Application of an AI-enhanced interactive virtual clinical reasoning training system in orthodontic residency training

Application of an AI-enhanced interactive virtual clinical reasoning training system in orthodontic residency training | 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 Application of an AI-enhanced interactive virtual clinical reasoning training system in orthodontic residency training Niu Qiannan, Wen Yi, Qi Yizhe, Wu Yuanqing, Yao Ying, He Jiaojiao, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8383271/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 Case-based discussion is essential for developing clinical reasoning in orthodontics education, but its traditional format faces limitations in terms of case accessibility, teaching consistency, and scheduling flexibility. To address these challenges, we developed an AI-enhanced interactive virtual clinical reasoning training system and implemented it in our orthodontic curriculum. This study evaluates the educational effectiveness and practical utility of this innovative teaching system. Methods The study involved 34 resident trainees from the School of Stomatology at Fourth Military Medical University (16 enrolled in 2022 and 18 in 2023). Participants were randomly assigned to either traditional lecture-based case discussions or the AI-enhanced interactive virtual clinical reasoning training system for case-based learning. After the intervention, all participants completed the same instructor-designed theoretical examination and case evaluations using the AI clinical reasoning system to assess its educational effectiveness, and provided feedback via questionnaires concerning their learning experience. Results There was no significant difference in theoretical exam scores between the two groups. However, In case evaluation, the group using the AI-assisted 3D clinical reasoning system showed significantly improved performance, and subjective questionnaire results also indicated that these students had notably enhanced learning efficiency and knowledge mastery in orthodontics. Conclusion The AI-enhanced interactive virtual clinical reasoning training system creates realistic clinical simulations from authentic cases, effectively bridging theoretical knowledge and clinical practice while cultivating humanistic competencies. This integrated approach provides substantive support for medical students' transition to clinical roles. Case-based discussion orthodontics education Medical AI Artificial Intelligence clinical reasoning Medical student Figures Figure 1 Figure 2 Introduction Standardized residency training is a fundamental component of dental education in China and operates primarily within the “5 + 3” framework. This three-year programme is designed for five-year undergraduate graduates and professional degree postgraduate students. Through a structured and progressive training process, it facilitates the transition from a student to a practising dentist, aiming to comprehensively develop professional capabilities, specialized knowledge, patient care skills, communication and collaborative skills, the capacity for lifelong learning, and systematic clinical practice 1 , 2 . At the heart of this professional development lies clinical reasoning. It serves as the foundational skill for diagnosing and managing oral health conditions, making it the essential conduit that transforms academic knowledge into effective patient care. Ultimately, cultivating this core competency in every dental trainee is a central mission of clinical teaching, as it not only defines expert practice but also drives progress in the field of dental science itself 3 , 4 . In recent years, the implementation of standardized residency training has revealed several discipline-specific challenges in orthodontics 5 . First, as undergraduate dental education seldom includes orthodontic internships, trainees typically encounter orthodontic patients for the first time during their residency. This delayed practical exposure often results in underdeveloped patient communication skills. Second, orthodontic cases are often clinically complex and highly variable and require adaptable treatment strategies and close interdisciplinary collaboration with fields such as general dentistry and clinical medicine. This level of complexity poses considerable difficulties for residents whose prior learning has been predominantly theoretical. Third, becoming a proficient orthodontist demands an extended training period supported by extensive clinical practice with a diverse range of patients. However, in many training institutions, the limited availability of patients restricts residents’ opportunities to translate theoretical knowledge into systematic clinical reasoning, hindering their progression from knowledge acquisition to qualitative professional development 6 . To address these challenges, an AI-enhanced interactive virtual clinical reasoning training system supported by artificial intelligence has been developed. This system incorporates more than 200 real clinical cases and creates a virtual diagnosis and treatment environment. It allows trainees to engage in ubiquitous learning through simulated scenarios, including AI-assisted patient consultation, 3D virtual clinical examination, and diagnosis and treatment planning. Cases are classified according to their level of difficulty. Accessible via a web-based platform, the system supports both routine training and formal evaluation, assisting students in refining their diagnostic and treatment skills. Methods The study was approved by the Institutional Review Board (IRB) at the Fourth Military Medical University ZL201425. 1. Training approach during the residency programme During our residency training programme, we implement a structured, phase-based educational approach that equally emphasizes theoretical learning and hands-on practice. The training process is organized as follows: Trainees first participate in small-group lectures that summarize key diagnosis and treatment principles for common malocclusions, helping them build a systematic theoretical foundation. They then engage in group discussions of actual cases, through which they gradually develop clinical reasoning skills specific to different types of malocclusions. Each resident subsequently completes training in the clinical environment. Finally, trainees undergo a comprehensive evaluation that includes both operational performance and results from a clinical reasoning assessment system. Those who meet the qualification standards are permitted to proceed to real clinical practice. 2. AI-enhanced interactive virtual clinical reasoning training system in residency training Case-based discussion is essential for applying theoretical knowledge to clinical practice in residency training. Traditional methods such as chairside mentoring and group discussions often provide limited case variety, which can restrict the effectiveness and consistency of trainee learning. To address these challenges, we developed and implemented an AI-enhanced interactive virtual clinical reasoning training system. The design logic and workflow of the system are shown in Fig. 1 . This platform categorizes cases into three difficulty levels—corresponding to the first, second, and third years of residency—with each level containing 30 real clinical cases. The system simulates the entire clinical workflow, including AI-supported patient interviewing, 3D clinical examination, interpretation of auxiliary diagnostics, and development of diagnosis and treatment plans. Additionally, the system is equipped with an AI assistant that provides real-time support in retrieving orthodontics-related knowledge—pretrained with specialized content in dental medicine—and offers digital note-taking and standardized case documentation functionalities. This integrated approach aims to enhance trainees’ self-directed learning and clinical decision-making skills in a structured and scalable environment. The system is also built upon a scientifically grounded evaluation framework. Its most distinctive feature is the AI-powered consultation assessment, which transforms traditionally intangible “soft skills”—such as clinical inquiry, patient communication, and empathy—into structured, quantifiable metrics. For detailed scoring criteria and their respective weightings, please refer to Table 1 . Table 1 AI Consultation Assessment Criteria Scoring Items Item Percentage A. Information Completeness A1 Chief Complaint and HPI Chief Complaint 10 Onset and Duration of Illness 5 Aetiology and Predisposing Factors 10 A2 Past History General Health Status 5 Systemic Diseases 5 Other Oral Diseases 5 Treatment History 5 Allergy History 5 Psychological Status 5 A3 Personal History Occupation 5 Lifestyle Habits 5 Adverse Habits 10 A4 Family History Genetic Oral Diseases 5 B. Logic and Efficiency of Inquiry B1 Consultation Process Questioning Logic 5 B2 Questioning Efficiency Validity and Redundancy 5 C. Communication Nonleading Wording 5 Absence of Professional Jargon 5 3. Research object and methods A total of 16 resident trainees who were enrolled