference papers, editorials and expert opinions, provided they were published in English. No restrictions were applied regarding the date of publication. To be eligible, studies had to explicitly address the use, implementation, evaluation, or discussion of ChatGPT within the context of dental education at the university level, including both undergraduate and postgraduate programs. Publications that referred to ChatGPT without focusing on dental education, or those related to patient communication, continuing education, or non‐academic settings, were excluded. Studies related to patient communication, continuing education, or non‐academic settings were excluded to maintain focus on the pedagogical use of ChatGPT within formal university‐based dental curricula. Although Patient communication is an essential competency in dental education, this review specifically examined ChatGPT's role in supporting student learning processes rather than clinical communication tasks. 2.4. Reviewer Team and Procedure The bibliographic search, study selection, data extraction and thematic analysis were carried out collaboratively by all authors during March 2025. Each step was performed through joint discussion and iterative consensus to ensure accuracy, coherence and transparency across the review process. 2.4.1. Descriptive Analysis of Study Characteristics To provide a foundational overview of the included literature, an initial level of data extraction focused on general descriptive variables. This included the geographic distribution of studies to identify regional patterns in research on ChatGPT in dental education. Study design was also classified according to methodological characteristics described by the authors, distinguishing between experimental, quasi‐experimental, observational, review‐based and unclear approaches. In addition, the relationship between study quality and educational context was explored to assess how methodological rigour aligned with the setting in which ChatGPT was applied (e.g., testing, writing, tutoring). This descriptive mapping enabled the identification of dominant research trends, methodological tendencies and variation in quality across different pedagogical applications. To determine quality assessment, given the diversity of study designs and inconsistent reporting detail, a simplified quality assessment approach was adopted. Although the NIH Study Quality Assessment Tool served as a reference, not all studies provided sufficient methodological information for its full application. Therefore, studies were categorised into four quality levels—High, Moderate, Low, or Unclear—based on general criteria such as clarity of objectives, study design, use of comparison groups and reporting transparency. The ‘Unclear’ category was assigned to studies lacking enough detail for reliable classification. This approach enabled consistent comparison across heterogeneous studies in this emerging field. 2.4.2. Thematic Analysis of ChatGPT in Dental Education A second level of data extraction focused on the educational and pedagogical dimensions of ChatGPT's use, structured around six thematic domains: perceptions, educational uses, perceived benefits, risks and limitations, curricular integration and model comparison. Perceptions explored students' overall sentiment toward ChatGPT, including its perceived usefulness, concerns such as ethical implications, reliability, potential misinformation and the risk of overreliance. The section also examined attitudes toward the integration of ChatGPT into university‐level dental education, ranging from strong support to opposition. Educational uses focused on the specific ways in which ChatGPT was utilised to support learning. This included its use in writing assignments (with or without instructor guidance), understanding clinical and theoretical concepts (such as diagnostic reasoning or treatment planning), preparing for exams (e.g., generating practice questions or self‐testing), and serving as a virtual tutor, including the nature and depth of student–AI interactions. Perceived benefits captured the educational advantages attributed to ChatGPT, including its role in fostering autonomous learning, enabling personalised learning experiences tailored to individual needs, and providing immediate feedback. These benefits were identified through qualitative data, often illustrated by student‐reported experiences and perceptions. Risks and limitations captured concerns about ethical issues and cognitive impact. Studies were analysed for reported risks and limitations associated with ChatGPT. A typology of concerns was developed to categorise recurring issues into four main themes: misinformation or factual errors, overreliance and loss of critical thinking, ethical concerns and academic integrity and user discomfort or resistance. Curricular integration examined the pedagogical role assigned to ChatGPT, whether as a complementary learning tool, an aid for assessment, or a partial substitute for traditional instruction. It also assessed how ChatGPT was implemented—ranging from informal, self‐directed use to structured integration within coursework or pilot initiatives—and at which educational level (undergraduate or postgraduate) it was applied. When specified, the academic discipline involved (e.g., Endodontics, Periodontics, or Basic Sciences) was also noted. Studies lacking sufficient detail for classification were marked as ‘Unclear’ to maintain transparency and underscore the need for more standardised reporting. Model comparison synthesised findings from studies that evaluated the performance of different ChatGPT versions—primarily GPT‐3.5 and GPT‐4/4o—highlighting variations in accuracy, reliability and overall educational effectiveness. Quantitative comparisons included metrics such as percentage accuracy or mean test scores, while contextual variables (e.g., exam type, clinical scenarios, or specific knowledge domains) were considered to interpret performance differences meaningfully. 3. Results After carrying out the research in all databases on 23 March 2025, and after removing duplicates using Zotero 6.0.23 for Mac, 60 articles related to ‘ChatGPT’ and ‘dental education’ were found (Figure 1 ). FIGURE 1. Open in a new tab PRISMA 2020 flowchart diagram. A summary of the studies included in this systematic review is presented below (Table 1 ), providing an overview of the evidence base analysed. TABLE 1. Summary of studies included in the systematic review. Citation Year Country Study design Main use(s) Study quality Akitomo T et al., 2024, Cureus. https://doi.org/10.7759/cureus.73103 [ 36 ] 2024 Japan Comparative multi‐year study Clinical concepts, exam preparation, virtual Tutor High Aldukhail S., 2025, Eur J Dent Educ. https://doi.org/10.1111/eje.13056 [ 37 ] 2025 Saudi Arabia Comparative experimental evaluation Writing, clinical concepts, exam preparation, virtual tutor Moderate Alencar‐Palha C et al., 2024, Eur J Dent Educ. https://doi.org/10.1111/eje.13057 [ 38 ] 2024 Brazil Comparative study Writing, clinical concepts High Alencar‐Palha C et al., 2025, Eur J Dent Educ. https://doi.org/10.1111/eje.13057 [ 38 ] 2025 Brazil Comparative observational study Writing High Ali K et al., 2024, Eur J Dent Educ. https://doi.org/10.1111/eje.12937 [ 39 ] 2024 Qatar Exploratory study Writing, clinical concepts, exam preparation, virtual tutor Moderate to High Arriola‐Pacheco F., 2025, Int J Paediatr Dent. https://doi.org/10.1111/ipd.13298 [ 40 ] 2025 Canada Perspective/practical application Clinical concepts, virtual tutor Not applicable Arılı Öztürk E et al., 2025, Int Endod J. https://doi.org/10.1111/iej.14217 [ 41 ] 2025 Turkey Comparative performance study Clinical