The Impact of Artificial Intelligence-Enabled Virtual Simulation on Clinical Reasoning in Dental Students in Managing Temporomandibular Disorders

The Impact of Artificial Intelligence-Enabled Virtual Simulation on Clinical Reasoning in Dental Students in Managing Temporomandibular Disorders | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article The Impact of Artificial Intelligence-Enabled Virtual Simulation on Clinical Reasoning in Dental Students in Managing Temporomandibular Disorders Pei Zhang, Wei He, Yilin Zhang, Zixin Zhou, Chunqin Wang, Chi Zhang, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8462289/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background The study aims to compare the efficacy of a virtual simulation-based teaching approach with a traditional method for clinical thinking training in temporomandibular disorders(TMD) for dental students. Methods This study developed a virtual simulation program for clinical thinking training related to TMD, which includes basic knowledge learning, virtual simulation practice, and learning effect testing. A quasi-experimental design was adopted, with 97 senior dental students as the experimental group, receiving the virtual simulation experimental teaching mode; and 81 senior students of the same major as the control group, adopting the traditional teaching mode. The teaching efficacy was evaluated through theoretical tests, written experimental reports, and questionnaires. Result The experimental group achieved significantly higher theoretical test score (84.6 ± 8.5 vs 78.7 ± 9.8, p < 0.0001) and operational skills total score (89.1 ± 7.4 vs 79.8 ± 9.2, p < 0.001) compared to the control group. In individual operational skills assessments, the experimental group outperformed the control group in history-taking, palpation, image interpretation, diagnosis, and treatment plan formulation. Additionally, the experimental group reported significantly higher satisfaction in theoretical learning, clinical thinking and operational skills, and overall satisfaction indicating greater engagement and perceived effectiveness of the virtual simulation model. Conclusion The virtual simulation system enhances learning engagement, clinical skills, theoretical knowledge retention via personalized pathways and real time feedback, thereby improving students' competence in TMD diagnosis and treatment planning. Dentistry Experimental Teaching Virtual Simulation Temporomandibular Disorders Artificial Intelligence Technology Figures Figure 1 Figure 2 Background Temporomandibular disorders (TMD) refer to a group of conditions affecting the temporomandibular joint and/or the masticatory muscle system, leading to symptoms such as joint pain, clicking, and limited mouth opening [ 1 ] . With a relatively high prevalence, epidemiological surveys report a global TMD incidence of approximately 29.5%–34% [ 2 , 3 ] . If left untreated, TMD can progress to joint locking, restricted mouth opening [ 4 ] , and in severe cases, complete inability to open the mouth. When TMD occurs in children or adolescents, it can lead to developmental abnormalities in the lower jaw, resulting in facial deformities that cause significant physical and psychological distress, severely impairing the patient's quality of life [ 5 ] . As global health awareness rises, the demand for TMD diagnosis and treatment is increasing, placing higher requirements on dental education [ 6 ] . Traditional TMD teaching primarily relies on classroom theoretical lectures and clinical practice [ 7 ] . However, the clinical diagnosis and classification of TMD are quite complex, which requires comprehensive consideration of factors such as patient history, clinical manifestations, imaging examinations, and laboratory tests [ 8 ] . Static teaching resources alone are insufficient to cultivate students' comprehensive clinical thinking abilities [ 9 ] . Moreover, clinical practice is limited by the number of cases, the experience of supervising teachers, and ethical constraints, making it difficult to provide adequate hands-on opportunities for every student or for teachers to guide multiple students simultaneously in analyzing complex cases [ 10 ] . This teaching model often results in graduates lacking sufficient clinical operational skills, directly affecting their career development [ 11 ] . Exploring new teaching methods has become an urgent issue to address [ 12 ] . The introduction of virtual simulation teaching can effectively resolve this problem, as virtual simulation technology has irreplaceable advantages in enhancing teaching effectiveness, enriching classroom formats, and enabling the sharing of high-quality experimental teaching resources, making it highly suitable for dental education [ 13 , 14 ] . In recent years, artificial intelligence (AI) technology has been widely applied in the education field, offering advantages such as enabling personalized learning, enhancing learning interactivity, and improving teaching efficiency [ 15 , 16 ] . Artificial intelligence has shown promising applications not only in diagnostic and educational contexts but also in other dental procedures, such as shade-matching [ 17 ] . In this project, AI technology not only provides students with real time question-answering services but also conducts systematic analysis of their learning outcomes, identifying areas of knowledge deficiency, and prompting targeted repetitive practice to improve mastery of the content. Additionally, AI can generate CT and MRI images as required for assessments, expanding the question bank, reducing the use of clinical data, and avoiding patient information leakage. Based on these foundations, this study developed an AI-based TMD virtual simulation teaching system, integrating software and hardware design to build a "virtual-real integration" comprehensive clinical thinking training platform. By evaluating students' mastery of basic knowledge and diagnosis, the differences between various teaching methods were compared. Through this approach, the study aims to identify the necessity of introducing virtual simulation teaching projects in TMD training, improve teaching protocols, and measure the effectiveness of such education in clinical practice. The comprehensive virtual simulation system is shown in Fig. 1 . Methods Features of the Comprehensive Virtual Simulation System This experimental platform integrated virtual reality, multimedia, human-computer interaction, force feedback hardware, and network communication technologies. It comprised three core modules: "Basic Knowledge Learning," "Clinical Examination Practice," and "Diagnosis and Treatment Planning," establishing a complete clinical diagnostic and therapeutic pathway of "examination-diagnosis-treatment" for TMD, a prevalent clinical condition. Learners engaged in role-playing to perform online clinical examinations, imaging assessments, diagnoses, and treatment plan formulations. The virtual environment, including clinic layout, clinical materials, and equipment, was modeled after the actual setting of the Temporomandibular Joint and Occlusion Clinic at Shandong University School of Stomatology. The platform was equipped with a joint vibration simulation device (Fig. 1 -F) developed by the course team, providing near-realistic tactile feedback for palpation examinations to enhance the learning experience. In the Basic Knowledge Learning module, users followed prompts to complete the full process of TMD patient consultation, examination, diagnosis, and treatment planning in a simulated clinical environment. During learning, the platform evaluated performance based on key clinical points through multiple-choice questions and operational tasks, covering 4 aspects including consultation, examination techniques, diagnostic accuracy, and treatment plan rationality, with assigned scores. It supported repeated practice and retrospective analysis of human-computer interactions. If errors occurred in operations or diagnoses, the system recorded and provided feedback. Based on scores from different modules and overall performance, the system conducted quantitative scoring and comprehensive analysis. The integration of AI enhanced the platform's capabilities by enabling real time adaptive learning. AI algorithms analyzed students' performance data to identify individual learning gaps, offering personalized feedback and tailored learning paths. Additionally, AI-driven virtual patient models dynamically adjusted their responses based on student inputs, simulating a wide range of TMD scenarios to improve diagnostic accuracy. The system also employed natural language processing to facilitate interactive dialogues, allowing students to practice history-taking with virtual patients, while machine learning models predicted potential diagnostic pitfalls and suggested corrective actions, further refining clinical thinking skills. Instructors can track learning duration, progress, and knowledge mastery in real time through interactive platform functions, enabling personalized teaching. The platform provided standardized diagnostic and treatment procedure videos and a knowledge point courseware library to support learning. The Research Process This experiment adopted a quasi-experimental research design, establishing a control group and an experimental group: 97 fourth-year undergraduate students formed the experimental group, which utilized a virtual simulation teaching model; the control group consisted of 81 fourth-year students from the same major, who followed a traditional teaching model. The study was approved by the Ethics Committee of Shandong University School of Stomatology (No.20251120). And this study was registered in the Chinese Clinical Trial Register under registration number ChiCTR2600117026 on January 19, 2026. The detailed research process, including the teaching procedures for both the experimental and control groups as well as the assessment methods, is illustrated in Fig. 2 . 1. Experimental Group Teaching Process (Virtual Simulation Teaching Model) : Students in the experimental group received a virtual simulation experimental teaching model, encompassing theoretical instruction, virtual simulation platform training, experimental training, and clinical practice training. The entire process was student-centered, emphasizing immersive interaction and personalized guidance to enhance knowledge application, operational skills, and comprehensive thinking. The specific process is as follows: 1.1 Theoretical Instruction Stage : In the classroom, teachers delivered lectures on TMD fundamentals based on the textbook, covering clinical manifestations, examination methods, diagnostic criteria, and treatment principles. This stage lasted approximately 30–40 minutes. 