in 2022 and 18 who were enrolled in 2023 at the School of Stomatology, Fourth Military Medical University, participated in this study. All the participants received consistent teaching and assessment throughout the training programme. Both groups were taught by the same faculty members in theoretical courses and participated in case-based group discussions under the guidance of the same instructional team. All instructors involved were certified through the National Resident Training Teaching Qualification Examination. Students in Group A learned cases using the AI-enhanced interactive virtual clinical reasoning training system, while those in Group B learned through traditional small-group discussions. Upon completion of the training, participants from both groups took the same instructor-designed theoretical examination. This exam had a maximum score of 70 points. To ensure objectivity, three instructors independently graded each exam, and the final theoretical score was derived from the average of their three assessments. Furthermore, all students completed three case evaluations using the AI clinical reasoning system, which accounted for a maximum of 30 points. The system’s integrated assessment module automatically generated a detailed competency profile for each student and calculated their final case-based score by averaging their performance across the three evaluations. At the end of the course, we collected anonymous questionnaire responses to gather student feedback on the system's effectiveness in supporting their learning process. 4. Statistics Statistical analysis was performed using SPSS for Windows, version 22.0. The scores of both student groups—including the theoretical assessment, case analysis scores—were found to meet the assumptions of a normal distribution and homogeneity of variance. An independent samples t test was applied to compare the scores between the two groups. A p value of less than 0.05 was considered to indicate statistical significance. Results 1. The statistical analysis showed that while Group A scored higher than Group B on the theoretical assessment, the difference was not statistically significant (Table 2 ). However, in the case analysis assessment, Group A’s score was significantly higher than that of Group B (Table 3 ). Table 2 Comparison of theoretical assessment scores between the two groups of students assessment method Group A(n = 17) Group B (n = 17) p theoretical assessment 64.12 ± 1.933 63.24 ± 2.195 P = 0.223 Table 3 Comparison of case analysis assessment scores between the two groups of students assessment method Group A(n = 17) Group B (n = 17) p case analysis assessment 26.29 ± 1.572 22.71 ± 1.448 P < 0.0001 2. The AI system’s assessment showed that the average score of the competency profiles for Group A was higher than that for Group B in the case evaluations.(Figure 2 ). 3. According to the survey results, 94.1% of the students believe that using the AI system has improved their understanding of the orthodontic process; 88.2% and 100% of the students feel that the system has strengthened their application ability in orthodontics and stimulated more independent thinking and clinical reasoning; 88.2% of the students perceived the difficulty level of the cases in the system as moderate. The system enables 94.1% of the students to better recall and apply theoretical knowledge during practice, and makes the knowledge learned by 100% of the students more memorable(Table 4 ). These results indicate that the AI-assisted 3D clinical reasoning system effectively enhances students' mastery of orthodontic content, improves their learning efficiency, and can effectively promote their learning outcomes. Table 4 Questionnaire results on the use of the AI-enhanced interactive virtual clinical reasoning training system Question Options 1. Degree of improvement in understanding orthodontic procedures after use:‌ Not applicable 0% Slight improvement 0% Moderate improvement 5.9% Significant improvement 88.2% Substantial improvement 5.9% 2. System's reinforcement of applied orthodontic knowledge: Not applicable 0% Slight improvement 5.9% Moderate improvement 5.9% Significant improvement 82.3% Substantial improvement 5.9% 3. Reasonableness of virtual case difficulty levels: Too easy 0% Relatively easy 0% Moderate 88.2% Relatively difficult 11.8% Too challenging 0% 4. System's stimulation of independent thinking and clinical reasoning: Strongly Disagree 0% Disagree 0% Neutral 0% Agree 94.13% Strongly Agree 5.9% 5. System's assistance in recalling and applying theoretical knowledge in practice: Strongly Disagree 0% Disagree 0% Neutral 5.9% Agree 82.4% Strongly Agree 11.7% 6. System's contribution to deeper knowledge retention: Strongly Disagree 0% Disagree 0% Neutral 0% Agree 88.2% Strongly Agree 11.8% Discussion Case-based learning (CBL) is an educational strategy centred on the learner, where participants work closely together to examine real clinical cases and develop understanding through collaboration 7 . This approach has gained broad recognition in medical training globally 8 . Through exposure to realistic patient scenarios, CBL helps strengthen clinical reasoning, teamwork, and the ability to connect theory with practice—all while encouraging critical thinking 9 , 10 . That said, traditional case teaching still has drawbacks, such as limited case variety, inconsistent instruction quality, and rigid time or location requirements. These factors can hinder the development of students’ full potential. While artificial intelligence has gained considerable traction in clinical dental practice—demonstrating substantial utility in areas such as diagnostic support, treatment planning, and outcome prediction 11 —its integration into dental education remains at an early developmental stage. The potential of AI to enhance case-based learning through dynamic scenario generation, adaptive feedback, and clinical simulation has yet to be systematically leveraged in most educational settings 12 . Current CBL methodologies continue to rely predominantly on conventional resources and instructor-led facilitation. There is growing recognition of the need to thoughtfully incorporate digital tools into medical pedagogy and explore how emerging technologies can support deeper cognitive engagement and practical competence without compromising educational integrity. Future efforts to align technological innovation with instructional design may open new pathways for cultivating clinical readiness among dental students 13 , 14 . Therefore, we developed this AI-enhanced interactive virtual clinical reasoning training system to enhance the depth and efficiency of dental education through digital means. The system is built upon real clinical cases, which differ from simplified “standard cases” in their inherent complexity, frequent involvement of multidisciplinary considerations, and incorporation of critical decision-making variables such as patients' subjective demands. The use of real clinical cases ensures that the training content maintains high fidelity to actual clinical scenarios that practitioners will encounter in the future 15 , 16 . Furthermore, we systematically categorized the case library into three difficulty levels—beginner, intermediate, and advanced—based on clinical complexity and teaching objectives, each corresponding to different stages of resident training. Each level currently comprises 70 authentic clinical cases encompassing both common conditions and classic complex disorders. This structured design ensures that instruction strictly adheres to the medical education principle of “progressing from simple to complex, step by step," providing trainees at different stages with clear, tailored and progressive learning paths. The system integrates several core functional modules, including AI-powered medical inquiry, three-dimensional visual oral examination, interpretation of auxiliary tests, and diagnosis and treatment planning, comprehensively covering key aspects of clinical practice. The AI medical inquiry module is specifically designed to address the challenge of cultivating and assessing competencies in doctor–patient communication and humanistic care—areas traditionally difficult to quantify in medical education 17 . By simulating authentic clinical consultations, this component guides trainees to master essential orthodontic diagnostic skills through structured practice. In terms of auxiliary examinations, the system supports cephalometric landmark analysis and the evaluation of panoramic radiographs and CBCT images and incorporates AI-based image analysis technology to provide intelligent recognition and diagnostic support. To further enhance the learning experience, the system features an integrated intelligence tutoring component. Its AI assistant, trained on the latest editions of authoritative foundational medical and dental textbooks used in China, offers users real-time, accurate theoretical knowledge support 18 . The “Teacher says” section, curated by supervising instructors on the basis of actual patient consultations, includes key points for doctor–patient