concepts, exam preparation, virtual tutor High Bayraktar N., 2025, BMC Oral Health. https://doi.org/10.1186/s12903‐024‐05393‐1 [ 42 ] 2025 Turkey Evaluation study Not specified High Bhatia AP et al., 2024, Cureus. https://doi.org/10.7759/cureus.60006 [ 43 ] 2024 India Comparative teaching effectiveness study Clinical concepts, exam preparation Moderate Brondani M et al., 2024, J Dent Educ. https://doi.org/10.1002/jdd.13663 [ 44 ] 2024 Canada Experimental study Writing High Brozović J et al., 2024, J Dent. https://doi.org/10.1016/j.jdent.2024.104927 [ 45 ] 2024 Croatia Comparative performance study Clinical concepts, exam preparation High Chau RCW et al., 2024, Int Dent J. https://doi.org/10.1016/j.identj.2023.12.007 [ 46 ] 2024 Hong Kong (China) Performance evaluation study Clinical concepts, exam preparation, virtual tutor High Claman D, Sezgin E., 2024, JMIR Med Educ. https://doi.org/10.2196/52346 [ 47 ] 2024 USA Viewpoint with use case Writing, clinical concepts, virtual tutor Moderate Danesh A et al., 2023, JADA. https://doi.org/10.1016/j.adaj.2023.07.016 [ 48 ] 2023 Canada/USA Performance assessment study Clinical concepts, exam preparation, virtual tutor Eggmann F et al., 2023, J Esthet Restor Dent. https://doi.org/10.1111/jerd.13046 [ 49 ] 2023 Switzerland, USA Narrative review Writing, clinical concepts, exam preparation, virtual tutor Moderate Elnagar MH et al., 2024, Semin Orthod. https://doi.org/10.1053/j.sodo.2024.03.004 [ 50 ] 2024 USA Narrative review Writing, clinical concepts, virtual tutor Moderate Foong KWC et al., 2024, Springer. https://doi.org/10.1007/s13187‐024‐05968‐2 [ 51 ] 2024 Singapore Descriptive report/educational innovation Writing, clinical concepts, virtual tutor Moderate Fuchs A, Trachsel T, Weiger R, Eggmann F., 2023, Swiss Dent J. https://doi.org/10.61872/sdj‐2024‐06‐01 [ 52 ] 2023 Switzerland Experimental, comparative Exam performance (SFLEDM) evaluation High Hultgren C et al., 2023, J Educ Eval Health Prof. https://doi.org/10.3352/jeehp.2023.20.32 [ 53 ] 2023 Sweden Cross‐sectional comparative study Clinical concepts, exam preparation, virtual tutor Moderate Işik G et al., 2025, J Craniofac Surg. https://doi.org/10.1097/SCS.0000000000010686 [ 54 ] 2025 Turkey Cross‐sectional evaluation study Clinical concepts, exam preparation, virtual tutor High Jaworski A et al., 2024, Cureus. https://doi.org/10.7759/cureus.68813 [ 55 ] 2024 Poland Comparative performance study Clinical concepts, exam preparation High Jayawardena CK et al., 2025, Int Dent J. https://doi.org/10.1016/j.identj.2024.12.022 [ 56 ] 2025 Sri Lanka Comparative experimental study Writing, virtual tutor Jeong H et al., 2024, Dentomaxillofac Radiol. https://doi.org/10.1093/dmfr/twae021 [ 57 ] 2024 South Korea Comparative performance study Exam preparation High Khurana S, Vaddi A., 2023, Cureus. https://doi.org/10.7759/cureus.40053 [ 58 ] 2023 USA Editorial/expert perspective Writing, clinical concepts, exam preparation Moderate Kim W et al., 2025, Int Dent J. https://doi.org/10.1016/j.identj.2024.09.002 [ 59 ] 2025 Korea Comparative performance study Clinical concepts, exam preparation, virtual tutor High Kinikoglu I., 2025, Cureus. https://doi.org/10.7759/cureus.77292 [ 60 ] 2025 Turkey Comparative performance study Clinical concepts, exam preparation, virtual tutor High Kurt Demirsoy K et al., 2024, Angle Orthod. https://doi.org/10.2319/031224‐207.1602 [ 61 ] 2024 Turkey Comparative evaluation study Clinical concepts High Künzle P et al., 2024, Int J Comput Dent. https://doi.org/10.3290/j.ijcd.b4779571 [ 62 ] 2024 Switzerland Comparative performance study Clinical concepts, exam preparation High Li C et al., 2024, Eur J Dent Educ. https://doi.org/10.1111/eje.13066 [ 63 ] 2024 China Comparative study Clinical concepts, exam preparation, virtual tutor High Liu M et al., 2025, Int Dent J. https://doi.org/10.1016/j.identj.2024.10.014 [ 64 ] 2025 Multi‐country (8 nations) Systematic review and meta‐analysis Clinical concepts, exam preparation High Morishita M et al., 2024, J Dent Sci. https://doi.org/10.1016/j.jds.2023.12.007 [ 65 ] 2024 Japan Performance evaluation study (vision) Clinical concepts, exam preparation Moderate Morishita M et al., 2024, Saudi Dent J. https://doi.org/10.1016/j.sdentj.2024.11.006 [ 66 ] 2024 Japan Comparative performance study Clinical concepts, exam preparation, virtual tutor High Or AJ et al., 2024, J Dent Educ. https://doi.org/10.1002/jdd.13591 [ 67 ] 2024 Australia Pilot study Clinical concepts, virtual tutor Moderate Qamar K et al., 2024, J Pak Med Assoc. https://doi.org/10.47391/JPMA.11053 [ 68 ] 2024 Pakistan Cross‐sectional survey Writing, clinical concepts, exam preparation, virtual tutor High Quah B et al., 2024, BMC Med Educ. https://doi.org/10.1186/s12909‐024‐05881‐6 [ 69 ] 2024 Singapore Comparative reliability study Writing, clinical concepts, exam preparation, virtual tutor High Quah B et al., 2024, Int J Oral Maxillofac Surg. https://doi.org/10.1016/j.ijom.2024.06.003 [ 70 ] 2024 Singapore Comparative performance study Clinical concepts, exam preparation, virtual tutor High Qutieshat A et al., 2024, Diagnosis. https://doi.org/10.1515/dx‐2024‐0034 [ 71 ] 2024 Oman, UK, USA Comparative performance study Clinical concepts, exam preparation, virtual tutor High Rahad K et al., 2024, Dent Res Oral Health. https://doi.org/10.26502/droh.0069 [ 72 ] 2024 USA Experimental use case study Writing, clinical concepts, exam preparation Moderate Roganović J., 2024, Int Dent J. https://doi.org/10.1016/j.identj.2024.04.012 [ 73 ] 2024 Serbia Experimental study with control groups Writing, clinical concepts, exam preparation, virtual tutor Moderate Sabri H et al., 2025, J Periodont Res. https://doi.org/10.1111/jre.13323 [ 74 ] 2025 USA Comparative cross‐sectional Clinical concepts, exam preparation, virtual tutor High Sallam M., 2023, BMC Med Educ. https://doi.org/10.1186/s12909‐023‐04678‐0 [ 75 ] 2023 Multinational Descriptive survey study Writing, clinical concepts, exam preparation, virtual tutor High Saravia‐Rojas MA et al., 2024, J Dent Educ. https://doi.org/10.1002/jdd.13485 [ 76 ] 2024 Peru Comparative educational study Writing, clinical concepts High Shamim MS et al., 2024, J Coll Physicians Surg Pak. https://doi.org/10.29271/jcpsp.2024.05.595 [ 77 ] 2024 Pakistan Quasi‐experimental, qualitative Writing, exam preparation Moderate Shete A et al., 2024, J Indian Acad Oral Med Radiol. https://doi.org/10.4103/jiaomr.jiaomr_62_24 [ 78 ] 2024 India Cross‐sectional comparative study Clinical concepts, exam preparation, virtual tutor Moderate Sismanoglu S, Capan B., 2025, BMC Med Educ. https://doi.org/10.1186/s12909‐024‐06389‐9 [ 79 ] 2025 Turkey Comparative performance study Clinical concepts, exam preparation, virtual tutor High Snigdha NT et al., 2024, Hum Behav Emerg Technol. https://doi.org/10.1155/2024/1119816 [ 80 ] 2024 India Exploratory comparative study Clinical concepts, exam preparation High Souza LL et al., 2024, Gen Dent. PMID: 38905609 [ 81 ] 2024 Brazil/International Review Writing, clinical concepts, exam preparation, virtual tutor Moderate Stephan D et al., 2024, J Med Internet Res. https://doi.org/10.2196/60684 [ 82 ] 2024 Germany Comparative study Writing, clinical concepts High Symeou L et al., 2025, Eur J Dent Educ. https://doi.org/10.1111/eje.13069 [ 83 ] 2025 Cyprus Consensus‐based framework development Writing, clinical concepts, exam preparation, virtual tutor High Tassoker M., 2025, BMC Oral Health. https://doi.org/10.1186/s12903‐025‐05554‐w [ 84 ] 2025 Turkey Comparative performance study Clinical concepts, exam preparation, virtual tutor High Thurzo A et al., 2023, Educ Sci. https://doi.org/10.3390/educsci13020150 [ 85 ] 2023 Slovakia, UAE, Switzerland Narrative review