1.2 Virtual Simulation Experimental Teaching Stage : Students accessed the practice or assessment modules of the platform, simulating real clinical scenarios, including virtual clinic layouts, patient models, and dental equipment. Through 3D interactive operations (rotation, zooming, and translation), students learned TMD clinical examination steps, such as history-taking, visual inspection, mandibular movement examination, muscle palpation, joint palpation, intraoral occlusal examination, and imaging analysis. Students were required to complete module tasks, such as adjusting the sequence of examination steps, recording results, and providing preliminary diagnoses, with system feedback to correct errors. This stage lasted approximately 1.5 hours, aiming to develop independent operational skills and clinical thinking. 1.3 Experimental Training Stage : Students performed TMD examinations using a high-fidelity simulated head manikin and a joint vibration analysis simulator. Instructors provided step-by-step guidance throughout the complete clinical examination process, encompassing muscle and joint palpation, radiographic image interpretation, and diagnostic reasoning. This session seamlessly integrated virtual simulation technology with hands-on practice, lasting approximately one hour. 2. Control Group Teaching Process (Traditional Teaching Model) : Students in the control group received a conventional teaching model, including theoretical instruction, experimental training, and clinical practice training. The process focused on traditional lectures, combining theory and practice but lacking immersive virtual simulation training. The specific process is as follows: 2.1 Theoretical Instruction Stage : This stage was the same as that in the experimental group (see Section 1.1). It lasted approximately 30–40 minutes. 2.2 Experimental Training Stage : Students practiced TMD examinations using dedicated teaching manikins (e.g., typodonts mounted in craniofacial simulators). Faculty members provided real time guidance and demonstrations throughout the complete clinical examination sequence, which included muscle and temporomandibular joint palpation, radiographic image interpretation, and diagnostic formulation. This hands-on session emphasized instructor-led demonstration followed by supervised student replication and lasted approximately one hour. 3. Teaching Effectiveness Assessment : The assessment of teaching effectiveness adopted multidimensional indicators, including theoretical tests, operational skills evaluation, and questionnaire surveys, referencing a quasi-experimental design to ensure objectivity in intergroup comparisons. Theoretical examinations were scored anonymously using student ID numbers. For practical assessments, students wore surgical masks and caps, and were identified only by examination numbers to minimize assessor bias. The specific methods are as follows: 3.1 Theoretical Test : A post-class theoretical exam was conducted to assess mastery of TMD foundational knowledge. The test included multiple-choice questions, fill-in-the-blank questions, and short-answer questions, covering clinical examinations, diagnostic criteria, and treatment principles. Differences in test scores between the experimental and control groups were compared (using t-tests, with p < 0.05 considered significant). 3.2 Operational Skills Evaluation : During the experimental training and clinical practice stages, TMD examination operation time, accuracy, and report quality were assessed. A standardized scoring table was used, covering 5 key points such as history-taking, palpation, image interpretation, diagnosis and treatment plan formulation, with each item assigned a score. Differences between the two groups were compared. Additionally, teacher feedback was used to evaluate diagnostic accuracy and the rationality of treatment plans. 3.3 Questionnaire Survey : Post-class questionnaires were distributed to assess learning satisfaction and teaching efficiency. The survey covered aspects such as learning interest, operational confidence, improvement in clinical thinking, and platform usability (exclusive to the experimental group), using a Likert scale (1–5 points). Satisfaction levels between the two groups were compared (using t-tests). The experimental group additionally evaluated the immersion and future trend recognition of the virtual simulation platform. Questionnaires were distributed via the Questionnaire Star online platform ( https://www.wjx.cn ). The questionnaire developed for this study has been included in the supplementary materials. 3.4 Statistical Analysis : Data were entered into IBM SPSS 27.0 software and presented as mean ± standard deviation (SD). For continuous variables fitting a normal distribution (e.g., age, test scores, and Likert scale scores), independent samples t-tests were used; for non-normally distributed data, the non-parametric Mann-Whitney U rank sum test was applied; for categorical variables (e.g., gender), chi-square tests were used. The significance level was set at p < 0.05. Results The baseline characteristics of the participants, as shown in Table 1 , revealed no significant differences between the experimental group (n = 97) and the control group (n = 81) in terms of age (22.23 ± 0.75 vs. 22.09 ± 0.61, t = 1.37, p = 0.173) or sex distribution (40.2% male vs. 32.0% male, χ²=0.74, p = 0.391), ensuring comparability between the groups. In terms of theoretical knowledge acquisition, Table 2 demonstrates that the experimental group, which utilized the AI-enabled virtual simulation teaching model, scored significantly higher on the post-class theoretical tests compared to the control group receiving traditional teaching (84.6 ± 8.5 vs. 78.7 ± 9.8, t = 4.26, p < 0.0001). This indicates that the immersive and interactive elements of the virtual simulation platform enhanced students' retention and understanding of TMD-related concepts, such as clinical manifestations, diagnostic criteria, and treatment principles, aligning with findings from similar studies on virtual simulation in dental education where theoretical mastery improved markedly post-intervention. As shown in Table 3 , the experimental group significantly outperformed the control group in all five evaluated clinical skill domains (all p < 0.001). The mean scores for the experimental group versus the control group were as follows: history-taking (17.5 ± 1.6 vs. 15.6 ± 2.1), palpation (18.2 ± 1.3 vs. 16.3 ± 2.2), image interpretation (17.5 ± 1.8 vs. 15.6 ± 2.3), diagnosis (18.1 ± 1.2 vs. 16.1 ± 2.0), and treatment plan formulation (17.8 ± 1.7 vs. 16.2 ± 2.1). The total operational skills score was markedly higher in the experimental group than in the control group (89.1 ± 7.4 vs. 79.8 ± 9.2, t = 14.40, p < 0.001), representing an average improvement of 9.3 points (approximately 11.6%), exceeding the minimal clinically important difference (MCID) of 5–7 points reported in similar dental education studies. These results demonstrate that repeated practice with real time AI feedback and haptic simulation substantially enhanced students’ proficiency and standardization across the entire diagnostic and treatment planning process. Questionnaire results (Table 4 ) revealed significantly higher satisfaction in the experimental group across all measured domains (all p < 0.001). For theoretical learning, the experimental group reported an average score of 4.71 ± 0.42 compared to 4.21 ± 0.56 in the control group (mean difference 0.50, t = 6.58). In clinical thinking and operational skills, the experimental group scored 4.62 ± 0.46 versus 4.08 ± 0.56 in the control group (mean difference 0.54, t = 6.92). Overall satisfaction was also substantially higher in the experimental group (4.71 ± 0.41 vs. 4.19 ± 0.56, mean difference 0.52, t = 6.86). Notably, more than 95% of students in the experimental group rated learning interest, operational confidence, and willingness to recommend the platform at 4 or 5 points, with average scores consistently exceeding 4.58 across all sub-items. Open-ended feedback particularly praised the immediate error correction, personalized learning paths, and realistic haptic feedback, while several students suggested further expansion of case variety in future iterations. Table 1 The basic information of students Experimental Group(n = 97) Control Group(n = 81) t/χ²-value P -value* Age 22.23 ± 0.75 22.09 ± 0.61 t = 1.37 p = 0.173 Sex Male [n(%)] 39(40.2%) 26(32.0%) Female [n(%)] 58(59.7%) 55(67.9%) χ² = 0.74 p = 0.391 * Significant differences when p -value < 0.05 Table 2 Theoretical test scores Experimental Group(n = 97) Control Group(n = 81) t/χ²-value P -value* Theoretical Test Scores 84.6 ± 8.5 78.7 ± 9.8 t = 4.26 p < 0.0001 * Significant differences when p -value < 0.05 Table 3 Operational skills assessment results Evaluation Items Experimental Group(n = 97) Control Group(n = 81) t/χ²-value P -value* History-Taking 17.5 ± 1.6 15.6 ± 2.1 t = 6.92 p < 0.001 Palpation 18.2 ± 1.3 16.3 ± 2.2 t = 6.79 p < 0.001 Image Interpretation 17.5 ± 1.8 15.6 ± 2.3 t = 6.11 p < 0.001 Diagnosis 18.1 ± 1.2 16.1 ± 2.0 t = 8.34 p < 0.001 Treatment P lan Formulation 17.8 ± 1.7 16.2 ± 2.1 t = 5.45 p < 0.001 Total Score 89.1 ± 7.4 79.8 ± 9.2 t = 7.33 p < 0.001 * Significant differences when p -value < 0.05 Table 4 Learning effectiveness satisfaction survey results Experimental Group(n = 97) Control Group(n = 81) t/χ²-value P -value * Theoretical Learning Content Clarity 4.66 ± 0.48 4.27 ± 0.55 t = 4.83 p < 0.001 Knowledge Retention and Mastery 4.69 ± 0.46 4.16 ± 0.63 t = 6.06 p < 0.001 Learning Interest 4.78 ± 0.42 4.20 ± 0.65 t = 6.72 p < 0.001 Theoretical Learning Average Score 4.71 ± 0.42 4.21 ± 0.56 t = 6.58 p < 0.001 Clinical Thinking and Operational Skills Clinical Diagnostic Ability 4.64 ± 0.51 4.09 ± 0.60 t = 6.20 p < 0.001 Operational Standardization 4.64 ± 0.51 4.06 ± 0.67 t = 6.22 p < 0.001 Interactive Design 4.58 ± 0.55 4.06 ± 0.59 t = 5.81 p < 0.001 Clinical Thinking Ability 4.62 ± 0.53 4.09 ± 0.64 t = 5.83 p < 0.001 Clinical Skills Average Score 4.62 ± 0.46 4.08 ± 0.56 t = 6.92 p < 0.001 Overall Satisfaction Overall Learning Experience 4.66 ± 0.48 4.22 ± 0.60 t = 5.14 p < 0.001 Comparison with Traditional Teaching 4.72 ± 0.45 4.17 ± 0.58 t = 6.79 p < 0.001 Recommendation Willingness 4.76 ± 0.43 4.19 ± 0.59 t = 6.97 p < 0.001 Overall Satisfaction Average Score 4.71 ± 0.41 4.19 ± 0.56 t = 6.86 p < 0.001 * Significant differences when p -value < 0.05 Discussion The constraints of conventional pedagogical approaches, particularly the limited opportunities for practical application due to restricted case availability and ethical considerations, have been extensively substantiated in contemporary dental education. A 2024 investigation into preclinical dental surgical training revealed that traditional manikin-based methodologies yielded inferior performance metrics (mean score: 86.10 ± 6.21) compared to virtual modalities, underscoring deficiencies in feedback immediacy and learner engagement [ 18 ] . Correspondingly, within the broader medical education landscape, conventional methods frequently fail to facilitate iterative, risk-free practice, resulting in deficits in skill mastery and knowledge retention. This is corroborated by a narrative review