communication, critical thinking in clinical practice, operational key points, treatment process analysis, and case summaries, ensuring that students can thoroughly comprehend all aspects of each case 19 . Another key strength of the system lies in its scientifically grounded evaluation framework. The system employs simulated patient consultations to transform difficult-to-measure skills—such as clinical questioning, patient communication, and empathy—into structured and quantifiable evaluation metrics. As a result, it opens the door to measuring the abstract concept of humanistic literacy. This capability creates a dynamic, trackable, and intervenable feedback loop, offering a data-driven foundation for the measurable, personalized development of these critical skills. During the evaluation phase, the system also generates a personalized “student profile,” visualized through a radar chart, to display learning processes and outcomes in a scientifically intuitive manner. This visualization assists instructors in accurately discerning individual students’ competency characteristics, thereby providing both data-driven insights and practical means to move closer to the goal of truly personalized, adaptive teaching 20 . In this study, a random grouping of residents was conducted, and traditional teaching and an AI-enhanced interactive virtual clinical reasoning training system were adopted. Statistical analysis of the case analysis scores revealed that the learning performance of the students in the AI-enhanced interactive virtual clinical reasoning training system group significantly improved, and the subjective questionnaire survey results also revealed that the learning efficiency and mastery of knowledge of the students in this group clearly increased. The AI system reconstructs the learning scenario of orthodontics through 3D visualization, natural language dialogue, virtual case libraries and other technologies, solving the pain point of “abstract and difficult-to-understand procedures”, and 94.1% of students achieved “significant improvement in understanding”. Natural language dialogue simulates real-world consultation, allowing students to ask questions and review diagnostic logic at any time, compensating for the insufficient interaction between teachers and students that is common in traditional teaching and promoting “significant reinforcement of knowledge” (88.2%). The virtual case library provides standardized clinical scenarios, offering continuous practice opportunities for students. In total, 88.2% of participants considered the virtual cases to be of “moderate difficulty”, which takes into account the needs of students at different levels, avoiding fatigue caused by excessive difficulty or the lack of a challenge caused by low difficulty. The system simulates the full process of consultation, diagnosis, and scheme formulation, allowing students to repeatedly train in “virtual clinics”, and 100% of participants felt that the system promoted the critical connection between "independent thinking and clinical reasoning” and theoretical knowledge and practical operation (such as embedding theoretical knowledge points in cases). This capability effectively addressed the problem of a disconnection between theory and practice, with 94.1% of participants reporting that the system effectively promoted the application of theoretical knowledge. Repetitive interactions and reinforcement learning after error feedback help students transform knowledge from short-term memory to long-term memory, and 100% of participants felt that the system supported their knowledge retention. The AI-enhanced interactive virtual clinical reasoning training system reconstructs learning scenarios through technology, optimizes learning motivation through experience, cultivates core literacy through skills development, and improves learning effects along the whole chain from understanding to consolidation to application to retention. It provides an innovative paradigm of “technology-empowered learning” for orthodontic residency teaching. To advance this research, efforts are needed to enhance the system's case database in terms of scale and difficulty, alongside dedicated training for educators to facilitate student learning. A dual-pronged approach is recommended for future development: first, longitudinal studies should be initiated to examine the sustained impact of the training, and second, synergies with AI-based diagnostic tools and virtual reality therapeutic simulations should be explored to construct a more integrated and intelligent environment for the development of clinical reasoning skills. Declarations Ethics approval and consent to participate This study has had an ethics committee approval, by the Institutional Review Board (IRB) at the Fourth Military Medical University ZL203950. The authors confirm that the study was performed in accordance with the ethical standards as laid down in the 1964 Declaration of Helsinki and its later amendments. All participants signed the informed consent before participating in the program. Consent for publication All data were obtained after written informed consent to answer and for data to be analysed and published. Availability of data and materials The datasets analysed during the current study are available from the corresponding author on reasonable request. Competing interests The authors have no conflicts of interest to disclose. Funding The study was supported by the National Natural Science Foundation of China [82301121]. Authors’ contributions( Niu Qiannan 1+ , Wen Yi 1+ , Qi Yizhe 1 , Wu Yuanqing 2 ,Yao Ying 1 , He Jiaojiao 1 , Wang Lei 1 * , Jin Fang ) NQ and WL conceived the study. Data were collected and analyzed by QY,YY and WL. The manuscript was drafted by NQ, WY, JF, and WL. All authors (NQ, WY, QY, WY, YY, HJ, WL,JF) critically reviewed, edited, and approved the final manuscript. All authors have read and agree to its submission to BMC Medical Education . Acknowledgments Not applicable. References Ono T, Pangrazio-Kulbersh V, Perillo L, Artese F, Czochrowska E, Darendeliler MA. etal.World Federation of Orthodontists guidelines for postgraduate orthodontic education.J World Fed Orthod.2023;12:41–9. Mahdavifard H, Noorollahian S, Omid A, Yamani N. What competencies does an orthodontic postgraduate need?BMC Med Educ.2024;24:1461. Shin KR. Critical thinking ability and clinical decision-making skills among senior nursing students in associate and baccalaureate programs in Korea.J Adv Nurs.1998;27:414–8. Doust J, Glasziou P. Clinical thinking: evidence, communication and decision-making.Oxford:Blackwell Publishing;2007. Allareddy V, Shin K, Marshall SD, Southard TE. Characteristics of an excellent orthodontic residency program.Am J Orthod Dentofac Orthop.2019;156:522–30. Joplin-Gonzales P, Rounds L. The essential elements of the clinical reasoning process.Nurse Educ.2022;47:E145–9. Cen XY, Hua Y, Niu S, Yu T. Application of case-based learning in medical student education: a meta-analysis.Eur Rev Med Pharmacol Sci.2021;25:3173–81. McLean SF. Case-based learning and its application in medical and health-care fields: a review of worldwide literature.J Med Educ Curric Dev.2016;3:JMECD.S20377. Ali M, Han SC, Bilal HSM, Lee S, Kang MJY, Kang BH. etal.iCBLS: An interactive case-based learning system for medical education.Int J Med Inf.2018;109:55–69. Zhang SL, Ren SJ, Zhu DM, Liu TY, Wang L, Zhao JH. etal.Which novel teaching strategy is most recommended in medical education? A systematic review and network meta-analysis.BMC Med Educ.2024;24:1342. Schwendicke F, Samek W, Krois J. Artificial intelligence in dentistry: chances and challenges.J Dent Res.2020;99:769–74. Khanagar SB, Al-Ehaideb A, Maganur PC, Vishwanathaiah S, Patil S, Baeshen HA. etal.Developments, application, and performance of artificial intelligence in dentistry: a systematic review.J Dent Sci.2021;16:508–22. Saghiri MA, Vakhnovetsky J, Nadershahi N. Scoping review of artificial intelligence and immersive digital tools in dental education.J Dent Educ.2022;86:736–50. Alzahrani FAA, Alolaiwi L, Alshammari SA. Shaping the future of dental education: a scoping review of artificial intelligence integration strategies.Cureus.2025;17:e84921. Waliany S, Caceres W, Merrell SB, Thadaney S, Johnstone N, Osterberg L. Preclinical curriculum of prospective case-based teaching with faculty- and student-blinded approach.BMC Med Educ.2019;19:31. Aparicio F. DeBuenagaM,RubioM,HernandoA.An intelligent information access system assisting a case based learning methodology evaluated in higher education with medical students.Comput Educ.2012;58:1282–95. Ghorashi N, Ismail A, Ghosh P, Sidawy A, Javan R. AI-powered chatbots in medical education: potential applications and implications.Cureus.2023;15:e43271. Barteit S, Guzek D, Jahn A, Bärnighausen T, Jorge MM, Neuhann F. Evaluation of e-learning for medical education in low- and middle-income countries: a systematic review.Comput Educ.2020;145:103726. Dong H, Sherer R, Lio J, Jiang I. Teacher immediacy for effective teaching in medical education.Med Sci Educ.2022;32:1535–9. Tchekmedyian V, Shields HM, Pelletier SR, Pazo VC. The effect of rubric-guided, focused, personalized coaching sessions and video-recorded presentations on teaching skills among fourth-year medical students: a pilot study.Acad Med.2017;92:1583–9. 