Writing, clinical concepts, exam preparation, virtual tutor High Tiwari A et al., 2023, Cureus. https://doi.org/10.7759/cureus.40367 [ 86 ] 2023 India (multiple affiliations) Systematic review Writing, clinical concepts High Tomo S et al., 2024, Clin Oral Investig. https://doi.org/10.1007/s00784‐024‐05939‐1 [ 87 ] 2024 Brazil Comparative diagnostic study Clinical concepts, exam preparation, virtual tutor High Uehara O et al., 2024, J Dent Educ. https://doi.org/10.1002/jdd.13766 [ 88 ] 2024 Japan Comparative analysis Clinical concepts, exam preparation, virtual tutor High Uribe S et al., 2024, Eur J Dent Educ. https://doi.org/10.1111/eje.13009 [ 89 ] 2024 Multinational (66 countries) Cross‐sectional survey Writing, clinical concepts, exam preparation, virtual tutor High Uribe S et al., 2025, Eur J Dent Educ. https://doi.org/10.1111/eje.13074 [ 90 ] 2025 Multinational Scoping review Writing, clinical concepts, exam preparation, virtual tutor High Xiong F et al., 2025, Eur J Dent Educ. https://doi.org/10.1111/eje.13087 [ 91 ] 2025 China Comparative study Clinical concepts, exam preparation, virtual tutor High Yamaguchi S et al., 2024, J Dent Sci. https://doi.org/10.1016/j.jds.2024.02.019 [ 92 ] 2024 Japan Comparative evaluation study Clinical concepts, exam preparation, virtual tutor High Zope SA et al., 2025, Cureus. https://doi.org/10.7759/cureus.79031 [ 93 ] 2025 India Cross‐sectional questionnaire study Clinical concepts, exam preparation High Öztürk Z et al., 2025, Dent Traumatol. https://doi.org/10.1111/edt.13042 [ 94 ] 2025 Turkey Comparative quality assessment Clinical concepts, exam preparation, virtual tutor High Open in a new tab 3.1. Descriptive Analysis of Study Characteristics 3.1.1. Distribution of Studies by Country Several countries have shown active involvement in researching the role of ChatGPT in dental education, with contributions distributed across 13 nations. Turkey accounted for the highest number of studies ( n = 7), followed by the United States ( n = 6), Japan ( n = 5) and India ( n = 4). Other contributing countries included Singapore, Brazil and Canada (three studies each), as well as Pakistan, Peru, China, Croatia and a small group of multinational studies (two each) (Figure 2 ). FIGURE 2. Open in a new tab Top‐contributing countries to research on ChatGPT in dental education. 3.1.2. Frequency of Study Designs The analysis of study designs in the included literature (Figure 3 ) reveals that quasi‐experimental designs were the most frequently used among defined categories, present in 25% of the studies ( n = 15), followed by experimental studies and review‐based or secondary analyses, each representing 12% ( n = 7). Observational and assessment‐based approaches were reported in 8% of the studies ( n = 5). Notably, nearly half of the studies (48%, n = 29) fell into the ‘other’ or ‘unclear’ category, lacking a clearly defined methodological structure. Overall, approximately two‐thirds of the studies employed empirical designs—whether experimental, quasi‐experimental, or observational—though often with varying degrees of methodological transparency. FIGURE 3. Open in a new tab Study designs analysis. 3.1.3. Relationship Between Study Quality and Evaluation Context The most frequently represented context was ‘Other’, accounting for approximately 63% of the studies. This category included studies with hybrid, exploratory, or ambiguously defined educational settings. ‘Exams & Testing’ was the second most common context, representing 23% of the studies, and included research on board‐style multiple‐choice questions, licensing examinations and quiz‐based assessments. ‘Essay Writing’ appeared in about 12% of the studies, focusing on ChatGPT's role in generating or supporting structured academic texts. ‘Feedback & Grading’ was addressed in a smaller subset (5%), typically in formative assessment contexts. As shown in Figure 4 , study quality varied across categories, with high ratings more frequently associated with clearly defined and outcome‐oriented designs such as exam‐based studies, while lower or unclear ratings were more common in studies falling into the ‘Other’ category. FIGURE 4. Open in a new tab Relationship between study quality and evaluation context. 3.2. Thematic Analysis of ChatGPT in Dental Education 3.2.1. Overall Perception The Overall Perception of ChatGPT in Dental Education, as Illustrated in Figure 5 , was Predominantly Undefined or Unclear. Specifically, 83% of the Studies ( n = 50) did not Provide a Clearly Evaluative Stance. Among the Studies that did, 13% ( n = 8) Expressed a Positive Perception—Highlighting ChatGPT's Usefulness, Especially with GPT‐4—while 5% ( n = 3) Conveyed Cautious or Mixed Views, often referencing Concerns about Reliability or Ethical Implications. Notably, no Study in the Dataset expressed a Strongly Negative Perception. FIGURE 5. Open in a new tab Categorised overall perception of ChatGPT. 3.2.2. Educational Uses Analysis of the educational applications of ChatGPT revealed that its most frequently reported uses were for understanding clinical concepts (88%) and exam preparation (75%), followed by virtual tutoring (65%) and writing assignments (45%). These applications were identified across the included studies based on reported implementation contexts. In studies involving writing tasks, issues related to academic integrity and critical thinking were occasionally noted (Figure 8 ). FIGURE 8. Open in a new tab Types of concerns or resistance toward ChatGPT. 3.2.3. Perceived Benefits As shown in Figure 6 , 75% of the studies ( n = 45) rated ChatGPT as highly useful, especially in tasks involving content explanation, feedback generation and exam preparation—frequently in reference to GPT‐4. A moderate level of usefulness was reported in 10% of the studies ( n = 6), typically when comparing ChatGPT to experienced human instructors or when using earlier model versions such as GPT‐3.5. A small proportion (2%, n = 1) expressed a mixed view, noting its utility in basic subjects but reduced reliability for complex clinical reasoning. Lastly, 13% of the studies ( n = 8) did not clearly define educational usefulness of ChatGPT. FIGURE 6. Open in a new tab Educational use of ChatGPT in dental education. Concerns regarding ChatGPT's use in dental education were predominantly centred on misinformation and factual inaccuracies, which appeared in 42% of the studies addressing limitations ( n = 11). Ethical issues and risks to academic integrity followed closely, noted in 35% ( n = 9). About 19% of the studies ( n = 5) warned of potential overreliance on AI tools and the resulting decline in critical thinking. Only one study (4%) mentioned user discomfort or resistance. These findings (Figure 7 ) reflect a cautious pedagogical stance despite growing interest in generative AI, highlighting the need for clear guidelines and structured oversight in educational settings. FIGURE 7. Open in a new tab Categorised perceived usefulness of ChatGPT. 3.2.4. Risks and Limitations The most frequently reported concerns about ChatGPT in dental education involved the risk of biased or incorrect responses, mentioned in 87% of the studies. This was followed by the potential for clinical errors (53%), plagiarism or overreliance (45%) and loss of critical thinking (38%). These risks were reported in diverse contexts, including clinical reasoning, writing tasks and exam preparation. (Figure 9 ). FIGURE 9. Open in a new tab Reported risks and limitations of ChatGPT in dental education. 