advocating for immersive technologies to ameliorate these shortcomings [ 19 ] . Recently, the incorporation of AI-enabled virtual simulation in TMD education effectively mitigates these limitations by providing tailored, interactive learning environments that augment both theoretical comprehension and clinical proficiency. The findings of our present study are consonant with a recent retrospective analysis in dental education, wherein the digital virtual reality simulator cohort achieved statistically superior course outcomes (88.41 ± 4.75 vs. 86.10 ± 6.21, p < 0.05) compared to the traditional cohort, with enhancements attributed to real time feedback and high-fidelity simulations fostering improved clinical precision and self-efficacy [ 18 ] . In our experimental cohort, significantly higher theoretical examination scores (84.6 ± 8.5 vs 78.7 ± 9.8, p < 0.0001) and operational skill assessments (89.1 ± 7.4 vs. 79.8 ± 9.2, p < 0.001) align with these observations, particularly in domains such as history-taking and diagnostic formulation, where AI-driven adaptive learning pathways enabled targeted reinforcement of identified weaknesses. This is further corroborated by a recent study on virtual simulation experiments (VSE) in medical microbiology, which demonstrated enhanced knowledge retention (post-test score: 87.4 ± 4.4) and operational competencies (89.6 ± 5.2) in the VSE cohort, with an 18% improvement in task accuracy attributable to immediate AI-mediated feedback and immersive scenarios [ 20 ] . Additionally, within dental-specific contexts, a recent randomized controlled trial established that virtual reality simulators were comparably effective to traditional phantom heads for veneer preparation, with equivalent quality scores (e.g., 88.9 ± 3.6 for one simulator), yet offered superior user-perceived realism and haptic feedback, suggesting their utility in enhancing TMD-related palpation and imaging tasks [ 21 ] . Learner satisfaction and motivational engagement were markedly elevated in the AI-enabled virtual simulation cohort, as evidenced by higher scores across theoretical learning, clinical reasoning, and overall satisfaction domains (Table 4 ). These findings resonate with the aforementioned dental surgical study, where DVRS participants reported exceptional satisfaction (Cronbach’s Alpha = 0.952) regarding system usability, feedback clarity, and skill enhancement, with over 90% expressing enthusiasm for sustained utilization [ 18 ] . Similarly, a hybrid study in nursing education demonstrated that AI-enabled virtual reality simulation (AI-VRS) significantly enhanced perceived clinical preparedness and interprofessional competencies, despite no significant differences in knowledge acquisition, highlighting the motivational advantages of interactive AI components, such as conversational agents for history-taking practice [ 22 ] . Our questionnaire data, with scores exceeding 4.5 for realism and system operability, suggest that AI personalization not only heightened engagement but also aligned with constructivist learning principles by enabling learners to actively construct TMD diagnostic frameworks, consistent with the motivational effects (e.g., interest score: 4.0 ± 0.9) observed in the microbiology VSE study [ 20 ] . In conclusion, AI-enabled virtual simulation constituted a robust advancement in TMD education, substantiated by empirical evidence of enhanced learning outcomes and motivational engagement, thereby justifying its broader integration into dental curricula. Limitations Despite its strengths, this study has several limitations. The quasi-experimental design lacked randomization, risking selection bias [ 19 ] , and was conducted in only one cohort, limiting data volume and reproducibility. Additionally, minor AI interaction usability issues were noted by learners. Future studies should address these shortcomings by employing randomized controlled trials with multiple cohorts and longitudinal follow-up, while simultaneously refining AI interactivity through generative AI integration. Such improvements will substantially enhance causal inference, generalizability, and practical applicability of AI-VR in perioperative nursing education. Conclusion This project successfully constructed a comprehensive clinical thinking training system for TMD by deeply integrating AI and virtual simulation technology, providing an innovative and systematic solution for dental education. Guided by constructivist learning theory, the system realizes the connection from theory to practice through a three-module design of "basic knowledge learning - clinical examination practice - diagnosis and treatment plan formulation", providing students with a clinical learning environment close to reality. The evaluation of teaching practice effects shows that the system not only significantly improves students' learning interest, participation and clinical skills, but also effectively consolidates theoretical knowledge through personalized learning paths and real time feedback mechanisms, and enhances students' comprehensive ability in formulating TMD diagnosis and treatment plans. Declarations Acknowledgments Funding : This study was funded by: Shandong "111 Plan" Project for Undergraduate Education Reform in AI-empowered Key Fields (D2024002); Shandong University School-level Education and Teaching Reform Research Project (2023Y189); Cheeloo College of Medicine, Shandong University Characteristic Undergraduate Education and Teaching Research Project (qlyxjy-202338); Shandong University Graduate Education and Teaching Reform Research Project (XYJG2023091); Shandong University [Research · Curriculum Ideological and Political Education] (Fourth Phase) "Comprehensively Promoting the Construction of Chinese-style Modernization" Special Project (KCSZ23008); Shandong University 2025 Experimental Technology Research Project (sy20252403); Shandong First Medical University (Shandong Academy of Medical Sciences) Education and Teaching Research Topic (JXGGYJ-22221603); Shandong University 2024 Undergraduate Education and Teaching Reform and Research Project (2024Y191)；Shandong University Cheeloo Medicine Featured Undergraduate Education and Teaching Research Project (qlyxjy-202511) Conflict of interest The authors declare that they have no conflict of interest. Ethica l approval All procedures performed in this study involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. The study was approved by the Ethics Committee of Shandong University School of Stomatology. (No.20251120) Informed consent All participants provided written informed consent before recruitment. Author contributions All authors contributed to the study conception and design. The project was supervised by Shaohua Ge and Shengjun Sun. Material preparation, data collection and analysis were performed by Pei Zhang, He Wei and Yilin Zhang. Zixin Zhou assisted with preliminary data organization, Chunqin Wang supported literature checking, and Chi Zhang helped with figure and table proofreading. The first draft of the manuscript was written by Pei Zhang, and all authors approved the final manuscript. References Schiffman E, Ohrbach R, Truelove E, Look JO, Anderson G, Ceusters W, et al. Diagnostic criteria for temporomandibular disorders (DC/TMD) for clinical and research applications: recommendations of the International RDC/TMD Consortium Network and Orofacial Pain Special Interest Group. J Oral Facial Pain Headache. 2014;28:6–27. Zieliński G, Pająk-Zielińska B, Ginszt M. A meta-analysis of the global prevalence of temporomandibular disorders. J Clin Med. 2024;13:1365. Valesan LF, Da-Cas CD, Réus JC, Denardin AC, Garanhani RR, Bonotto D, et al. Prevalence of temporomandibular joint disorders: a systematic review and meta-analysis. Clin Oral Investig. 2021;25:441–53. De Leeuw R, Klasser GD, editors. Orofacial pain: guidelines for assessment, diagnosis, and management. 6th ed. Quintessence Publishing; 2023. Minervini G, Franco R, Marrapodi MM, Fiorillo L, Cervino G, Cicciù M. Prevalence of temporomandibular disorders in children and adolescents evaluated with Diagnostic Criteria for Temporomandibular Disorders: a systematic review with meta-analysis. J Oral Rehabil. 2023;50:522–30. Ronsivalle V, Marrapodi MM, Tirupathi S, Afnan L, Cicciù M, Minervini G. Prevalence of temporomandibular disorders in juvenile idiopathic arthritis evaluated with diagnostic criteria for temporomandibular disorders: A systematic review with meta-analysis. J Oral Rehabil. 2024;51(3):628–37. Bandiaky O, Lopez S, Hamon L, Clouet R, Soueidan A, Le Guehennec L. Impact of haptic simulators in preclinical dental education: A systematic review. J Dent Educ. 2024;88(3):366–79. Okeson JP. Management of temporomandibular disorders and occlusion. 8th ed. Elsevier; 2022. Koolivand H, Shooreshi MM, Safari-Faramani R, Borjali M, Heydari S, Salehi AR. Comparison of the effectiveness of virtual reality-based education and conventional teaching methods in dental education: a systematic review. BMC Med Educ. 2024;24:8. Mergen M, Graf N, Meyerheim M. Reviewing the current state of virtual reality integration in medical education - a scoping review. BMC Med Educ. 2024;24:788. Cardoso SA, Suyambu J, Iqbal J, Cortes Jaimes DC, Amin A, Sikto JT, et al. Exploring the role of simulation training in improving surgical skills among residents: a narrative review. Cureus. 2023;15:e44654. Elendu C, Amaechi DC, Okatta AU, Amaechi EC, Elendu TC, Ezeh CP, et al. The impact of simulation-based training in medical education: a review. Med (Baltim). 2024;103:e38813. Algarni YA, Saini RS, Vaddamanu SK, Alwadi M, Alqahtani A, Alabdulkader A, et al. The impact of virtual reality simulation on dental education: a systematic review of learning outcomes and student engagement. J Dent Educ. 2024;88:1549–62. Bandiaky O, Lopez S, Hamon L, Lejus-Bourdeau C, Cousin I, Serfaty R. Impact of haptic simulators in preclinical dental education: a systematic review. J Dent Educ. 2024;88:366–79. Daud A, Matoug-Elwerfelli M, Daas H, Alhadidi A, Gonzalez-Marrero Y, Shore E, et al. Enhancing learning experiences in pre-clinical restorative dentistry: the impact of virtual reality haptic simulators. BMC Med Educ. 2023;23:948. Pethani F. Artificial intelligence in dental education: opportunities and challenges of large language models and multimodal foundation models. JMIR Med Educ. 2024;10:e52346. Shetty S, Gali S, Augustine D, Sv S. Artificial intelligence systems in dental shade-matching: A systematic review. J Prosthodont. 2024;33(6):519–32. Hamama H, Harrison KY, Murbay S. Benefits of using virtual reality in cariology teaching. BMC Med Educ. 2024;24:1051. Thurzo A, Strunga M, Urban R, Surovková J, Líška M. Impact of artificial intelligence on dental education: a review and guide for curriculum update. Educ Sci (Basel). 2023;13:150. Fu J, Lao Z, Gao L, Zhang Y, Chen X, Li H, et al. The application of virtual simulation technology in scaling and root planing teaching. BMC Oral Health. 