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-8383271","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":570428753,"identity":"161449d2-6d5a-4879-b9fd-8c372ff5f257","order_by":0,"name":"Niu Qiannan","email":"","orcid":"","institution":"The Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Niu","middleName":"","lastName":"Qiannan","suffix":""},{"id":570428755,"identity":"063ff862-697f-423c-99ca-b9afea146e4b","order_by":1,"name":"Wen Yi","email":"","orcid":"","institution":"The Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Wen","middleName":"","lastName":"Yi","suffix":""},{"id":570428758,"identity":"8fd05672-8b46-4371-9b19-0e99ae915e20","order_by":2,"name":"Qi Yizhe","email":"","orcid":"","institution":"The Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Qi","middleName":"","lastName":"Yizhe","suffix":""},{"id":570428762,"identity":"ffbd90bc-6fe2-475e-a976-61560b367441","order_by":3,"name":"Wu Yuanqing","email":"","orcid":"","institution":"The Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Wu","middleName":"","lastName":"Yuanqing","suffix":""},{"id":570428765,"identity":"6cc17746-29f5-421d-83ab-a259c869e40c","order_by":4,"name":"Yao Ying","email":"","orcid":"","institution":"The Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yao","middleName":"","lastName":"Ying","suffix":""},{"id":570428766,"identity":"20b93ff3-79e1-4345-8012-f16c896ad39b","order_by":5,"name":"He Jiaojiao","email":"","orcid":"","institution":"The Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"He","middleName":"","lastName":"Jiaojiao","suffix":""},{"id":570428768,"identity":"ca17403a-f7d1-4443-86b4-a82bdd505f27","order_by":6,"name":"Jin Fang","email":"","orcid":"","institution":"The Fourth Military Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jin","middleName":"","lastName":"Fang","suffix":""},{"id":570428772,"identity":"9ff9426a-6830-49f7-85e8-04667ac9f65d","order_by":7,"name":"Wang Lei","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuUlEQVRIiWNgGAWjYBACNoYDCQc+/LCR4ydaCx/jgYcPZ/akGUs2EKtFjvngY2MetkOJBgeIdhjb4TQJHp4DCcbHkzcw/KjYRoQWnmNpEhIWd/LMzjwrYOw5c5sILRJn0iQMeJ4Vm93IMWBmbCNGi/z7bxIJbIcTN88gWgvDgWSDA0AtGyRI0JL4sBEYyBJAvxwkyi/yDQcSDv8BRWV78sYHPyqI0IIEEoiPGoQWUnWMglEwCkbBCAEAxZZC4tM4FoAAAAAASUVORK5CYII=","orcid":"","institution":"The Fourth Military Medical University","correspondingAuthor":true,"prefix":"","firstName":"Wang","middleName":"","lastName":"Lei","suffix":""}],"badges":[],"createdAt":"2025-12-17 08:23:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8383271/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8383271/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100005750,"identity":"0ece0279-da33-4695-9cdb-cb88d95a24e5","added_by":"auto","created_at":"2026-01-12 05:35:33","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":644817,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript1218.docx","url":"https://assets-eu.researchsquare.com/files/rs-8383271/v1/c21e43722061b8e89ec4aee0.docx"},{"id":100005752,"identity":"ef2ad658-5879-405b-87a1-dad06c4ff3d4","added_by":"auto","created_at":"2026-01-12 05:35:33","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9135,"visible":true,"origin":"","legend":"","description":"","filename":"b5af213483aa4e7eb52496318bf62064.json","url":"https://assets-eu.researchsquare.com/files/rs-8383271/v1/b74840769bf75e3e85343570.json"},{"id":100360704,"identity":"1c0efb47-0715-4e26-a47e-1d3e9f293899","added_by":"auto","created_at":"2026-01-16 07:41:09","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":68799,"visible":true,"origin":"","legend":"","description":"","filename":"b5af213483aa4e7eb52496318bf620641enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8383271/v1/a16f9e8371c8b6f29028123d.xml"},{"id":100005757,"identity":"82fb0fcc-8fec-406c-ba33-de3fcc051f66","added_by":"auto","created_at":"2026-01-12 05:35:33","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":600040,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8383271/v1/c6bd0e4985b619a9d38cd3b1.png"},{"id":100005754,"identity":"a3f573c7-2dae-4b50-8de9-e1da6c4f5bff","added_by":"auto","created_at":"2026-01-12 05:35:33","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":79109,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8383271/v1/8cd810ee783fc4bfd5a0f938.png"},{"id":100005756,"identity":"25d92317-e0f1-4e05-97e1-0ad1de9b53a9","added_by":"auto","created_at":"2026-01-12 05:35:33","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":87099,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8383271/v1/ded6377a16c0b26ca1aa8d4d.png"},{"id":100005753,"identity":"2efb8590-b4e0-4694-813a-82c58424eca6","added_by":"auto","created_at":"2026-01-12 05:35:33","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14567,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8383271/v1/4576e7137cf63ccfa5497a91.png"},{"id":100005759,"identity":"e3081a72-e630-4bf7-8136-987df3d036b7","added_by":"auto","created_at":"2026-01-12 05:35:33","extension":"xml","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67416,"visible":true,"origin":"","legend":"","description":"","filename":"b5af213483aa4e7eb52496318bf620641structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8383271/v1/a1908f61407b6b555a4731e9.xml"},{"id":100005758,"identity":"52495199-e1a2-444d-af63-7cae6f71336a","added_by":"auto","created_at":"2026-01-12 05:35:33","extension":"html","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":75158,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8383271/v1/9e6ea565a704ba5c87fa4a65.html"},{"id":100360839,"identity":"9bf492ce-9bf1-4188-b5b9-0bb90c86ba95","added_by":"auto","created_at":"2026-01-16 07:44:00","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":475189,"visible":true,"origin":"","legend":"\u003cp\u003eDesign Concept and Rationale\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8383271/v1/b41ff28905d44619bd5ed98a.png"},{"id":100005748,"identity":"590db2a0-2163-49fb-b220-8d14033ea40c","added_by":"auto","created_at":"2026-01-12 05:35:33","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":77166,"visible":true,"origin":"","legend":"\u003cp\u003eCompetency profiles of Groups A and B (AI-enhanced interactive virtual clinical reasoning training system).\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8383271/v1/22469ce185bd5fd76be449e6.png"},{"id":100418190,"identity":"be72d2ec-b3c7-4e27-9bc8-2bbba4031921","added_by":"auto","created_at":"2026-01-16 13:25:17","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1043641,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8383271/v1/e9326d45-7509-4b71-b8c8-a9e290c16ca7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Application of an AI-enhanced interactive virtual clinical reasoning training system in orthodontic residency training","fulltext":[{"header":"Introduction","content":"\u003cp\u003eStandardized residency training is a fundamental component of dental education in China and operates primarily within the \u0026ldquo;5\u0026thinsp;+\u0026thinsp;3\u0026rdquo; framework. This three-year programme is designed for five-year undergraduate graduates and professional degree postgraduate students. Through a structured and progressive training process, it facilitates the transition from a student to a practising dentist, aiming to comprehensively develop professional capabilities, specialized knowledge, patient care skills, communication and collaborative skills, the capacity for lifelong learning, and systematic clinical practice\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e,\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e. At the heart of this professional development lies clinical reasoning. It serves as the foundational skill for diagnosing and managing oral health conditions, making it the essential conduit that transforms academic knowledge into effective patient care. Ultimately, cultivating this core competency in every dental trainee is a central mission of clinical teaching, as it not only defines expert practice but also drives progress in the field of dental science itself\u003csup\u003e\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e,\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eIn recent years, the implementation of standardized residency training has revealed several discipline-specific challenges in orthodontics\u003csup\u003e\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u003c/sup\u003e. First, as undergraduate dental education seldom includes orthodontic internships, trainees typically encounter orthodontic patients for the first time during their residency. This delayed practical exposure often results in underdeveloped patient communication skills. Second, orthodontic cases are often clinically complex and highly variable and require adaptable treatment strategies and close interdisciplinary collaboration with fields such as general dentistry and clinical medicine. This level of complexity poses considerable difficulties for residents whose prior learning has been predominantly theoretical. Third, becoming a proficient orthodontist demands an extended training period supported by extensive clinical practice with a diverse range of patients. However, in many training institutions, the limited availability of patients restricts residents\u0026rsquo; opportunities to translate theoretical knowledge into systematic clinical reasoning, hindering their progression from knowledge acquisition to qualitative professional development\u003csup\u003e\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eTo address these challenges, an AI-enhanced interactive virtual clinical reasoning training system supported by artificial intelligence has been developed. This system incorporates more than 200 real clinical cases and creates a virtual diagnosis and treatment environment. It allows trainees to engage in ubiquitous learning through simulated scenarios, including AI-assisted patient consultation, 3D virtual clinical examination, and diagnosis and treatment planning. Cases are classified according to their level of difficulty. Accessible via a web-based platform, the system supports both routine training and formal evaluation, assisting students in refining their diagnostic and treatment skills.