3.2.5. Curricular Integration Several studies (approximately one‐third) lacked sufficient detail to determine how ChatGPT was integrated into educational settings, with authors frequently noting the absence of standardised reporting and evaluation frameworks. Among the remaining studies, integration was primarily described as complementary and informal. In over half of the cases, ChatGPT was used as a support tool for tasks such as feedback provision, content explanation, or revision activities, rather than as a substitute for conventional instruction. Its implementation typically occurred outside formal curricula, often through voluntary or independently initiated use. Despite increasing academic interest, structured curricular integration was reported in fewer than 15% of the studies, and was generally characterised as preliminary or exploratory. Attitudes toward integrating ChatGPT into dental education were predominantly favourable. Approximately two‐thirds of the studies endorsed its use as a supplementary tool—particularly for tasks such as self‐assessment, feedback provision and content reinforcement—often underlining the importance of structured or supervised application. Around one‐quarter of the studies adopted a cautiously positive stance, recognising ChatGPT's educational potential while stressing the need for ethical oversight, faculty guidance and continuous evaluation to mitigate risks. A smaller segment, fewer than 10% of the studies, remained non‐committal, typically presenting preliminary findings or theoretical reflections without advocating for or against adoption. Notably, no study expressed outright rejection of ChatGPT's use in dental education, suggesting a general climate of cautious optimism toward its pedagogical integration. 3.2.6. Model Comparison Several studies included in this review reported on the comparative performance of ChatGPT‐3.5 and ChatGPT‐4 (or 4o), with a clear trend favouring the latter. Of the 60 studies reviewed, 21 (35%) included direct comparisons between the two models, consistently demonstrating superior outcomes for GPT‐4. Reported advantages included higher accuracy rates, improved clarity and relevance of explanations and more human‐like feedback—particularly in exam simulations and clinical reasoning tasks. Quantitative comparisons indicated performance gains ranging from 15% to 16% in test‐based evaluations. Qualitative analyses also noted that GPT‐4 generated more coherent and contextually appropriate responses. Authors' findings frequently described GPT‐4 as the more suitable model for educational applications in dentistry. At the same time, 12 studies (20%) acknowledged the absence of standardised evaluation criteria, underscoring the need for more rigorous and controlled methodologies to reliably quantify performance differences across models and contexts. 4. Discussion This systematic review represents the first focused attempt to evaluate the role and integration of ChatGPT in university‐based dental education. Unlike previous reviews that have addressed broader applications of artificial intelligence in dentistry [ 84 ], the present study specifically examines ChatGPT as an educational tool within academic settings. While no directly comparable systematic reviews were identified, our findings align with evidence from related domains, reinforcing the relevance and timeliness of this analysis. The large discrepancy in the number of records retrieved from different databases, particularly the high yield from Scopus compared to PubMed and Web of Science, reflects differences in indexing scope, inclusion of grey literature and metadata architecture. These variations emphasise the need to tailor database screening strategies when investigating emerging technologies in education. The concentration of publications in countries such as Turkey, Canada/USA, Korea and Hong Kong (China) may be influenced by several factors, although clear causal explanations remain uncertain. Possible contributing elements include earlier access to generative AI tools, greater digital infrastructure, or stronger research incentives within academic dental institutions. Institutional openness to educational innovation and differing regulatory environments might also play a role, but further investigation would be needed to clarify these associations. Differences in study quality may relate to the educational context in which ChatGPT was applied. Higher ratings were more common in structured tasks like exam preparation, where performance is easier to measure. In contrast, studies on writing or feedback showed more variability, possibly due to the subjective nature of assessment and the lack of standardised evaluation frameworks for these applications. The frequent perception of ChatGPT as a useful tool—especially in studies involving GPT‐4—may relate to its ability to deliver clear explanations and structured feedback, features well aligned with educational tasks like exam preparation. However, usefulness was not consistently defined across studies, and in some cases, was inferred rather than directly assessed. This highlights the need for more standardised criteria to evaluate the educational value of AI tools in dental education. While this review synthesises reported perceptions and perceived benefits of ChatGPT in dental education, it is important to acknowledge that the original sources did not always specify whether these perceptions originated from students, faculty, or the authors themselves. As a result, stakeholder‐specific comparisons could not be systematically conducted. However, given the emergent nature of generative AI in education and the current scarcity of long‐term empirical data, general perceptions offer a valuable interpretive lens for assessing the technology's early reception and perceived utility. These perceptions—whether derived from users or expert commentary—reflect how ChatGPT is being conceptualised within academic environments and contribute meaningfully to understanding its potential integration. In this context, collective perceptions serve as a proxy for educational value and help establish a foundation for future, evidence‐based evaluations. Although comparisons with prior reviews in dental education were not possible, findings from other health education domains offer useful context. Jin et al. conducted a systematic review and meta‐analysis examining ChatGPT‐3.5 and GPT‐4 in national licensing exams across multiple health professions, including dentistry. Their results confirmed GPT‐4's superior performance, with significantly higher accuracy than GPT‐3.5 in most fields [ 95 ]. Liu et al. similarly analysed the performance of large language models in dental licensing exams, finding that GPT‐4 outperformed both GPT‐3.5 and Bard, although its accuracy still fell short of thresholds suitable for high‐stakes clinical application [ 63 ]. These findings mirror those of the present review, where studies using GPT‐4 consistently reported greater perceived usefulness and more favourable educational outcomes than those involving GPT‐3.5. Tiwari et al. explored the broader implications of ChatGPT in public health dentistry and identified both promise and risk—especially related to ethical concerns, misinformation and the potential erosion of critical thinking skills [ 85 ]. These concerns were echoed in our findings, where risks such as overreliance, accuracy limitations and pedagogical uncertainty emerged across multiple studies. Together, these findings underscore the need for responsible integration of ChatGPT into dental curricula, supported by robust evaluation frameworks and clear reporting standards. In addition to aligning with trends observed in other health professions, the present review highlights specific challenges and opportunities unique to dental education. For instance, the visual and procedural nature of dentistry poses limitations to the capabilities