2024;24:86. Philip N, Ali K, Duggal M, Murtadha L, Pring A, Nazzal H. Effectiveness and student perceptions of haptic virtual reality simulation training as an instructional tool in pre-clinical paediatric dentistry: a pilot pedagogical study. Int J Environ Res Public Health. 2023;20:4226. Kavadella A, Dias da Silva MA, Kaklamanos EG, Stangvaltaite-Mouhat L, Panagiotou S, Giannakopoulos N, et al. Evaluation of ChatGPT’s real-life implementation in undergraduate dental education: mixed methods study. JMIR Med Educ. 2024;10:e51344. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8462289","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":596243430,"identity":"248327ee-4658-497e-a532-d314553884e9","order_by":0,"name":"Pei Zhang","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Pei","middleName":"","lastName":"Zhang","suffix":""},{"id":596243431,"identity":"85976d8f-931e-47b5-bae4-a217e3d19a63","order_by":1,"name":"Wei He","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"He","suffix":""},{"id":596243432,"identity":"29a76522-745c-4dfc-92b9-8e733d772891","order_by":2,"name":"Yilin Zhang","email":"","orcid":"","institution":"Shandong Provincial Hospital Affiliated to Shandong First Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yilin","middleName":"","lastName":"Zhang","suffix":""},{"id":596243433,"identity":"83cd9609-4f18-49da-8229-c368fcd3e12f","order_by":3,"name":"Zixin Zhou","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Zixin","middleName":"","lastName":"Zhou","suffix":""},{"id":596243434,"identity":"d85ed976-d8a1-461c-ac20-6010d266fa2f","order_by":4,"name":"Chunqin Wang","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Chunqin","middleName":"","lastName":"Wang","suffix":""},{"id":596243437,"identity":"78eb2250-da5c-4ef1-ace4-2c178f9a1607","order_by":5,"name":"Chi Zhang","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Chi","middleName":"","lastName":"Zhang","suffix":""},{"id":596243440,"identity":"f2e802e6-59dc-4aad-9881-c40bf821c53f","order_by":6,"name":"Shaohua Ge","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Shaohua","middleName":"","lastName":"Ge","suffix":""},{"id":596243441,"identity":"e112ebdc-3bfe-4e16-8e31-93292d9d164d","order_by":7,"name":"Shengjun Sun","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7ElEQVRIiWNgGAWjYJACZhDB2MDA+ICBDcRMIF4LswFpWoCATYIoLfIzcg9/Lqi4Y9c8I/dY5Y+ywwz87DkGDD934NZicCMvTXrGmWfJjTPy0m7znDvMINnzxoCx9wweLRI5Zsy8bYeTGWfkmN1mbDsMNCTHgJmxDZ/Dcow/8/6DaCn8CdRiT0gLA1CBNG/DYTuQFgZekC0SBLQYnHljJs1z7HACY88bY2mec+k8EmeeFRzsxeewdqDDeGoO2xu25xh+/FFmLcffnrzxwU98DoOCxI0NEAYPiDhAWAMDg708MapGwSgYBaNgZAIAyJhPpN7EIw8AAAAASUVORK5CYII=","orcid":"","institution":"Shandong University","correspondingAuthor":true,"prefix":"","firstName":"Shengjun","middleName":"","lastName":"Sun","suffix":""}],"badges":[],"createdAt":"2025-12-27 16:38:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8462289/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8462289/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104405802,"identity":"60c90b7d-e00d-4c22-a551-acda5806a8d7","added_by":"auto","created_at":"2026-03-11 12:23:52","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":910370,"visible":true,"origin":"","legend":"\u003cp\u003eComprehensive virtual simulation system: \u003cstrong\u003eA.\u003c/strong\u003e Basic knowledge learning phase; \u003cstrong\u003eB.\u003c/strong\u003e Simulates the consultation process for TMD in a clinical environment; \u003cstrong\u003eC.\u003c/strong\u003e Assessment process during learning; \u003cstrong\u003eD.\u003c/strong\u003e System prompts provided after operational errors; \u003cstrong\u003eE.\u003c/strong\u003e Final assessment phase; \u003cstrong\u003eF.\u003c/strong\u003e Joint vibration simulation device.\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8462289/v1/a32f97a3ad1f5aec8908d87d.png"},{"id":104345422,"identity":"94ee0cb0-202f-4028-87da-3995b316e1d8","added_by":"auto","created_at":"2026-03-10 17:38:03","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":347566,"visible":true,"origin":"","legend":"\u003cp\u003eThe research process\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8462289/v1/08178e12efee9246a48be80d.png"},{"id":109166078,"identity":"90ad1fd8-622c-48cc-9d52-59d21856df37","added_by":"auto","created_at":"2026-05-13 08:16:37","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1524057,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8462289/v1/91fd87db-3cd8-403b-8bd5-d020f1090bcd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"The Impact of Artificial Intelligence-Enabled Virtual Simulation on Clinical Reasoning in Dental Students in Managing Temporomandibular Disorders","fulltext":[{"header":"Background","content":"\u003cp\u003eTemporomandibular disorders (TMD) refer to a group of conditions affecting the temporomandibular joint and/or the masticatory muscle system, leading to symptoms such as joint pain, clicking, and limited mouth opening \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e1\u003c/span\u003e]\u003c/sup\u003e. With a relatively high prevalence, epidemiological surveys report a global TMD incidence of approximately 29.5%–34% \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e3\u003c/span\u003e]\u003c/sup\u003e. If left untreated, TMD can progress to joint locking, restricted mouth opening \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e4\u003c/span\u003e]\u003c/sup\u003e, and in severe cases, complete inability to open the mouth. When TMD occurs in children or adolescents, it can lead to developmental abnormalities in the lower jaw, resulting in facial deformities that cause significant physical and psychological distress, severely impairing the patient's quality of life \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e5\u003c/span\u003e]\u003c/sup\u003e. As global health awareness rises, the demand for TMD diagnosis and treatment is increasing, placing higher requirements on dental education \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e6\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eTraditional TMD teaching primarily relies on classroom theoretical lectures and clinical practice \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e7\u003c/span\u003e]\u003c/sup\u003e. However, the clinical diagnosis and classification of TMD are quite complex, which requires comprehensive consideration of factors such as patient history, clinical manifestations, imaging examinations, and laboratory tests \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e8\u003c/span\u003e]\u003c/sup\u003e. Static teaching resources alone are insufficient to cultivate students' comprehensive clinical thinking abilities \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e9\u003c/span\u003e]\u003c/sup\u003e. Moreover, clinical practice is limited by the number of cases, the experience of supervising teachers, and ethical constraints, making it difficult to provide adequate hands-on opportunities for every student or for teachers to guide multiple students simultaneously in analyzing complex cases \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e10\u003c/span\u003e]\u003c/sup\u003e. This teaching model often results in graduates lacking sufficient clinical operational skills, directly affecting their career development \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e11\u003c/span\u003e]\u003c/sup\u003e. Exploring new teaching methods has become an urgent issue to address \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e12\u003c/span\u003e]\u003c/sup\u003e. The introduction of virtual simulation teaching can effectively resolve this problem, as virtual simulation technology has irreplaceable advantages in enhancing teaching effectiveness, enriching classroom formats, and enabling the sharing of high-quality experimental teaching resources, making it highly suitable for dental education \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e14\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eIn recent years, artificial intelligence (AI) technology has been widely applied in the education field, offering advantages such as enabling personalized learning, enhancing learning interactivity, and improving teaching efficiency \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e16\u003c/span\u003e]\u003c/sup\u003e. Artificial intelligence has shown promising applications not only in diagnostic and educational contexts but also in other dental procedures, such as shade-matching \u003csup\u003e[\u003cspan class=\"CitationRef\"\u003e17\u003c/span\u003e]\u003c/sup\u003e. In this project, AI technology not only provides students with real time question-answering services but also conducts systematic analysis of their learning outcomes, identifying areas of knowledge deficiency, and prompting targeted repetitive practice to improve mastery of the content. Additionally, AI can generate CT and MRI images as required for assessments, expanding the question bank, reducing the use of clinical data, and avoiding patient information leakage.\u003c/p\u003e \u003cp\u003eBased on these foundations, this study developed an AI-based TMD virtual simulation teaching system, integrating software and hardware design to build a \"virtual-real integration\" comprehensive clinical thinking training platform. By evaluating students' mastery of basic knowledge and diagnosis, the differences between various teaching methods were compared. Through this approach, the study aims to identify the necessity of introducing virtual simulation teaching projects in TMD training, improve teaching protocols, and measure the effectiveness of such education in clinical practice. The comprehensive virtual simulation system is shown in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \n\n \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"Methods","content":"\u003ch3\u003eFeatures of the Comprehensive Virtual Simulation System\u003c/h3\u003e\n\u003cp\u003eThis experimental platform integrated virtual reality, multimedia, human-computer interaction, force feedback hardware, and network communication technologies. It comprised three core modules: \u0026quot;Basic Knowledge Learning,\u0026quot; \u0026quot;Clinical Examination Practice,\u0026quot; and \u0026quot;Diagnosis and Treatment Planning,\u0026quot; establishing a complete clinical diagnostic and therapeutic pathway of \u0026quot;examination-diagnosis-treatment\u0026quot; for TMD, a prevalent clinical condition. Learners engaged in role-playing to perform online clinical examinations, imaging assessments, diagnoses, and treatment plan formulations.\u003c/p\u003e\n\u003cp\u003eThe virtual environment, including clinic layout, clinical materials, and equipment, was modeled after the actual setting of the Temporomandibular Joint and Occlusion Clinic at Shandong University School of Stomatology. The platform was equipped with a joint vibration simulation device (Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e-F) developed by the course team, providing near-realistic tactile feedback for palpation examinations to enhance the learning experience.