\u003c/p\u003e"},{"header":"Methods","content":"\u003cp\u003e The study was approved by the Institutional Review Board (IRB) at the Fourth Military Medical University ZL201425.\u003c/p\u003e \u003cp\u003e \u003cb\u003e1. Training approach during the residency programme\u003c/b\u003e \u003c/p\u003e \u003cp\u003eDuring our residency training programme, we implement a structured, phase-based educational approach that equally emphasizes theoretical learning and hands-on practice. The training process is organized as follows: Trainees first participate in small-group lectures that summarize key diagnosis and treatment principles for common malocclusions, helping them build a systematic theoretical foundation. They then engage in group discussions of actual cases, through which they gradually develop clinical reasoning skills specific to different types of malocclusions. Each resident subsequently completes training in the clinical environment. Finally, trainees undergo a comprehensive evaluation that includes both operational performance and results from a clinical reasoning assessment system. Those who meet the qualification standards are permitted to proceed to real clinical practice.\u003c/p\u003e \u003cp\u003e \u003cb\u003e2. AI-enhanced interactive virtual clinical reasoning training system in residency training\u003c/b\u003e \u003c/p\u003e \u003cp\u003eCase-based discussion is essential for applying theoretical knowledge to clinical practice in residency training. Traditional methods such as chairside mentoring and group discussions often provide limited case variety, which can restrict the effectiveness and consistency of trainee learning.\u003c/p\u003e \u003cp\u003eTo address these challenges, we developed and implemented an AI-enhanced interactive virtual clinical reasoning training system. The design logic and workflow of the system are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. This platform categorizes cases into three difficulty levels\u0026mdash;corresponding to the first, second, and third years of residency\u0026mdash;with each level containing 30 real clinical cases. The system simulates the entire clinical workflow, including AI-supported patient interviewing, 3D clinical examination, interpretation of auxiliary diagnostics, and development of diagnosis and treatment plans.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eAdditionally, the system is equipped with an AI assistant that provides real-time support in retrieving orthodontics-related knowledge\u0026mdash;pretrained with specialized content in dental medicine\u0026mdash;and offers digital note-taking and standardized case documentation functionalities. This integrated approach aims to enhance trainees\u0026rsquo; self-directed learning and clinical decision-making skills in a structured and scalable environment.\u003c/p\u003e \u003cp\u003eThe system is also built upon a scientifically grounded evaluation framework. Its most distinctive feature is the AI-powered consultation assessment, which transforms traditionally intangible \u0026ldquo;soft skills\u0026rdquo;\u0026mdash;such as clinical inquiry, patient communication, and empathy\u0026mdash;into structured, quantifiable metrics. For detailed scoring criteria and their respective weightings, please refer to Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\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\u003eAI Consultation Assessment Criteria\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\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=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eScoring Items\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eItem\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePercentage\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"12\" rowspan=\"13\"\u003e \u003cp\u003eA. Information Completeness\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003eA1 Chief Complaint and HPI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eChief Complaint\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eOnset and Duration of Illness\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAetiology and Predisposing Factors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\" morerows=\"5\" rowspan=\"6\"\u003e \u003cp\u003eA2 Past History\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eGeneral Health Status\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSystemic Diseases\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eOther Oral Diseases\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eTreatment History\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAllergy History\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePsychological Status\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003eA3 Personal History\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eOccupation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eLifestyle Habits\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAdverse Habits\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eA4 Family History\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eGenetic Oral Diseases\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eB. Logic and Efficiency of Inquiry\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eB1 Consultation Process\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eQuestioning Logic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eB2 Questioning Efficiency\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eValidity and Redundancy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eC. Communication\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNonleading Wording\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAbsence of Professional Jargon\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cb\u003e3. Research object and methods\u003c/b\u003e \u003c/p\u003e \u003cp\u003eA total of 16 resident trainees who were enrolled in 2022 and 18 who were enrolled in 2023 at the School of Stomatology, Fourth Military Medical University, participated in this study. All the participants received consistent teaching and assessment throughout the training programme.\u003c/p\u003e \u003cp\u003eBoth groups were taught by the same faculty members in theoretical courses and participated in case-based group discussions under the guidance of the same instructional team. All instructors involved were certified through the National Resident Training Teaching Qualification Examination. Students in Group A learned cases using the AI-enhanced interactive virtual clinical reasoning training system, while those in Group B learned through traditional small-group discussions.\u003c/p\u003e \u003cp\u003eUpon completion of the training, participants from both groups took the same instructor-designed theoretical examination. This exam had a maximum score of 70 points. To ensure objectivity, three instructors independently graded each exam, and the final theoretical score was derived from the average of their three assessments.\u003c/p\u003e \u003cp\u003eFurthermore, all students completed three case evaluations using the AI clinical reasoning system, which accounted for a maximum of 30 points. The system\u0026rsquo;s integrated assessment module automatically generated a detailed competency profile for each student and calculated their final case-based score by averaging their performance across the three evaluations.\u003c/p\u003e \u003cp\u003eAt the end of the course, we collected anonymous questionnaire responses to gather student feedback on the system's effectiveness in supporting their learning process.