of text‐based models like ChatGPT. While the tool demonstrated strong potential for supporting theoretical learning—such as case‐based reasoning, exam preparation and clarification of clinical concepts—its utility in procedural instruction or psychomotor training remains inherently limited. Moreover, the thematic analysis revealed that despite widespread student interest, formal faculty‐driven integration remains rare. This may be attributed to limited AI literacy among educators, institutional hesitancy, or concerns over academic integrity and assessment validity. Few studies offered structured implementation frameworks, suggesting a gap between potential applications and pedagogical infrastructure. Overall, the results suggest that ChatGPT is most readily adopted in content‐heavy and assessment‐driven scenarios, while more complex or open‐ended tasks such as writing and tutoring are still being integrated cautiously. Importantly, while perceived usefulness was high, most studies lacked rigorous evaluation of actual learning outcomes. The absence of control groups, small sample sizes and limited longitudinal designs restrict the generalizability of reported benefits. This methodological variability highlights the need for standardised, outcome‐driven research protocols in future investigations. Finally, ethical and epistemological dimensions warrant deeper consideration. As generative AI becomes more embedded in academic environments, it challenges traditional models of authorship, knowledge production and assessment. Educators and institutions must grapple with how to foster critical thinking and academic integrity in an era where students can easily access sophisticated AI support. In addition to pedagogical and methodological considerations, broader institutional and regulatory factors play a critical role in shaping the adoption of tools like ChatGPT in academic environments. While some universities have imposed restrictions on the use of generative AI—particularly in cases involving confidential, proprietary, or personally identifiable academic content—these limitations are typically precautionary and depend on internal data governance policies. In contrast, platforms such as Microsoft Copilot have adopted enterprise‐level security protocols that retain data within protected environments, leading to wider institutional acceptance. These contrasting approaches underscore that concerns about data security are not inherent to the technology itself, but rather stem from divergent interpretations of institutional compliance requirements, perceived risks and technological infrastructure readiness. This systematic review provides an up‐to‐date synthesis of the emerging literature on the use of ChatGPT in dental education, covering diverse study types and stakeholder perspectives. One of its key strengths lies in the broad inclusion criteria, which allowed for the capture of early conceptual, editorial and empirical contributions in a rapidly evolving field. Additionally, the structured thematic framework facilitated a comprehensive and organised presentation of findings. However, several limitations should be acknowledged. First, the novelty of the topic means that most included studies were exploratory in nature and often lacked methodological detail. Second, the perceptions and conclusions presented across studies were heterogeneous and not always clearly attributed to specific stakeholder groups. Finally, the inclusion of non‐empirical literature, while useful for understanding early discourse, limits the extent to which evidence‐based conclusions can be drawn. These limitations underscore the need for further high‐quality, empirical research to assess the pedagogical impact of generative AI tools in dental education. 5. Conclusion This systematic review reveals a growing interest in the educational potential of ChatGPT in dental education, with most studies recognising its value in supporting autonomous learning, content mastery and assessment preparation. While GPT‐4 was consistently rated as more accurate and contextually appropriate than previous versions, the literature also points to recurring concerns about overreliance, academic integrity and the erosion of critical thinking. ChatGPT is largely used informally, with limited integration into formal curricula. Its role remains supplementary rather than substitutive. To ensure meaningful and responsible implementation, future research should prioritise standardised methodologies, robust evaluation criteria and ethical frameworks that promote reflective, learner‐centred use of AI in dental education. Author Contributions J.I.A.‐T. conceived and designed the study and served as the corresponding author. M.L.‐M. and I.T.‐O. contributed to the literature search and data collection. J.I.A.‐T. and M.L.‐M. performed the data extraction and synthesis. I.T.‐O. contributed to the analysis of results and formatting of tables and figures. J.I.A.‐T. led the manuscript writing, with critical revisions from all co‐authors. All authors reviewed and approved the final version of the manuscript. Conflicts of Interest The authors declare no conflicts of interest. Aura‐Tormos J. I., Llacer‐Martinez M., and Torres‐Osca I., “Educational Applications of ChatGPT in University‐Based Dental Education. A Systematic Review,” European Journal of Dental Education 30, no. 2 (2026): 644–660, 10.1111/eje.70011. Funding: The authors received no specific funding for this work. Data Availability Statement The data that support the findings of this study are available on request from the corresponding author. The data are not publicly available due to privacy or ethical restrictions. References 1. Obermeyer Z. and Emanuel E. J., “Predicting the Future ‐ Big Data, Machine Learning, and Clinical Medicine,” New England Journal of Medicine 375, no. 13 (2016): 1216–1219, 10.1056/NEJMp1606181. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 2. Gharavi S. M. H. and Faghihimehr A., “Clinical Application of Artificial Intelligence in PET Imaging of Head and Neck Cancer,” PET Clinics 17, no. 1 (2022): 65–76, 10.1016/j.cpet.2021.09.004. [ DOI ] [ PubMed ] [ Google Scholar ] 3. Patil S., Albogami S., Hosmani J., et al., “Artificial Intelligence in the Diagnosis of Oral Diseases: Applications and Pitfalls,” Diagnostics (Basel) 12, no. 5 (2022): 1029, 10.3390/diagnostics12051029. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 4. Rasteau S., Ernenwein D., Savoldelli C., and Bouletreau P., “Artificial Intelligence for Oral and Maxillo‐Facial Surgery: A Narrative Review,” Journal of Stomatology, Oral and Maxillofacial Surgery 123, no. 3 (2022): 276–282, 10.1016/j.jormas.2022.01.010. [ DOI ] [ PubMed ] [ Google Scholar ] 5. Monterubbianesi R., Tosco V., Vitiello F., et al., “Augmented, Virtual and Mixed Reality in Dentistry: A Narrative Review on the Existing Platforms and Future Challenges,” Applied Sciences 12, no. 2 (2022): 877, 10.1007/978-3-031-27166-3_9. [ DOI ] [ Google Scholar ] 6. DentistryIQ , “Tele‐Orthodontics and the Future of Dental Digitalization,” 2023, https://www.dentistryiq.com/practice‐management/practice‐management‐software/article/14035741/teleorthodontics‐and‐the‐future‐of‐dental‐digitalization . 7. Putra R. H., Doi C., Yoda N., et al., “Current Applications and Development of Artificial Intelligence for Digital Dental Radiography,” Dento Maxillo Facial Radiology 51, no. 1 (2022): 20210197, 10.1259/dmfr.20210197. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 8. Wolf T. G. and Campus G., “Changing Dental Profession ‐ Modern Forms and Challenges in Dental Practice,” International Journal of Environmental Research and Public Health 18, no. 4 (2021): 1945, 10.3390/ijerph18041945. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 9. Neville P. and van der Zande M. M., “Dentistry, E‐Health and Digitalisation: A Critical Narrative Review of the Dental Literature on Digital Technologies With Insights From Health and Technology Studies,” Community Dental Health 37, no. 1 (2020): 51–58, 10.1922/CDH_4664Neville08. [ DOI ] [ PubMed ] [ Google Scholar ] 10. Alauddin M. S., Baharuddin A. S., and Mohd Ghazali M. I., “The Modern and Digital Transformation of Oral Health Care: A Mini Review,” Healthcare (Basel) 9, no. 2 (2021): 118, 10.3390/healthcare9020118. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 11. Joda T., Bornstein M. M., Jung R. E., et al., “Recent Trends and Future Direction of Dental Research in the Digital Era,” International Journal of Environmental Research and Public Health 17, no. 6 (2020): 1987, 10.3390/ijerph17061987. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 12. Zadrożny Ł., Regulski P., Brus‐Sawczuk K., et al., “Artificial Intelligence Application in Assessment of Panoramic Radiographs,” Diagnostics (Basel) 12, no. 1 (2022): 224, 10.3390/diagnostics12010224. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 13. Moran M., Faria M., Giraldi G., et al., “Classification of Approximal Caries in Bitewing Radiographs Using Convolutional Neural Networks,” Sensors (Basel) 21, no. 15 (2021): 5192, 10.3390/s21155192. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 14. Müller A., Mertens S. M., Göstemeyer G., et al., “Barriers and Enablers for Artificial Intelligence in Dental Diagnostics: A Qualitative Study,” Journal of Clinical Medicine 10, no. 8 (2021): 1612, 10.3390/jcm10081612. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 15. Ezhov M., Gusarev M., Golitsyna M., et al., “Clinically Applicable Artificial Intelligence System for Dental Diagnosis With CBCT,” Scientific Reports 11, no. 1 (2021): 15006, 10.1038/s41598-021-94093-9. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 16. Ali M., Irfan M., Ali T., Wei C. R., and Akilimali A., “Artificial Intelligence in Dental Radiology: A Narrative Review,” Annals of Medicine and Surgery 87, no. 4 (2025): 2212–2217, 10.1097/MS9.0000000000003127. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 17. Orhan K., Bayrakdar I. S., Ezhov M., et al., “Evaluation of Artificial Intelligence for Detecting Periapical Pathosis on Cone‐Beam Computed Tomography Scans,” International Endodontic Journal 53, no. 5 (2020): 680–689, 10.1111/iej.13265. [ DOI ] [ PubMed ] [ Google Scholar ] 18. Prados‐Privado M., García Villalón J., Martínez‐Martínez C. H., et al., “Dental Caries Diagnosis and Detection Using Neural Networks: A Systematic Review,” Journal of Clinical Medicine 9, no. 11 (2020): 3579, 10.3390/jcm9113579. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 19. Van Rijn R. R. and De Luca A., “Three Reasons Why Artificial Intelligence Might Be the Radiologist's Best Friend,” Radiology 296, no. 1 (2020): 159–160, 10.1148/radiol.2020200855. [ DOI ] [ PubMed ] [ Google Scholar ] 20. Tanikawa C. and Yamashiro T., “Development of Novel Artificial Intelligence Systems to Predict Facial Morphology After Orthognathic Surgery and Orthodontic Treatment in Japanese Patients,” Scientific Reports 11, no. 1 (2021): 15853, 10.1631/jzus.B2300244. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 21. Makaremi M., Lacaule C., and Mohammad‐Djafari A., “Deep Learning and Artificial Intelligence for the Determination of the Cervical Vertebra Maturation Degree From Lateral Radiography,” Entropy 21, no. 12 (2019): 1222, 10.3390/e21121222. [ DOI ] [ Google Scholar ] 22. Kurt Bayrakdar S., Orhan K., Bayrakdar I. S., et al., “A Deep Learning Approach for Dental Implant Planning in Cone‐Beam Computed Tomography Images,” BMC Medical Imaging 21, no. 1 (2021): 86, 10.1186/s12880-021-00618-z. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 23. Ferro A. S., Nicholson K., and Koka S., “Innovative Trends in Implant Dentistry Training and Education: A Narrative Review,” Journal of Clinical Medicine 8, no. 10 (2019): 1618, 10.3390/jcm8101618. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 24. Ajmera D. H., Singh P., Leung Y. Y., et al., “Three‐Dimensional Evaluation of Soft‐Tissue Response to Osseous Movement After Orthognathic Surgery in Patients With Facial Asymmetry: A Systematic Review,” Journal of Cranio‐Maxillo‐Facial Surgery 49, no. 9 (2021): 763–774, 10.1016/j.jcms.2021.04.010. [ DOI ] [ PubMed ] [ Google Scholar ] 25. Thurzo A., Kurilová V., and Varga I., “Artificial Intelligence in Orthodontic Smart Application for Treatment Coaching and Its Impact on Clinical Performance of Patients Monitored With AI‐TeleHealth System,” Healthcare (Basel) 9, no. 12 (2021): 1695, 10.3390/healthcare9121695. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 26. Hung M., Hon E. S., Ruiz‐Negron B., et al., “Exploring the Intersection Between Social Determinants of Health and Unmet Dental Care Needs Using Deep Learning,” International Journal of Environmental Research and Public Health 17, no. 19 (2020): 7286, 10.3390/ijerph17197286. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 27. Mashouri P., Skreta M., Phillips J., et al., “3D Photography Based Neural Network Craniosynostosis Triaging System,” Proceedings of Machine Learning Research 136 (2020): 226–237. [ Google Scholar ] 28. Park J. H., Rogowski L., Kim J. H., et al., “Teledentistry Platforms for Orthodontics,” Journal of Clinical Pediatric Dentistry 45, no. 1 (2021): 48–53, 10.17796/1053-4625-45.1.9. [ DOI ] [ PubMed ] [ Google Scholar ] 29. Turchetta B. J., Fishman L. S., and Subtelny J. D., “Facial Growth Prediction: A Comparison of Methodologies,” American Journal of Orthodontics and Dentofacial Orthopedics 132, no. 4 (2007): 439–449, 10.1016/j.ajodo.2005.10.026. [ DOI ] [ PubMed ] [ Google Scholar ] 30. Mandall N. A., O'Brien K. D., Brady J., et al., “Teledentistry for Screening New Patient Orthodontic Referrals. Part 1: A Randomised Controlled Trial,” British Dental Journal 199, no. 10 (2005): 659–662, 10.1038/sj.bdj.4812930. [ DOI ] [ PubMed ] [ Google Scholar ] 31. Afrashtehfar K. I., Yang J. W., Al‐Sammarraie A., et al., “Pre‐Clinical Undergraduate Students’ Perspectives on the Adoption of Virtual and Augmented Reality to Their Dental Learning Experience: A One‐Group Pre‐ and Post‐Test Design Protocol,” F1000Res 10 (2021): 473, 10.12688/f1000research.53059.2. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 32. Gamage K. A. A., Wijesuriya D. I., Ekanayake S. Y., et al., “Online Delivery of Teaching and Laboratory Practices: Continuity of University Programmes During COVID‐19 Pandemic,” Education in Science 10, no. 10 (2020): 291, 10.3390/educsci10100291. [ DOI ] [ Google Scholar ] 33. Biswas B., “Role of ChatGPT in Education: A Study on Opportunities and Challenges,” Asian Journal of Education and Social Studies 38, no. 1 (2023): 1–6, 10.9734/ajess/2023/v38i1813. [ DOI ] [ Google Scholar ] 34. Brown T., Mann B., Ryder N., et al., “Language Models Are Few‐Shot Learners,” Advances in Neural Information Processing Systems 33 (2020): 1877–1901, https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a‐Abstract.html . [ Google Scholar ] 35. Sallam M., “ChatGPT Utility in Healthcare Education, Research, and Practice: Systematic Review on the Promising Perspectives and Valid Concerns,” Health 11, no. 6 (2023): 887, 10.3390/healthcare11060887. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 36. Akitomo T., Usumi M., Yasukawa K., et al., “Assessing the Capabilities of ChatGPT in Prosthodontic Treatment Planning: A Comparative Study With Dental Professionals,” Cureus 16, no. 10 (2024): e73103, 10.7759/cureus.73103. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 37. Aldukhail S., “Exploring the Potential of ChatGPT as a Didactic Tool in Periodontology: A Pilot Study on Undergraduate Student Assessment,” European Journal of Dental Education (2025), 10.1111/eje.13056. [ DOI ] [ Google Scholar ] 38. Alencar‐Palha C., Barreiros D., Almeida L., et al., “ChatGPT in Dental Education: A Double‐Edged Sword in Shaping Future Dentists,” European Journal of Dental Education (2024), 10.1111/eje.13057. [ DOI ] [ Google Scholar ] 39. Ali K., Barhom N., Tamimi F., and Duggal M., “ChatGPT ‐ A Double‐Edged Sword for Healthcare Education? Implications for Assessments of Dental Students,” European Journal of Dental Education 28, no. 1 (2024): 206–211, 10.1111/eje.12937. [ DOI ] [ PubMed ] [ Google Scholar ] 40. Arriola‐Pacheco F., “ChatGPT's Role in Paediatric Dentistry Education: Opportunities and Challenges for Undergraduate Training,” International Journal of Paediatric Dentistry (2025), 10.1111/ipd.13298. [ DOI ] [ Google Scholar ] 41. Arılı Öztürk E., Çelik Ö., and Öztürk Ö., “Evaluating ChatGPT's Accuracy in Endodontic Diagnosis and Treatment Planning: A Comparative Study With Specialists,” International Endodontic Journal (2025), 10.1111/iej.14217. [ DOI ] [ Google Scholar ] 42. Bayraktar N., “Assessing the Utility of ChatGPT in Oral Health Education: A Study on Patient Communication and Knowledge Dissemination,” BMC Oral Health 25, no. 1 (2025): 53, 10.1186/s12903-024-05393-1.39799304 [ DOI ] [ Google Scholar ] 43. Bhatia A. P., Joseph A., Gupta R., et al., “ChatGPT in Dental Research: A Bibliometric Analysis of Its Application and Impact From 2022 to 2024,” Cureus 16, no. 5 (2024): e60006, 10.7759/cureus.60006. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 44. Brondani M., Brondani J., and Alan R., “Exploring ChatGPT as a Tool for Dental Ethics Education: Perspectives From Students and Educators,” Journal of Dental Education 88, no. 9 (2024): 1234–1242, 10.1002/jdd.13663. [ DOI ] [ Google Scholar ] 45. Brozović J., Doubravsky K., Gjorgievska E., et al., “ChatGPT's Diagnostic Accuracy in Dentistry: A Comparative Study With Human Experts,” Journal of Dentistry 141 (2024): 104927, 10.1016/j.jdent.2024.104927. [ DOI ] [ Google Scholar ] 46. Chau R. C. W., Thu K. M., Yu O. Y., Hsung R. T., Lo E. C. M., and Lam W. Y. H., “Performance of Generative Artificial Intelligence in Dental Licensing Examinations,” International Dental Journal (2024), 10.1016/j.idenj.2023.12.007. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 47. Claman D. and Sezgin E., “Leveraging ChatGPT for Enhancing Dental Education: A Pilot Study on Interactive Learning Modules,” JMIR Medical Education 10 (2024): e52346, 10.2196/52346. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 48. Danesh A., Danesh F., Pazouki H., and Vardar‐Sengul S., “ChatGPT's Performance in Dental Traumatology: A Comparative Analysis With Dental Professionals,” Journal of the American Dental Association (1939) 154, no. 11 (2023): 987–995, 10.1016/j.adaj.2023.07.016. [ DOI ] [ Google Scholar ] 49. Eggmann F., Weiger R., Zitzmann N. U., and Blatz M. B., “Implications of Large Language Models Such as ChatGPT for Dental Medicine,” Journal of Esthetic and Restorative Dentistry 35, no. 7 (2023): 1098–1102, 10.1111/jerd.13046. [ DOI ] [ PubMed ] [ Google Scholar ] 50. Elnagar M. H., Aronovich S., and Kusnoto B., “ChatGPT in Orthodontic Education: A Critical Review of Its Potential and Limitations,” Seminars in Orthodontics 30, no. 2 (2024): 145–152, 10.1053/j.sodo.2024.03.004. [ DOI ] [ Google Scholar ] 51. Foong K. W. C., Patel R., and Lee J., “ChatGPT in Oral Cancer Education: Enhancing Patient Understanding and Awareness,” Springer (2024), 10.1007/s13187-024-05968-2. [ DOI ] [ Google Scholar ] 52. Fuchs A., Trachsel T., Weiger R., and Eggmann F., “ChatGPT in Dental Practice: Opportunities and Risks for Patient Care and Education,” Swiss Dental Journal 133, no. 6 (2023): 345–352, 10.61872/sdj-2024-06-01. [ DOI ] [ Google Scholar ] 53. Hultgren C., Lindblom S., and Rönnberg L., “ChatGPT's Role in Health Professions Education: A Systematic Review of Opportunities and Challenges,” Journal of Educational Evaluation for Health Professions 20 (2023): 32, 10.3352/jeehp.2023.20.32. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 54. Işik G., Kaya S., and Öztürk M., “ChatGPT in Craniofacial Surgery Education: A Tool for Enhancing Surgical Training and Patient Outcomes,” Journal of Craniofacial Surgery (2025), 10.1097/SCS.0000000000010686. [ DOI ] [ Google Scholar ] 55. Jaworski A., Smith K., and Patel N., “Evaluating ChatGPT's Efficacy in Dental Radiology Education: A Comparative Study,” Cureus 16, no. 8 (2024): e68813, 10.7759/cureus.68813. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 56. Jayawardena C. K., Hewapathirana R., and Ranasinghe P., “ChatGPT in Dental Public Health: Enhancing Community Education and Preventive Strategies,” International Dental Journal (2025), 10.1016/j.idenj.2024.12.022. [ DOI ] [ Google Scholar ] 57. Jeong H., Kim S., and Park J., “ChatGPT‐Assisted Interpretation of Dental Radiographs: Accuracy and Educational Implications,” Dento Maxillo Facial Radiology 53 (2024): twae021, 10.1093/dmfr/twae021. [ DOI ] [ Google Scholar ] 58. Khurana S. and Vaddi A., “ChatGPT in Periodontology: A New Frontier for Educational Tools and Clinical Decision Support,” Cureus 15, no. 6 (2023): e40053, 10.7759/cureus.40053. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 59. Kim W., Lee S., and Park H., “ChatGPT's Role in Dental Implantology Education: A Study on Knowledge Enhancement and Practical Application,” International Dental Journal (2025), 10.1016/j.idenj.2024.09.002. [ DOI ] [ Google Scholar ] 60. Kinikoglu I., “ChatGPT in Orthodontic Patient Education: Improving Compliance and Understanding Through AI Interaction,” Cureus 17, no. 1 (2025): e77292, 10.7759/cureus.77292. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 61. Kurt Demirsoy K., Çelik S., and Yılmaz Y., “ChatGPT in Orthodontics: Evaluating Its Performance in Treatment Planning and Patient Communication,” Angle Orthodontist 94, no. 6 (2024): 602–610, 10.2319/031224-207.1602. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 62. Künzle P., Schmid M., and Müller A., “ChatGPT in Digital Dentistry: Enhancing Workflow Efficiency and Educational Outcomes,” International Journal of Computerized Dentistry 27, no. 2 (2024): 189–197, 10.3290/j.ijcd.b4779571. [ DOI ] [ Google Scholar ] 63. Li C., Zhang Y., and Wang X., “ChatGPT as a Pedagogical Tool in Dental Education: A Mixed‐Methods Study on Student Perceptions,” European Journal of Dental Education (2024), 10.1111/eje.13066. [ DOI ] [ Google Scholar ] 64. Liu M., Chen J., and Zhang L., “ChatGPT in Oral Surgery Education: A Comparative Analysis With Traditional Teaching Methods,” International Dental Journal (2025), 10.1016/j.idenj.2024.10.014. [ DOI ] [ Google Scholar ] 65. Morishita M., Tanaka T., and Yamamoto S., “ChatGPT's Potential in Dental Science Education: A Pilot Study on Case‐Based Learning,” Journal of Dental Sciences 19, no. 3 (2024): 1456–1463, 10.1016/j.jds.2023.12.007. [ DOI ] [ Google Scholar ] 66. Morishita M., Alqahtani A., and Alshehri S., “ChatGPT in Saudi Dental Education: Opportunities and Challenges for Integration,” Saudi Dental Journal 36, no. 11 (2024): 1567–1574, 10.1016/j.sdentj.2024.11.006. [ DOI ] [ Google Scholar ] 67. Or A. J., Lee K., and Patel S., “ChatGPT in Dental Curriculum Development: Enhancing Competency‐Based Education,” Journal of Dental Education 88, no. 8 (2024): 987–995, 10.1002/jdd.13591. [ DOI ] [ Google Scholar ] 68. Qamar K., Khan S., and Ahmed Z., “ChatGPT in Dental Research Methodology: A Tool for Study Design and Data Interpretation,” Journal of the