\u003c/p\u003e\n\u003cp\u003eIn the Basic Knowledge Learning module, users followed prompts to complete the full process of TMD patient consultation, examination, diagnosis, and treatment planning in a simulated clinical environment.\u003c/p\u003e\n\u003cp\u003eDuring learning, the platform evaluated performance based on key clinical points through multiple-choice questions and operational tasks, covering 4 aspects including consultation, examination techniques, diagnostic accuracy, and treatment plan rationality, with assigned scores. It supported repeated practice and retrospective analysis of human-computer interactions. If errors occurred in operations or diagnoses, the system recorded and provided feedback. Based on scores from different modules and overall performance, the system conducted quantitative scoring and comprehensive analysis.\u003c/p\u003e\n\u003cp\u003eThe integration of AI enhanced the platform\u0026apos;s capabilities by enabling real time adaptive learning. AI algorithms analyzed students\u0026apos; performance data to identify individual learning gaps, offering personalized feedback and tailored learning paths. Additionally, AI-driven virtual patient models dynamically adjusted their responses based on student inputs, simulating a wide range of TMD scenarios to improve diagnostic accuracy. The system also employed natural language processing to facilitate interactive dialogues, allowing students to practice history-taking with virtual patients, while machine learning models predicted potential diagnostic pitfalls and suggested corrective actions, further refining clinical thinking skills.\u003c/p\u003e\n\u003cp\u003eInstructors can track learning duration, progress, and knowledge mastery in real time through interactive platform functions, enabling personalized teaching. The platform provided standardized diagnostic and treatment procedure videos and a knowledge point courseware library to support learning.\u003c/p\u003e\n\u003ch2\u003eThe Research Process\u003c/h2\u003e\n\u003cp\u003eThis experiment adopted a quasi-experimental research design, establishing a control group and an experimental group: 97 fourth-year undergraduate students formed the experimental group, which utilized a virtual simulation teaching model; the control group consisted of 81 fourth-year students from the same major, who followed a traditional teaching model. The study was approved by the Ethics Committee of Shandong University School of Stomatology (No.20251120). And this study was registered in the Chinese Clinical Trial Register under registration number ChiCTR2600117026 on January 19, 2026.\u003c/p\u003e\n\u003cp\u003eThe detailed research process, including the teaching procedures for both the experimental and control groups as well as the assessment methods, is illustrated in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e1. Experimental Group Teaching Process (Virtual Simulation Teaching Model)\u003c/strong\u003e:\u003c/p\u003e\n\u003cp\u003eStudents in the experimental group received a virtual simulation experimental teaching model, encompassing theoretical instruction, virtual simulation platform training, experimental training, and clinical practice training. The entire process was student-centered, emphasizing immersive interaction and personalized guidance to enhance knowledge application, operational skills, and comprehensive thinking. The specific process is as follows:\u003c/p\u003e\n\u003cp\u003e\u003cspan\u003e\u003cstrong\u003e1.1 Theoretical Instruction Stage\u003c/strong\u003e: In the classroom, teachers delivered lectures on TMD fundamentals based on the textbook, covering clinical manifestations, examination methods, diagnostic criteria, and treatment principles. This stage lasted approximately 30\u0026ndash;40 minutes.\u003cbr\u003e\u003c/span\u003e\u003cspan\u003e\u003cstrong\u003e1.2 Virtual Simulation Experimental Teaching Stage\u003c/strong\u003e: Students accessed the practice or assessment modules of the platform, simulating real clinical scenarios, including virtual clinic layouts, patient models, and dental equipment. Through 3D interactive operations (rotation, zooming, and translation), students learned TMD clinical examination steps, such as history-taking, visual inspection, mandibular movement examination, muscle palpation, joint palpation, intraoral occlusal examination, and imaging analysis. Students were required to complete module tasks, such as adjusting the sequence of examination steps, recording results, and providing preliminary diagnoses, with system feedback to correct errors. This stage lasted approximately 1.5 hours, aiming to develop independent operational skills and clinical thinking.\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cspan\u003e\u003cstrong\u003e1.3 Experimental Training Stage\u003c/strong\u003e: Students performed TMD examinations using a high-fidelity simulated head manikin and a joint vibration analysis simulator. Instructors provided step-by-step guidance throughout the complete clinical examination process, encompassing muscle and joint palpation, radiographic image interpretation, and diagnostic reasoning. This session seamlessly integrated virtual simulation technology with hands-on practice, lasting approximately one hour.\u003cbr\u003e\u003c/span\u003e\u003cspan\u003e\u003cstrong\u003e2. Control Group Teaching Process (Traditional Teaching Model)\u003c/strong\u003e:\u003cbr\u003e\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003eStudents in the control group received a conventional teaching model, including theoretical instruction, experimental training, and clinical practice training. The process focused on traditional lectures, combining theory and practice but lacking immersive virtual simulation training. The specific process is as follows:\u003c/p\u003e\n\u003cp\u003e\u003cspan\u003e\u003cstrong\u003e2.1 Theoretical Instruction Stage\u003c/strong\u003e: This stage was the same as that in the experimental group (see Section 1.1). It lasted approximately 30\u0026ndash;40 minutes.\u003cbr\u003e\u003c/span\u003e\u003cspan\u003e\u003cstrong\u003e2.2 Experimental Training Stage\u003c/strong\u003e: Students practiced TMD examinations using dedicated teaching manikins (e.g., typodonts mounted in craniofacial simulators). Faculty members provided real time guidance and demonstrations throughout the complete clinical examination sequence, which included muscle and temporomandibular joint palpation, radiographic image interpretation, and diagnostic formulation. This hands-on session emphasized instructor-led demonstration followed by supervised student replication and lasted approximately one hour.\u003cbr\u003e\u003c/span\u003e\u003cspan\u003e\u003cstrong\u003e3. Teaching Effectiveness Assessment\u003c/strong\u003e:\u003cbr\u003e\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003eThe assessment of teaching effectiveness adopted multidimensional indicators, including theoretical tests, operational skills evaluation, and questionnaire surveys, referencing a quasi-experimental design to ensure objectivity in intergroup comparisons. Theoretical examinations were scored anonymously using student ID numbers. For practical assessments, students wore surgical masks and caps, and were identified only by examination numbers to minimize assessor bias. The specific methods are as follows:\u003c/p\u003e\n\u003cp\u003e\u003cspan\u003e\u003cstrong\u003e3.1 Theoretical Test\u003c/strong\u003e: A post-class theoretical exam was conducted to assess mastery of TMD foundational knowledge. The test included multiple-choice questions, fill-in-the-blank questions, and short-answer questions, covering clinical examinations, diagnostic criteria, and treatment principles. Differences in test scores between the experimental and control groups were compared (using t-tests, with \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05 considered significant).\u003cbr\u003e\u003c/span\u003e\u003cspan\u003e\u003cstrong\u003e3.2 Operational Skills Evaluation\u003c/strong\u003e: During the experimental training and clinical practice stages, TMD examination operation time, accuracy, and report quality were assessed. A standardized scoring table was used, covering 5 key points such as history-taking, palpation, image interpretation, diagnosis and treatment plan formulation, with each item assigned a score. Differences between the two groups were compared. Additionally, teacher feedback was used to evaluate diagnostic accuracy and the rationality of treatment plans.\u003cbr\u003e\u003c/span\u003e\u003cspan\u003e\u003cstrong\u003e3.3 Questionnaire Survey\u003c/strong\u003e: Post-class questionnaires were distributed to assess learning satisfaction and teaching efficiency. The survey covered aspects such as learning interest, operational confidence, improvement in clinical thinking, and platform usability (exclusive to the experimental group), using a Likert scale (1\u0026ndash;5 points). Satisfaction levels between the two groups were compared (using t-tests). The experimental group additionally evaluated the immersion and future trend recognition of the virtual simulation platform. Questionnaires were distributed \u003cem\u003evia\u003c/em\u003e the Questionnaire Star online platform (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.wjx.cn\u003c/span\u003e\u003c/span\u003e). The questionnaire developed for this study has been included in the supplementary materials.\u003cbr\u003e\u003c/span\u003e\u003cspan\u003e\u003cstrong\u003e3.4 Statistical Analysis\u003c/strong\u003e: Data were entered into IBM SPSS 27.0 software and presented as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation (SD). For continuous variables fitting a normal distribution (e.g., age, test scores, and Likert scale scores), independent samples t-tests were used; for non-normally distributed data, the non-parametric Mann-Whitney U rank sum test was applied; for categorical variables (e.g., gender), chi-square tests were used. The significance level was set at \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05.\u003cbr\u003e\u003c/span\u003e\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003eThe baseline characteristics of the participants, as shown in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, revealed no significant differences between the experimental group (n\u0026thinsp;=\u0026thinsp;97) and the control group (n\u0026thinsp;=\u0026thinsp;81) in terms of age (22.23\u0026thinsp;\u0026plusmn;\u0026thinsp;0.75 vs. 22.09\u0026thinsp;\u0026plusmn;\u0026thinsp;0.61, t\u0026thinsp;=\u0026thinsp;1.37, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.173) or sex distribution (40.2% male vs. 32.0% male, χ\u0026sup2;=0.74, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.391), ensuring comparability between the groups.