\u003c/p\u003e \u003cp\u003e \u003cb\u003e4. Statistics\u003c/b\u003e \u003c/p\u003e \u003cp\u003eStatistical analysis was performed using SPSS for Windows, version 22.0. The scores of both student groups\u0026mdash;including the theoretical assessment, case analysis scores\u0026mdash;were found to meet the assumptions of a normal distribution and homogeneity of variance. An independent samples t test was applied to compare the scores between the two groups. A p value of less than 0.05 was considered to indicate statistical significance.\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003e1. The statistical analysis showed that while Group A scored higher than Group B on the theoretical assessment, the difference was not statistically significant (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). However, in the case analysis assessment, Group A\u0026rsquo;s score was significantly higher than that of Group B (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\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\u003eComparison of theoretical assessment scores between the two groups of students\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eassessment\u0026nbsp;method\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGroup A(n\u0026thinsp;=\u0026thinsp;17)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eGroup B\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;17)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etheoretical assessment\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e64.12\u0026thinsp;\u0026plusmn;\u0026thinsp;1.933\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e63.24\u0026thinsp;\u0026plusmn;\u0026thinsp;2.195\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003eP\u0026thinsp;=\u0026thinsp;0.223\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\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\u003eComparison of case analysis assessment scores between the two groups of students\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\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 \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eassessment\u0026nbsp;method\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eGroup A(n\u0026thinsp;=\u0026thinsp;17)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eGroup B\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;17)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ecase analysis assessment\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e26.29\u0026thinsp;\u0026plusmn;\u0026thinsp;1.572\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e22.71\u0026thinsp;\u0026plusmn;\u0026thinsp;1.448\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003eP\u0026thinsp;\u0026lt;\u0026thinsp;0.0001\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e2. The AI system\u0026rsquo;s assessment showed that the average score of the competency profiles for Group A was higher than that for Group B in the case evaluations.(Figure \u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003col\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003e3. According to the survey results, 94.1% of the students believe that using the AI system has improved their understanding of the orthodontic process;\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003e88.2% and 100% of the students feel that the system has strengthened their application ability in orthodontics and stimulated more independent thinking and clinical reasoning; 88.2% of the students perceived the difficulty level of the cases in the system as moderate. The system enables 94.1% of the students to better recall and apply theoretical knowledge during practice, and makes the knowledge learned by 100% of the students more memorable(Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). These results indicate that the AI-assisted 3D clinical reasoning system effectively enhances students' mastery of orthodontic content, improves their learning efficiency, and can effectively promote their learning outcomes.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003c/ol\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\u003eQuestionnaire results on the use of the AI-enhanced interactive virtual clinical reasoning training system\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\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 \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"6\" nameend=\"c6\" namest=\"c1\"\u003e \u003cp\u003eQuestion Options\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1. Degree of improvement in understanding orthodontic procedures after use:\u0026zwnj;\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot applicable\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSlight improvement\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eModerate improvement\u003c/p\u003e \u003cp\u003e5.9%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSignificant improvement\u003c/p\u003e \u003cp\u003e88.2%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eSubstantial improvement\u003c/p\u003e \u003cp\u003e5.9%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2. System's reinforcement of applied orthodontic knowledge:\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot applicable\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSlight improvement\u003c/p\u003e \u003cp\u003e5.9%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eModerate improvement\u003c/p\u003e \u003cp\u003e5.9%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSignificant improvement\u003c/p\u003e \u003cp\u003e82.3%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eSubstantial improvement\u003c/p\u003e \u003cp\u003e5.9%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e3. Reasonableness of virtual case difficulty levels:\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eToo easy\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRelatively easy\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eModerate\u003c/p\u003e \u003cp\u003e88.2%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eRelatively difficult\u003c/p\u003e \u003cp\u003e11.8%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eToo\u003c/p\u003e \u003cp\u003echallenging\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e4. System's stimulation of independent thinking and clinical reasoning:\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eStrongly Disagree\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDisagree\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNeutral\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eAgree\u003c/p\u003e \u003cp\u003e94.13%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eStrongly Agree\u003c/p\u003e \u003cp\u003e5.9%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e5. System's assistance in recalling and applying theoretical knowledge in practice:\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eStrongly Disagree\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDisagree\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNeutral\u003c/p\u003e \u003cp\u003e5.9%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eAgree\u003c/p\u003e \u003cp\u003e82.4%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eStrongly Agree\u003c/p\u003e \u003cp\u003e11.7%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e6. System's contribution to deeper knowledge retention:\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eStrongly Disagree\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDisagree\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNeutral\u003c/p\u003e \u003cp\u003e0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eAgree\u003c/p\u003e \u003cp\u003e88.2%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eStrongly Agree\u003c/p\u003e \u003cp\u003e11.8%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eCase-based learning (CBL) is an educational strategy centred on the learner, where participants work closely together to examine real clinical cases and develop understanding through collaboration\u003csup\u003e\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e. This approach has gained broad recognition in medical training globally\u003csup\u003e\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u003c/sup\u003e. Through exposure to realistic patient scenarios, CBL helps strengthen clinical reasoning, teamwork, and the ability to connect theory with practice\u0026mdash;all while encouraging critical thinking\u003csup\u003e\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e, \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u003c/sup\u003e. That said, traditional case teaching still has drawbacks, such as limited case variety, inconsistent instruction quality, and rigid time or location requirements. These factors can hinder the development of students\u0026rsquo; full potential.