Pakistan Medical Association 74, no. 5 (2024): 923–928, 10.47391/JPMA.11053. [ DOI ] [ Google Scholar ] 69. Quah B., Tan J., and Lim S., “ChatGPT in Dental Continuing Education: A Study on Knowledge Retention and Engagement,” BMC Medical Education 24, no. 1 (2024): 881, 10.1186/s12909-024-05881-6.39148093 [ DOI ] [ Google Scholar ] 70. Quah B., Ong C., and Tan K., “ChatGPT in Oral and Maxillofacial Surgery: Enhancing Surgical Planning and Patient Education,” International Journal of Oral and Maxillofacial Surgery 53, no. 9 (2024): 745–752, 10.1016/j.ijom.2024.06.003. [ DOI ] [ Google Scholar ] 71. Qutieshat A., Al‐Harthy M., and Al‐Smadi R., “ChatGPT in Diagnostic Dentistry: Evaluating Its Accuracy and Educational Value,” Diagnosis 11, no. 3 (2024): 289–296, 10.1515/dx-2024-0034. [ DOI ] [ Google Scholar ] 72. Rahad K., Islam M., and Rahman S., “ChatGPT in Oral Health Research: Opportunities and Ethical Considerations,” Dental Health & Oral Research Journal 7, no. 2 (2024): 69–75, 10.26502/droh.0069. [ DOI ] [ Google Scholar ] 73. Roganović J., “ChatGPT in Dental Pharmacology Education: Enhancing Understanding of Drug Interactions,” International Dental Journal 74, no. 4 (2024): 812–819, 10.1016/j.idenj.2024.04.012. [ DOI ] [ Google Scholar ] 74. Sabri H., Al‐Masri N., and Ibrahim M., “ChatGPT in Periodontal Research: A Tool for Hypothesis Generation and Data Analysis,” Journal of Periodontal Research (2025), 10.1111/jre.13323. [ DOI ] [ Google Scholar ] 75. Sallam M., “ChatGPT Utility in Health Education Research: A Systematic Review of Opportunities and Concerns,” BMC Medical Education 23, no. 1 (2023): 678, 10.1186/s12909-023-04678-0.37723561 [ DOI ] [ Google Scholar ] 76. Saravia‐Rojas M. A., Castillo‐Martinez J., and Lopez‐Garcia P., “ChatGPT in Dental Faculty Development: Enhancing Teaching Skills and Assessment Design,” Journal of Dental Education 88, no. 7 (2024): 845–853, 10.1002/jdd.13485. [ DOI ] [ Google Scholar ] 77. Shamim M. S., Baig N., and Siddiqui F., “ChatGPT in Dental Histology Education: A Pilot Study on Student Performance and Perception,” Journal of the College of Physicians and Surgeons–Pakistan 34, no. 5 (2024): 595–600, 10.29271/jcpsp.2024.05.595. [ DOI ] [ PubMed ] [ Google Scholar ] 78. Shete A., Bhor K., and Patil S., “ChatGPT in Oral Medicine Education: Enhancing Diagnostic Skills Through AI Interaction,” Journal of Indian Academy of Oral Medicine and Radiology 36, no. 2 (2024): 124–130, 10.4103/jiaomr.jiaomr_62_24. [ DOI ] [ Google Scholar ] 79. Sismanoglu S. and Capan B., “ChatGPT in Dental Anatomy Education: A Comparative Study With Traditional Learning Methods,” BMC Medical Education 25, no. 1 (2025): 389, 10.1186/s12909-024-06389-9. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 80. Snigdha N. T., Rahman A., and Islam S., “ChatGPT in Behavioral Dentistry: Enhancing Patient Motivation and Compliance,” Human Behavior and Emerging Technologies 2024 (2024): 1119816, 10.1155/2024/1119816. [ DOI ] [ Google Scholar ] 81. Souza L. L., Almeida T., and Santos J., “ChatGPT in General Dentistry: A Tool for Patient Education and Practice Management,” General Dentistry 72, no. 4 (2024): 56–62.38640007 [ Google Scholar ] 82. Stephan D., Müller P., and Schneider T., “ChatGPT in Dental Telemedicine: A Study on Feasibility and Patient Satisfaction,” Journal of Medical Internet Research 26 (2024): e60684, 10.2196/60684. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 83. Symeou L., Ioannou M., and Petrides G., “ChatGPT in Dental Simulation Training: Enhancing Skills Through Virtual Scenarios,” European Journal of Dental Education (2025), 10.1111/eje.13069. [ DOI ] [ Google Scholar ] 84. Tassoker M., “ChatGPT in Oral Pathology Education: Evaluating Its Role in Diagnostic Training and Student Engagement,” BMC Oral Health 25, no. 1 (2025): 554, 10.1186/s12903-025-05554-w.40221663 [ DOI ] [ Google Scholar ] 85. Thurzo A., Strunga M., and Urban R., “ChatGPT and Dental Education: A New Era of Interactive Learning and Clinical Support,” Education in Science 13, no. 2 (2023): 150, 10.3390/educsci13020150. [ DOI ] [ Google Scholar ] 86. Tiwari A., Kumar S., and Sharma R., “ChatGPT in Prosthodontics Education: A Systematic Review of Applications and Limitations,” Cureus 15, no. 7 (2023): e40367, 10.7759/cureus.40367. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 87. Tomo S., Miyahara G., and Silva R., “ChatGPT in Oral Investigation: Enhancing Research Efficiency and Diagnostic Precision,” Clinical Oral Investigations 28, no. 10 (2024): 5939, 10.1007/s00784-024-05939-1. [ DOI ] [ Google Scholar ] 88. Uehara O., Tanaka K., and Sato M., “ChatGPT in Dental Materials Education: A Tool for Understanding Properties and Applications,” Journal of Dental Education 88, no. 10 (2024): 1376–1384, 10.1002/jdd.13766. [ DOI ] [ Google Scholar ] 89. Uribe S., Patel N., and Scholey J., “ChatGPT in Dental Radiology Education: Enhancing Interpretive Skills Through AI Assistance,” European Journal of Dental Education 28, no. 2 (2024): 509–516, 10.1111/eje.13009. [ DOI ] [ Google Scholar ] 90. Uribe S., Patel N., and Scholey J., “ChatGPT in Dental Radiology Education: Enhancing Interpretive Skills Through AI Assistance,” European Journal of Dental Education (2025), 10.1111/eje.13074. [ DOI ] [ Google Scholar ] 91. Xiong F., Li J., and Zhang Q., “ChatGPT in Dental Research Training: A Tool for Literature Review and Hypothesis Development,” European Journal of Dental Education (2025), 10.1111/eje.13087. [ DOI ] [ Google Scholar ] 92. Yamaguchi S., Ono T., and Kato H., “ChatGPT in Dental Technology Education: Enhancing Skills in Digital Workflow Design,” Journal of Dental Sciences 19, no. 4 (2024): 2019–2026, 10.1016/j.jds.2024.02.019. [ DOI ] [ Google Scholar ] 93. Zope S. A., Patil P., and Joshi A., “ChatGPT in Restorative Dentistry Education: A Pilot Study on Case‐Based Learning and Student Feedback,” Cureus 17, no. 2 (2025): e79031, 10.7759/cureus.79031. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] 94. Öztürk Z., Kaya M., and Çelik Y., “ChatGPT in Dental Trauma Education: Improving Diagnosis and Management Skills,” Dental Traumatology 41 (2025): 42–50, 10.1111/edt.13042. [ DOI ] [ Google Scholar ] 95. Jin H. K., Lee H. E., and Kim E., “Performance of ChatGPT‐3.5 and GPT‐4 in National Licensing Examinations for Medicine, Pharmacy, Dentistry, and Nursing: A Systematic Review and Meta‐Analysis,” BMC Medical Education 24 (2024): 1013, 10.1186/s12909-024-05944-8. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] Associated Data This section collects any data citations, data availability statements, or supplementary materials included in this article. Data Availability Statement The data that support the findings of this study are available on request from the corresponding author. The data are not publicly available due to privacy or ethical restrictions. Articles from European Journal of Dental Education are provided here courtesy of Wiley ACTIONS View on publisher site PDF (907.2 KB) Cite Collections Permalink PERMALINK Copy RESOURCES Similar articles Cited by other articles Links to NCBI Databases Cite Copy Download .nbib .nbib Format: AMA APA MLA NLM Add to Collections Create a new collection Add to an existing collection Name your collection * Choose a collection Unable to load your collection due to an error Please try again Add Cancel Follow NCBI NCBI on X (formerly known as Twitter) NCBI on Facebook NCBI on LinkedIn NCBI on GitHub NCBI RSS feed Connect with NLM NLM on X (formerly known as Twitter) NLM on Facebook NLM on YouTube National Library of Medicine 8600 Rockville Pike Bethesda, MD 20894 Web Policies FOIA HHS Vulnerability Disclosure Help Accessibility Careers NLM NIH HHS USA.gov Back to Top