\u003c/p\u003e \u003cp\u003eIn terms of theoretical knowledge acquisition, Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e demonstrates that the experimental group, which utilized the AI-enabled virtual simulation teaching model, scored significantly higher on the post-class theoretical tests compared to the control group receiving traditional teaching (84.6\u0026thinsp;\u0026plusmn;\u0026thinsp;8.5 vs. 78.7\u0026thinsp;\u0026plusmn;\u0026thinsp;9.8, t\u0026thinsp;=\u0026thinsp;4.26, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.0001). This indicates that the immersive and interactive elements of the virtual simulation platform enhanced students' retention and understanding of TMD-related concepts, such as clinical manifestations, diagnostic criteria, and treatment principles, aligning with findings from similar studies on virtual simulation in dental education where theoretical mastery improved markedly post-intervention.\u003c/p\u003e \u003cp\u003eAs shown in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, the experimental group significantly outperformed the control group in all five evaluated clinical skill domains (all \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). The mean scores for the experimental group versus the control group were as follows: history-taking (17.5\u0026thinsp;\u0026plusmn;\u0026thinsp;1.6 vs. 15.6\u0026thinsp;\u0026plusmn;\u0026thinsp;2.1), palpation (18.2\u0026thinsp;\u0026plusmn;\u0026thinsp;1.3 vs. 16.3\u0026thinsp;\u0026plusmn;\u0026thinsp;2.2), image interpretation (17.5\u0026thinsp;\u0026plusmn;\u0026thinsp;1.8 vs. 15.6\u0026thinsp;\u0026plusmn;\u0026thinsp;2.3), diagnosis (18.1\u0026thinsp;\u0026plusmn;\u0026thinsp;1.2 vs. 16.1\u0026thinsp;\u0026plusmn;\u0026thinsp;2.0), and treatment plan formulation (17.8\u0026thinsp;\u0026plusmn;\u0026thinsp;1.7 vs. 16.2\u0026thinsp;\u0026plusmn;\u0026thinsp;2.1). The total operational skills score was markedly higher in the experimental group than in the control group (89.1\u0026thinsp;\u0026plusmn;\u0026thinsp;7.4 vs. 79.8\u0026thinsp;\u0026plusmn;\u0026thinsp;9.2, t\u0026thinsp;=\u0026thinsp;14.40, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001), representing an average improvement of 9.3 points (approximately 11.6%), exceeding the minimal clinically important difference (MCID) of 5\u0026ndash;7 points reported in similar dental education studies. These results demonstrate that repeated practice with real time AI feedback and haptic simulation substantially enhanced students\u0026rsquo; proficiency and standardization across the entire diagnostic and treatment planning process.\u003c/p\u003e \u003cp\u003eQuestionnaire results (Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e) revealed significantly higher satisfaction in the experimental group across all measured domains (all \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001). For theoretical learning, the experimental group reported an average score of 4.71\u0026thinsp;\u0026plusmn;\u0026thinsp;0.42 compared to 4.21\u0026thinsp;\u0026plusmn;\u0026thinsp;0.56 in the control group (mean difference 0.50, t\u0026thinsp;=\u0026thinsp;6.58). In clinical thinking and operational skills, the experimental group scored 4.62\u0026thinsp;\u0026plusmn;\u0026thinsp;0.46 versus 4.08\u0026thinsp;\u0026plusmn;\u0026thinsp;0.56 in the control group (mean difference 0.54, t\u0026thinsp;=\u0026thinsp;6.92). Overall satisfaction was also substantially higher in the experimental group (4.71\u0026thinsp;\u0026plusmn;\u0026thinsp;0.41 vs. 4.19\u0026thinsp;\u0026plusmn;\u0026thinsp;0.56, mean difference 0.52, t\u0026thinsp;=\u0026thinsp;6.86). Notably, more than 95% of students in the experimental group rated learning interest, operational confidence, and willingness to recommend the platform at 4 or 5 points, with average scores consistently exceeding 4.58 across all sub-items. Open-ended feedback particularly praised the immediate error correction, personalized learning paths, and realistic haptic feedback, while several students suggested further expansion of case variety in future iterations.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eThe basic information of students\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eExperimental Group(n\u0026thinsp;=\u0026thinsp;97)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eControl Group(n\u0026thinsp;=\u0026thinsp;81)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003et/χ\u0026sup2;-value\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e-value*\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e22.23\u0026thinsp;\u0026plusmn;\u0026thinsp;0.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e22.09\u0026thinsp;\u0026plusmn;\u0026thinsp;0.61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;1.37\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.173\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSex\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMale [n(%)]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e39(40.2%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e26(32.0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFemale [n(%)]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e58(59.7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e55(67.9%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eχ\u0026sup2; = 0.74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.391\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"5\"\u003e* Significant differences when \u003cem\u003ep\u003c/em\u003e-value\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eTheoretical test scores\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eExperimental Group(n\u0026thinsp;=\u0026thinsp;97)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eControl Group(n\u0026thinsp;=\u0026thinsp;81)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003et/χ\u0026sup2;-value\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e-value*\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTheoretical Test Scores\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e84.6\u0026thinsp;\u0026plusmn;\u0026thinsp;8.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e78.7\u0026thinsp;\u0026plusmn;\u0026thinsp;9.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;4.26\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.0001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"5\"\u003e* Significant differences when \u003cem\u003ep\u003c/em\u003e-value\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eOperational skills assessment results\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEvaluation Items\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eExperimental Group(n\u0026thinsp;=\u0026thinsp;97)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eControl Group(n\u0026thinsp;=\u0026thinsp;81)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003et/χ\u0026sup2;-value\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e-value*\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHistory-Taking\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e17.5\u0026thinsp;\u0026plusmn;\u0026thinsp;1.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e15.6\u0026thinsp;\u0026plusmn;\u0026thinsp;2.1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;6.92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePalpation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e18.2\u0026thinsp;\u0026plusmn;\u0026thinsp;1.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e16.3\u0026thinsp;\u0026plusmn;\u0026thinsp;2.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;6.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImage Interpretation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e17.5\u0026thinsp;\u0026plusmn;\u0026thinsp;1.8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e15.6\u0026thinsp;\u0026plusmn;\u0026thinsp;2.3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;6.11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDiagnosis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e18.1\u0026thinsp;\u0026plusmn;\u0026thinsp;1.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e16.1\u0026thinsp;\u0026plusmn;\u0026thinsp;2.0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;8.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTreatment \u003cem\u003eP\u003c/em\u003elan Formulation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e17.8\u0026thinsp;\u0026plusmn;\u0026thinsp;1.7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e16.2\u0026thinsp;\u0026plusmn;\u0026thinsp;2.1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;5.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal Score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e89.1\u0026thinsp;\u0026plusmn;\u0026thinsp;7.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e79.8\u0026thinsp;\u0026plusmn;\u0026thinsp;9.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;7.33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"5\"\u003e* Significant differences when \u003cem\u003ep\u003c/em\u003e-value\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eLearning effectiveness satisfaction survey results\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eExperimental Group(n\u0026thinsp;=\u0026thinsp;97)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eControl Group(n\u0026thinsp;=\u0026thinsp;81)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003et/χ\u0026sup2;-value\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003eP\u003c/em\u003e-value\u003csup\u003e*\u003c/sup\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTheoretical Learning\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eContent Clarity\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.66\u0026thinsp;\u0026plusmn;\u0026thinsp;0.48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.27\u0026thinsp;\u0026plusmn;\u0026thinsp;0.55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;4.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eKnowledge Retention and Mastery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.69\u0026thinsp;\u0026plusmn;\u0026thinsp;0.46\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.16\u0026thinsp;\u0026plusmn;\u0026thinsp;0.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;6.06\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLearning Interest\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.78\u0026thinsp;\u0026plusmn;\u0026thinsp;0.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.20\u0026thinsp;\u0026plusmn;\u0026thinsp;0.65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;6.72\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTheoretical Learning Average Score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.71\u0026thinsp;\u0026plusmn;\u0026thinsp;0.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.21\u0026thinsp;\u0026plusmn;\u0026thinsp;0.56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;6.58\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eClinical Thinking and Operational Skills\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClinical Diagnostic Ability\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.64\u0026thinsp;\u0026plusmn;\u0026thinsp;0.51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.09\u0026thinsp;\u0026plusmn;\u0026thinsp;0.