\u003c/p\u003e \u003cp\u003eWhile artificial intelligence has gained considerable traction in clinical dental practice\u0026mdash;demonstrating substantial utility in areas such as diagnostic support, treatment planning, and outcome prediction\u003csup\u003e\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u003c/sup\u003e\u0026mdash;its integration into dental education remains at an early developmental stage. The potential of AI to enhance case-based learning through dynamic scenario generation, adaptive feedback, and clinical simulation has yet to be systematically leveraged in most educational settings\u003csup\u003e\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u003c/sup\u003e. Current CBL methodologies continue to rely predominantly on conventional resources and instructor-led facilitation. There is growing recognition of the need to thoughtfully incorporate digital tools into medical pedagogy and explore how emerging technologies can support deeper cognitive engagement and practical competence without compromising educational integrity. Future efforts to align technological innovation with instructional design may open new pathways for cultivating clinical readiness among dental students\u003csup\u003e\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e,\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eTherefore, we developed this AI-enhanced interactive virtual clinical reasoning training system to enhance the depth and efficiency of dental education through digital means. The system is built upon real clinical cases, which differ from simplified \u0026ldquo;standard cases\u0026rdquo; in their inherent complexity, frequent involvement of multidisciplinary considerations, and incorporation of critical decision-making variables such as patients' subjective demands. The use of real clinical cases ensures that the training content maintains high fidelity to actual clinical scenarios that practitioners will encounter in the future\u003csup\u003e\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e,\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eFurthermore, we systematically categorized the case library into three difficulty levels\u0026mdash;beginner, intermediate, and advanced\u0026mdash;based on clinical complexity and teaching objectives, each corresponding to different stages of resident training. Each level currently comprises 70 authentic clinical cases encompassing both common conditions and classic complex disorders. This structured design ensures that instruction strictly adheres to the medical education principle of \u0026ldquo;progressing from simple to complex, step by step,\" providing trainees at different stages with clear, tailored and progressive learning paths.\u003c/p\u003e \u003cp\u003eThe system integrates several core functional modules, including AI-powered medical inquiry, three-dimensional visual oral examination, interpretation of auxiliary tests, and diagnosis and treatment planning, comprehensively covering key aspects of clinical practice. The AI medical inquiry module is specifically designed to address the challenge of cultivating and assessing competencies in doctor\u0026ndash;patient communication and humanistic care\u0026mdash;areas traditionally difficult to quantify in medical education\u003csup\u003e\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e\u003c/sup\u003e. By simulating authentic clinical consultations, this component guides trainees to master essential orthodontic diagnostic skills through structured practice.\u003c/p\u003e \u003cp\u003eIn terms of auxiliary examinations, the system supports cephalometric landmark analysis and the evaluation of panoramic radiographs and CBCT images and incorporates AI-based image analysis technology to provide intelligent recognition and diagnostic support. To further enhance the learning experience, the system features an integrated intelligence tutoring component. Its AI assistant, trained on the latest editions of authoritative foundational medical and dental textbooks used in China, offers users real-time, accurate theoretical knowledge support\u003csup\u003e\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e\u003c/sup\u003e. The \u0026ldquo;Teacher says\u0026rdquo; section, curated by supervising instructors on the basis of actual patient consultations, includes key points for doctor\u0026ndash;patient communication, critical thinking in clinical practice, operational key points, treatment process analysis, and case summaries, ensuring that students can thoroughly comprehend all aspects of each case\u003csup\u003e\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eAnother key strength of the system lies in its scientifically grounded evaluation framework. The system employs simulated patient consultations to transform difficult-to-measure skills\u0026mdash;such as clinical questioning, patient communication, and empathy\u0026mdash;into structured and quantifiable evaluation metrics. As a result, it opens the door to measuring the abstract concept of humanistic literacy. This capability creates a dynamic, trackable, and intervenable feedback loop, offering a data-driven foundation for the measurable, personalized development of these critical skills.\u003c/p\u003e \u003cp\u003eDuring the evaluation phase, the system also generates a personalized \u0026ldquo;student profile,\u0026rdquo; visualized through a radar chart, to display learning processes and outcomes in a scientifically intuitive manner. This visualization assists instructors in accurately discerning individual students\u0026rsquo; competency characteristics, thereby providing both data-driven insights and practical means to move closer to the goal of truly personalized, adaptive teaching\u003csup\u003e\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eIn this study, a random grouping of residents was conducted, and traditional teaching and an AI-enhanced interactive virtual clinical reasoning training system were adopted.\u003c/p\u003e \u003cp\u003eStatistical analysis of the case analysis scores revealed that the learning performance of the students in the AI-enhanced interactive virtual clinical reasoning training system group significantly improved, and the subjective questionnaire survey results also revealed that the learning efficiency and mastery of knowledge of the students in this group clearly increased. The AI system reconstructs the learning scenario of orthodontics through 3D visualization, natural language dialogue, virtual case libraries and other technologies, solving the pain point of \u0026ldquo;abstract and difficult-to-understand procedures\u0026rdquo;, and 94.1% of students achieved \u0026ldquo;significant improvement in understanding\u0026rdquo;. Natural language dialogue simulates real-world consultation, allowing students to ask questions and review diagnostic logic at any time, compensating for the insufficient interaction between teachers and students that is common in traditional teaching and promoting \u0026ldquo;significant reinforcement of knowledge\u0026rdquo; (88.2%). The virtual case library provides standardized clinical scenarios, offering continuous practice opportunities for students. In total, 88.2% of participants considered the virtual cases to be of \u0026ldquo;moderate difficulty\u0026rdquo;, which takes into account the needs of students at different levels, avoiding fatigue caused by excessive difficulty or the lack of a challenge caused by low difficulty. The system simulates the full process of consultation, diagnosis, and scheme formulation, allowing students to repeatedly train in \u0026ldquo;virtual clinics\u0026rdquo;, and 100% of participants felt that the system promoted the critical connection between \"independent thinking and clinical reasoning\u0026rdquo; and theoretical knowledge and practical operation (such as embedding theoretical knowledge points in cases). This capability effectively addressed the problem of a disconnection between theory and practice, with 94.1% of participants reporting that the system effectively promoted the application of theoretical knowledge. Repetitive interactions and reinforcement learning after error feedback help students transform knowledge from short-term memory to long-term memory, and 100% of participants felt that the system supported their knowledge retention. The AI-enhanced interactive virtual clinical reasoning training system reconstructs learning scenarios through technology, optimizes learning motivation through experience, cultivates core literacy through skills development, and improves learning effects along the whole chain from understanding to consolidation to application to retention. It provides an innovative paradigm of \u0026ldquo;technology-empowered learning\u0026rdquo; for orthodontic residency teaching.\u003c/p\u003e \u003cp\u003eTo advance this research, efforts are needed to enhance the system's case database in terms of scale and difficulty, alongside dedicated training for educators to facilitate student learning. A dual-pronged approach is recommended for future development: first, longitudinal studies should be initiated to examine the sustained impact of the training, and second, synergies with AI-based diagnostic tools and virtual reality therapeutic simulations should be explored to construct a more integrated and intelligent environment for the development of clinical reasoning skills.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study has had an ethics committee approval, by the Institutional Review Board (IRB) at the Fourth Military Medical University ZL203950. The authors confirm that the study was performed in accordance with the ethical standards as laid down in the 1964 Declaration of Helsinki and its later amendments. All participants signed the informed consent before participating in the program.