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;6.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOperational Standardization\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.64\u0026thinsp;\u0026plusmn;\u0026thinsp;0.51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.06\u0026thinsp;\u0026plusmn;\u0026thinsp;0.67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;6.22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInteractive Design\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.58\u0026thinsp;\u0026plusmn;\u0026thinsp;0.55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.06\u0026thinsp;\u0026plusmn;\u0026thinsp;0.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;5.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClinical Thinking Ability\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.62\u0026thinsp;\u0026plusmn;\u0026thinsp;0.53\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.09\u0026thinsp;\u0026plusmn;\u0026thinsp;0.64\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;5.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClinical Skills Average Score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.62\u0026thinsp;\u0026plusmn;\u0026thinsp;0.46\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.08\u0026thinsp;\u0026plusmn;\u0026thinsp;0.56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;6.92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eOverall Satisfaction\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOverall Learning Experience\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.66\u0026thinsp;\u0026plusmn;\u0026thinsp;0.48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.22\u0026thinsp;\u0026plusmn;\u0026thinsp;0.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;5.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eComparison with Traditional Teaching\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.72\u0026thinsp;\u0026plusmn;\u0026thinsp;0.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.17\u0026thinsp;\u0026plusmn;\u0026thinsp;0.58\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;6.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRecommendation Willingness\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.76\u0026thinsp;\u0026plusmn;\u0026thinsp;0.43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.19\u0026thinsp;\u0026plusmn;\u0026thinsp;0.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;6.97\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOverall Satisfaction Average Score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e \u003cp\u003e4.71\u0026thinsp;\u0026plusmn;\u0026thinsp;0.41\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e \u003cp\u003e4.19\u0026thinsp;\u0026plusmn;\u0026thinsp;0.56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003et\u0026thinsp;=\u0026thinsp;6.86\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"5\"\u003e* Significant differences when \u003cem\u003ep\u003c/em\u003e-value\u0026thinsp;\u0026lt;\u0026thinsp;0.05\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eThe constraints of conventional pedagogical approaches, particularly the limited opportunities for practical application due to restricted case availability and ethical considerations, have been extensively substantiated in contemporary dental education. A 2024 investigation into preclinical dental surgical training revealed that traditional manikin-based methodologies yielded inferior performance metrics (mean score: 86.10\u0026thinsp;\u0026plusmn;\u0026thinsp;6.21) compared to virtual modalities, underscoring deficiencies in feedback immediacy and learner engagement \u003csup\u003e[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]\u003c/sup\u003e. Correspondingly, within the broader medical education landscape, conventional methods frequently fail to facilitate iterative, risk-free practice, resulting in deficits in skill mastery and knowledge retention. This is corroborated by a narrative review advocating for immersive technologies to ameliorate these shortcomings \u003csup\u003e[\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eRecently, the incorporation of AI-enabled virtual simulation in TMD education effectively mitigates these limitations by providing tailored, interactive learning environments that augment both theoretical comprehension and clinical proficiency. The findings of our present study are consonant with a recent retrospective analysis in dental education, wherein the digital virtual reality simulator cohort achieved statistically superior course outcomes (88.41\u0026thinsp;\u0026plusmn;\u0026thinsp;4.75 vs. 86.10\u0026thinsp;\u0026plusmn;\u0026thinsp;6.21, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05) compared to the traditional cohort, with enhancements attributed to real time feedback and high-fidelity simulations fostering improved clinical precision and self-efficacy \u003csup\u003e[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]\u003c/sup\u003e. In our experimental cohort, significantly higher theoretical examination scores (84.6\u0026thinsp;\u0026plusmn;\u0026thinsp;8.5 \u003cem\u003evs\u003c/em\u003e 78.7\u0026thinsp;\u0026plusmn;\u0026thinsp;9.8, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.0001) and operational skill assessments (89.1\u0026thinsp;\u0026plusmn;\u0026thinsp;7.4 vs. 79.8\u0026thinsp;\u0026plusmn;\u0026thinsp;9.2, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001) align with these observations, particularly in domains such as history-taking and diagnostic formulation, where AI-driven adaptive learning pathways enabled targeted reinforcement of identified weaknesses. This is further corroborated by a recent study on virtual simulation experiments (VSE) in medical microbiology, which demonstrated enhanced knowledge retention (post-test score: 87.4\u0026thinsp;\u0026plusmn;\u0026thinsp;4.4) and operational competencies (89.6\u0026thinsp;\u0026plusmn;\u0026thinsp;5.2) in the VSE cohort, with an 18% improvement in task accuracy attributable to immediate AI-mediated feedback and immersive scenarios \u003csup\u003e[\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]\u003c/sup\u003e. Additionally, within dental-specific contexts, a recent randomized controlled trial established that virtual reality simulators were comparably effective to traditional phantom heads for veneer preparation, with equivalent quality scores (e.g., 88.9\u0026thinsp;\u0026plusmn;\u0026thinsp;3.6 for one simulator), yet offered superior user-perceived realism and haptic feedback, suggesting their utility in enhancing TMD-related palpation and imaging tasks \u003csup\u003e[\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eLearner satisfaction and motivational engagement were markedly elevated in the AI-enabled virtual simulation cohort, as evidenced by higher scores across theoretical learning, clinical reasoning, and overall satisfaction domains (Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). These findings resonate with the aforementioned dental surgical study, where DVRS participants reported exceptional satisfaction (Cronbach\u0026rsquo;s Alpha\u0026thinsp;=\u0026thinsp;0.952) regarding system usability, feedback clarity, and skill enhancement, with over 90% expressing enthusiasm for sustained utilization \u003csup\u003e[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]\u003c/sup\u003e. Similarly, a hybrid study in nursing education demonstrated that AI-enabled virtual reality simulation (AI-VRS) significantly enhanced perceived clinical preparedness and interprofessional competencies, despite no significant differences in knowledge acquisition, highlighting the motivational advantages of interactive AI components, such as conversational agents for history-taking practice \u003csup\u003e[\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]\u003c/sup\u003e. Our questionnaire data, with scores exceeding 4.5 for realism and system operability, suggest that AI personalization not only heightened engagement but also aligned with constructivist learning principles by enabling learners to actively construct TMD diagnostic frameworks, consistent with the motivational effects (e.g., interest score: 4.0\u0026thinsp;\u0026plusmn;\u0026thinsp;0.9) observed in the microbiology VSE study \u003csup\u003e[\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eIn conclusion, AI-enabled virtual simulation constituted a robust advancement in TMD education, substantiated by empirical evidence of enhanced learning outcomes and motivational engagement, thereby justifying its broader integration into dental curricula.\u003c/p\u003e"},{"header":"Limitations","content":"\u003cp\u003eDespite its strengths, this study has several limitations. The quasi-experimental design lacked randomization, risking selection bias \u003csup\u003e[\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]\u003c/sup\u003e, and was conducted in only one cohort, limiting data volume and reproducibility. Additionally, minor AI interaction usability issues were noted by learners. Future studies should address these shortcomings by employing randomized controlled trials with multiple cohorts and longitudinal follow-up, while simultaneously refining AI interactivity through generative AI integration. Such improvements will substantially enhance causal inference, generalizability, and practical applicability of AI-VR in perioperative nursing education.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThis project successfully constructed a comprehensive clinical thinking training system for TMD by deeply integrating AI and virtual simulation technology, providing an innovative and systematic solution for dental education. Guided by constructivist learning theory, the system realizes the connection from theory to practice through a three-module design of \"basic knowledge learning - clinical examination practice - diagnosis and treatment plan formulation\", providing students with a clinical learning environment close to reality. The evaluation of teaching practice effects shows that the system not only significantly improves students' learning interest, participation and clinical skills, but also effectively consolidates theoretical knowledge through personalized learning paths and real time feedback mechanisms, and enhances students' comprehensive ability in formulating TMD diagnosis and treatment plans.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgments\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e: This study was funded by: Shandong \u0026quot;111 Plan\u0026quot; Project for Undergraduate Education Reform in AI-empowered Key Fields (D2024002);\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003eShandong University School-level Education and Teaching Reform Research Project (2023Y189); Cheeloo College of Medicine, Shandong University Characteristic Undergraduate Education and Teaching Research Project (qlyxjy-202338); Shandong University Graduate Education and Teaching Reform Research Project (XYJG2023091); Shandong University [Research \u0026middot; Curriculum Ideological and Political Education] (Fourth Phase) \u0026quot;Comprehensively Promoting the Construction of Chinese-style Modernization\u0026quot; Special Project (KCSZ23008); Shandong University 2025 Experimental Technology Research Project (sy20252403); Shandong First Medical University (Shandong Academy of Medical Sciences) Education and Teaching Research Topic (JXGGYJ-22221603); Shandong University 2024 Undergraduate Education and Teaching Reform and Research Project (2024Y191)；Shandong University Cheeloo Medicine Featured Undergraduate Education and Teaching Research Project (qlyxjy-202511)\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of interest\u003c/strong\u003e The authors declare that they have no conflict of interest.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthica\u003c/strong\u003e\u003cstrong\u003el approval\u003c/strong\u003e All procedures performed in this study involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. The study was approved by the Ethics Committee of Shandong University School of Stomatology. (No.20251120)\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eInformed\u003c/strong\u003e\u003cstrong\u003e\u0026nbsp;consent\u003c/strong\u003e All participants provided written informed consent before recruitment.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u0026nbsp;\u003c/strong\u003eAll authors contributed to the study conception and design. The project was supervised by Shaohua Ge and Shengjun Sun. Material preparation, data collection and analysis were performed by Pei Zhang, He Wei and Yilin Zhang. Zixin Zhou assisted with preliminary data organization, Chunqin Wang supported literature checking, and Chi Zhang helped with figure and table proofreading. The first draft of the manuscript was written by Pei Zhang, and all authors approved the final manuscript.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eSchiffman E, Ohrbach R, Truelove E, Look JO, Anderson G, Ceusters W, et al. Diagnostic criteria for temporomandibular disorders (DC/TMD) for clinical and research applications: recommendations of the International RDC/TMD Consortium Network and Orofacial Pain Special Interest Group. J Oral Facial Pain Headache. 2014;28:6\u0026ndash;27.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZieliński G, Pająk-Zielińska B, Ginszt M. A meta-analysis of the global prevalence of temporomandibular disorders. J Clin Med. 2024;13:1365.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eValesan LF, Da-Cas CD, R\u0026eacute;us JC, Denardin AC, Garanhani RR, Bonotto D, et al. Prevalence of temporomandibular joint disorders: a systematic review and meta-analysis. Clin Oral Investig. 2021;25:441\u0026ndash;53.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDe Leeuw R, Klasser GD, editors. Orofacial pain: guidelines for assessment, diagnosis, and management. 6th ed. Quintessence Publishing; 2023.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMinervini G, Franco R, Marrapodi MM, Fiorillo L, Cervino G, Cicci\u0026ugrave; M. Prevalence of temporomandibular disorders in children and adolescents evaluated with Diagnostic Criteria for Temporomandibular Disorders: a systematic review with meta-analysis. J Oral Rehabil. 2023;50:522\u0026ndash;30.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRonsivalle V, Marrapodi MM, Tirupathi S, Afnan L, Cicci\u0026ugrave; M, Minervini G. Prevalence of temporomandibular disorders in juvenile idiopathic arthritis evaluated with diagnostic criteria for temporomandibular disorders: A systematic review with meta-analysis. J Oral Rehabil. 2024;51(3):628\u0026ndash;37.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBandiaky O, Lopez S, Hamon L, Clouet R, Soueidan A, Le Guehennec L. Impact of haptic simulators in preclinical dental education: A systematic review. J Dent Educ. 2024;88(3):366\u0026ndash;79.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOkeson JP. Management of temporomandibular disorders and occlusion. 8th ed. Elsevier; 2022.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKoolivand H, Shooreshi MM, Safari-Faramani R, Borjali M, Heydari S, Salehi AR. Comparison of the effectiveness of virtual reality-based education and conventional teaching methods in dental education: a systematic review. BMC Med Educ. 2024;24:8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMergen M, Graf N, Meyerheim M. Reviewing the current state of virtual reality integration in medical education - a scoping review. BMC Med Educ. 2024;24:788.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCardoso SA, Suyambu J, Iqbal J, Cortes Jaimes DC, Amin A, Sikto JT, et al. Exploring the role of simulation training in improving surgical skills among residents: a narrative review. Cureus. 2023;15:e44654.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eElendu C, Amaechi DC, Okatta AU, Amaechi EC, Elendu TC, Ezeh CP, et al. The impact of simulation-based training in medical education: a review. Med (Baltim). 2024;103:e38813.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlgarni YA, Saini RS, Vaddamanu SK, Alwadi M, Alqahtani A, Alabdulkader A, et al. The impact of virtual reality simulation on dental education: a systematic review of learning outcomes and student engagement. J Dent Educ. 2024;88:1549\u0026ndash;62.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBandiaky O, Lopez S, Hamon L, Lejus-Bourdeau C, Cousin I, Serfaty R. Impact of haptic simulators in preclinical dental education: a systematic review. J Dent Educ. 2024;88:366\u0026ndash;79.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDaud A, Matoug-Elwerfelli M, Daas H, Alhadidi A, Gonzalez-Marrero Y, Shore E, et al. Enhancing learning experiences in pre-clinical restorative dentistry: the impact of virtual reality haptic simulators. BMC Med Educ. 2023;23:948.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePethani F. Artificial intelligence in dental education: opportunities and challenges of large language models and multimodal foundation models. JMIR Med Educ. 2024;10:e52346.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShetty S, Gali S, Augustine D, Sv S. Artificial intelligence systems in dental shade-matching: A systematic review. J Prosthodont. 2024;33(6):519\u0026ndash;32.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHamama H, Harrison KY, Murbay S. Benefits of using virtual reality in cariology teaching. BMC Med Educ. 2024;24:1051.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThurzo A, Strunga M, Urban R, Surovkov\u0026aacute; J, L\u0026iacute;ška M. Impact of artificial intelligence on dental education: a review and guide for curriculum update. Educ Sci (Basel). 2023;13:150.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFu J, Lao Z, Gao L, Zhang Y, Chen X, Li H, et al. The application of virtual simulation technology in scaling and root planing teaching. BMC Oral Health. 2024;24:86.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePhilip N, Ali K, Duggal M, Murtadha L, Pring A, Nazzal H. Effectiveness and student perceptions of haptic virtual reality simulation training as an instructional tool in pre-clinical paediatric dentistry: a pilot pedagogical study. Int J Environ Res Public Health. 2023;20:4226.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKavadella A, Dias da Silva MA, Kaklamanos EG, Stangvaltaite-Mouhat L, Panagiotou S, Giannakopoulos N, et al. Evaluation of ChatGPT\u0026rsquo;s real-life implementation in undergraduate dental education: mixed methods study. JMIR Med Educ. 2024;10:e51344.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Dentistry, Experimental Teaching, Virtual Simulation, Temporomandibular Disorders, Artificial Intelligence Technology","lastPublishedDoi":"10.21203/rs.3.rs-8462289/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8462289/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eThe study aims to compare the efficacy of a virtual simulation-based teaching approach with a traditional method for clinical thinking training in temporomandibular disorders(TMD) for dental students.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThis study developed a virtual simulation program for clinical thinking training related to TMD, which includes basic knowledge learning, virtual simulation practice, and learning effect testing. A quasi-experimental design was adopted, with 97 senior dental students as the experimental group, receiving the virtual simulation experimental teaching mode; and 81 senior students of the same major as the control group, adopting the traditional teaching mode. The teaching efficacy was evaluated through theoretical tests, written experimental reports, and questionnaires.\u003c/p\u003e\u003ch2\u003eResult\u003c/h2\u003e \u003cp\u003eThe experimental group achieved significantly higher theoretical test score (84.6\u0026thinsp;\u0026plusmn;\u0026thinsp;8.5 \u003cem\u003evs\u003c/em\u003e 78.7\u0026thinsp;\u0026plusmn;\u0026thinsp;9.8, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.0001) and operational skills total score (89.1\u0026thinsp;\u0026plusmn;\u0026thinsp;7.4 \u003cem\u003evs\u003c/em\u003e 79.8\u0026thinsp;\u0026plusmn;\u0026thinsp;9.2, \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.001) compared to the control group. In individual operational skills assessments, the experimental group outperformed the control group in history-taking, palpation, image interpretation, diagnosis, and treatment plan formulation. Additionally, the experimental group reported significantly higher satisfaction in theoretical learning, clinical thinking and operational skills, and overall satisfaction indicating greater engagement and perceived effectiveness of the virtual simulation model.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eThe virtual simulation system enhances learning engagement, clinical skills, theoretical knowledge retention \u003cem\u003evia\u003c/em\u003e personalized pathways and real time feedback, thereby improving students' competence in TMD diagnosis and treatment planning.\u003c/p\u003e","manuscriptTitle":"The Impact of Artificial Intelligence-Enabled Virtual Simulation on Clinical Reasoning in Dental Students in Managing Temporomandibular Disorders","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-10 17:37:58","doi":"10.21203/rs.3.rs-8462289/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ca51fb25-4360-4cd1-8b9f-5c208ed43710","owner":[],"postedDate":"March 10th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Withdrawn","date":"2026-05-13T08:06:00+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-13T08:16:03+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-10 17:37:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8462289","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8462289","identity":"rs-8462289","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}