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll data were obtained after written informed consent to answer and for data to be analysed and published.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe datasets analysed during the current study are available from the corresponding author on reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors have no conflicts of interest to disclose.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study was supported by the National Natural Science Foundation of China [82301121].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors’ contributions(\u003c/strong\u003eNiu Qiannan\u0026nbsp;\u003csup\u003e1+\u003c/sup\u003e, Wen Yi\u003csup\u003e1+\u003c/sup\u003e, Qi Yizhe\u003csup\u003e1\u003c/sup\u003e, Wu Yuanqing\u003csup\u003e2\u003c/sup\u003e ,Yao Ying\u003csup\u003e1\u003c/sup\u003e, He Jiaojiao\u003csup\u003e1\u003c/sup\u003e, Wang Lei\u003csup\u003e1\u003c/sup\u003e\u003csup\u003e*\u003c/sup\u003e , Jin Fang\u003cstrong\u003e)\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNQ and WL conceived the study. Data were collected and analyzed by QY,YY and WL. The manuscript was drafted by NQ, WY, JF, and WL. All authors (NQ, WY, QY, WY, YY, HJ, WL,JF) critically reviewed, edited, and approved the final manuscript. All authors have read and agree to its submission to \u003cem\u003eBMC Medical Education\u003c/em\u003e.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgments\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eOno T, Pangrazio-Kulbersh V, Perillo L, Artese F, Czochrowska E, Darendeliler MA. etal.World Federation of Orthodontists guidelines for postgraduate orthodontic education.J World Fed Orthod.2023;12:41\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMahdavifard H, Noorollahian S, Omid A, Yamani N. What competencies does an orthodontic postgraduate need?BMC Med Educ.2024;24:1461.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShin KR. Critical thinking ability and clinical decision-making skills among senior nursing students in associate and baccalaureate programs in Korea.J Adv Nurs.1998;27:414\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDoust J, Glasziou P. Clinical thinking: evidence, communication and decision-making.Oxford:Blackwell Publishing;2007.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAllareddy V, Shin K, Marshall SD, Southard TE. Characteristics of an excellent orthodontic residency program.Am J Orthod Dentofac Orthop.2019;156:522\u0026ndash;30.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJoplin-Gonzales P, Rounds L. The essential elements of the clinical reasoning process.Nurse Educ.2022;47:E145\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCen XY, Hua Y, Niu S, Yu T. Application of case-based learning in medical student education: a meta-analysis.Eur Rev Med Pharmacol Sci.2021;25:3173\u0026ndash;81.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMcLean SF. Case-based learning and its application in medical and health-care fields: a review of worldwide literature.J Med Educ Curric Dev.2016;3:JMECD.S20377.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAli M, Han SC, Bilal HSM, Lee S, Kang MJY, Kang BH. etal.iCBLS: An interactive case-based learning system for medical education.Int J Med Inf.2018;109:55\u0026ndash;69.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang SL, Ren SJ, Zhu DM, Liu TY, Wang L, Zhao JH. etal.Which novel teaching strategy is most recommended in medical education? A systematic review and network meta-analysis.BMC Med Educ.2024;24:1342.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSchwendicke F, Samek W, Krois J. Artificial intelligence in dentistry: chances and challenges.J Dent Res.2020;99:769\u0026ndash;74.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKhanagar SB, Al-Ehaideb A, Maganur PC, Vishwanathaiah S, Patil S, Baeshen HA. etal.Developments, application, and performance of artificial intelligence in dentistry: a systematic review.J Dent Sci.2021;16:508\u0026ndash;22.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSaghiri MA, Vakhnovetsky J, Nadershahi N. Scoping review of artificial intelligence and immersive digital tools in dental education.J Dent Educ.2022;86:736\u0026ndash;50.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlzahrani FAA, Alolaiwi L, Alshammari SA. Shaping the future of dental education: a scoping review of artificial intelligence integration strategies.Cureus.2025;17:e84921.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWaliany S, Caceres W, Merrell SB, Thadaney S, Johnstone N, Osterberg L. Preclinical curriculum of prospective case-based teaching with faculty- and student-blinded approach.BMC Med Educ.2019;19:31.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAparicio F. DeBuenagaM,RubioM,HernandoA.An intelligent information access system assisting a case based learning methodology evaluated in higher education with medical students.Comput Educ.2012;58:1282\u0026ndash;95.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGhorashi N, Ismail A, Ghosh P, Sidawy A, Javan R. AI-powered chatbots in medical education: potential applications and implications.Cureus.2023;15:e43271.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBarteit S, Guzek D, Jahn A, B\u0026auml;rnighausen T, Jorge MM, Neuhann F. Evaluation of e-learning for medical education in low- and middle-income countries: a systematic review.Comput Educ.2020;145:103726.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDong H, Sherer R, Lio J, Jiang I. Teacher immediacy for effective teaching in medical education.Med Sci Educ.2022;32:1535\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTchekmedyian V, Shields HM, Pelletier SR, Pazo VC. The effect of rubric-guided, focused, personalized coaching sessions and video-recorded presentations on teaching skills among fourth-year medical students: a pilot study.Acad Med.2017;92:1583\u0026ndash;9.\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":"Case-based discussion, orthodontics education, Medical AI, Artificial Intelligence, clinical reasoning, Medical student","lastPublishedDoi":"10.21203/rs.3.rs-8383271/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8383271/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eCase-based discussion is essential for developing clinical reasoning in orthodontics education, but its traditional format faces limitations in terms of case accessibility, teaching consistency, and scheduling flexibility. To address these challenges, we developed an AI-enhanced interactive virtual clinical reasoning training system and implemented it in our orthodontic curriculum. This study evaluates the educational effectiveness and practical utility of this innovative teaching system.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThe study involved 34 resident trainees from the School of Stomatology at Fourth Military Medical University (16 enrolled in 2022 and 18 in 2023). Participants were randomly assigned to either traditional lecture-based case discussions or the AI-enhanced interactive virtual clinical reasoning training system for case-based learning. After the intervention, all participants completed the same instructor-designed theoretical examination and case evaluations using the AI clinical reasoning system to assess its educational effectiveness, and provided feedback via questionnaires concerning their learning experience.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eThere was no significant difference in theoretical exam scores between the two groups. However, In case evaluation, the group using the AI-assisted 3D clinical reasoning system showed significantly improved performance, and subjective questionnaire results also indicated that these students had notably enhanced learning efficiency and knowledge mastery in orthodontics.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eThe AI-enhanced interactive virtual clinical reasoning training system creates realistic clinical simulations from authentic cases, effectively bridging theoretical knowledge and clinical practice while cultivating humanistic competencies. This integrated approach provides substantive support for medical students' transition to clinical roles.\u003c/p\u003e","manuscriptTitle":"Application of an AI-enhanced interactive virtual clinical reasoning training system in orthodontic residency training","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-12 05:35:28","doi":"10.21203/rs.3.rs-8383271/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":"361156cd-d2c7-4d56-bb60-e053faa44c4a","owner":[],"postedDate":"January 12th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-16T13:05:28+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-12 05:35:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8383271","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8383271","identity":"rs-8383271","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}