AI-Driven Reform of Motor Therapy Curriculum Content: Opportunities, Challenges, and Future Directions

Research Paper This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. DOI: 10.5281/zenodo.17971271 Page 20 1. Introduction Motor therapy is an integral component of rehabilitation medicine, emphasizing functional recovery and health management through exercise interventions. Globally, cardiovascular and cerebrovascular diseases, musculoskeletal disorders, and other conditions have become major causes of functional impairment. As a core intervention strategy, motor therapy has demonstrated significant efficacy in improving functional capacity and quality of life. Clinical guidelines generally recommend combining motor therapy with educational and cognitive-behavioral interventions to enhance functional outcomes in patients1. With the digital transformation in healthcare, the application potential of artificial intelligence (AI) technology in motor rehabilitation has gradually emerged. AI not only processes and analyzes large volumes of clinical data but also enables disease prediction, personalized treatment planning, and clinical decision support through machine learning and deep learning. For instance, AI-assisted clinical decision-making systems have shown promise in improving treatment adherence and reducing hospitalization rates among patients with diabetes and cardiovascular diseases12. In the field of motor therapy, AI-driven wearable devices and intelligent auxiliary tools can real-time monitor patients' exercise status, guide AI-Driven Reform of Motor Therapy Curriculum Content: Opportunities, Challenges, and Future Directions WANG Yuxiao1*, WANG Yufan2, QIU Ju3, YANG Qihao4, Wang FengXia5, Liu Meng6, Li Jiyan7 1, 2, 3, 4, 5, 6, 7 Pingdingshan University Corresponding Author: WANG Yuxiao With the rapid advancement of artificial intelligence (AI) technologies, Motor Therapy—an interdisciplinary field integrating medicine, rehabilitation, and exercise science—has entered a critical stage of curriculum restructuring. AI has introduced a wide range of innovative instructional tools and practical applications into the design of Motor Therapy courses, thereby accelerating the transformation and enhancement of educational models. However, the integration of AI also presents several challenges, including issues related to data security and privacy protection, the establishment of ethical guidelines, and the need to adapt teaching content and pedagogical approaches to new technological contexts.This paper provides a systematic review of the current applications of AI in Motor Therapy education, analyzes its advantages and potential barriers, and proposes strategies and pathways for future curriculum reconstruction based on the latest research evidence. By examining the reform of Motor Therapy curricula empowered by AI, this study aims to offer theoretical foundations and practical guidance for the digital transformation of rehabilitation education and to promote continuous development and innovation in this field. KEY WORDS: artificial intelligence; motor therapy; curriculum reform; instructional innovation; rehabilitation education; digital transformation Abbreviated Key Title: UAI J Eud Huma Lit. ISSN: 3049-3196 (Online) Journal Homepage: https://uaipublisher.com/uaijehl-2/ Volume1 Issue6 (November-December) 2025 Frequency: Bimonthly Research Paper This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. DOI: 10.5281/zenodo.17971271 Page 21 rehabilitation training, and enhance patient engagement and treatment efficacy2. Additionally, AI-based virtual reality (VR) and augmented reality (AR) technologies are being explored to increase the interest and effectiveness of rehabilitation training, promoting the personalization and refinement of motor therapy34. However, the current curriculum content of motor therapy still relies heavily on traditional teaching models, which struggle to meet the demands of interdisciplinary knowledge integration and technological application in modern healthcare settings. Traditional curricula primarily focus on basic theories and manual operation skills, lacking systematic coverage of AI, big data analytics, digital tools, and other emerging technologies. This limitation hinders students' understanding of cutting-edge technologies and the development of practical competencies56. Against this backdrop, curriculum reform has become a critical pathway to modernize motor therapy education. On one hand, curricula need to integrate foundational AI knowledge, machine learning applications, intelligent device operation, and data interpretation to enhance students' information literacy and technological application capabilities7. On the other hand, interdisciplinary collaboration skills should be strengthened to enable students to effectively integrate motor therapy with knowledge from medicine, information technology, and other fields, facilitating the design and implementation of personalized rehabilitation programs8. Furthermore, curriculum reform faces numerous challenges, including insufficient teaching resources, inadequate AI training for educators, and considerations regarding ethical and privacy issues9. In the practice of AI-assisted healthcare, ethical concerns such as data privacy protection, algorithm transparency, fairness, and liability attribution cannot be overlooked. Curriculum design must incorporate relevant content to foster students' ethical awareness and legal compliance capabilities910. Meanwhile, developing differentiated teaching plans and practical sessions tailored to students at different learning stages and with diverse professional backgrounds will help improve learning outcomes and technological application proficiency 1112. In summary, with the in-depth development of AI technology in healthcare, the reconstruction of motor therapy curriculum content holds significant practical significance and urgent necessity. By systematically integrating AI technology applications, data-driven decision support, and ethical norm education, it is possible to effectively enhance students' practical and innovative abilities, promote the deep integration of motor therapy education with modern medical technology, and lay a solid foundation for the training of future rehabilitation medicine professionals6. This paper systematically reviews the opportunities, challenges, and future directions of AI-driven curriculum reconstruction in motor therapy, aiming to promote the collaborative development of education and technology and advance the modernization of motor therapy education. 2. Current Status of AI Application in Motor Therapy Curriculum 2.1 Integration Approaches of AI Elements in Motor Therapy Curriculum Currently, the integration of artificial intelligence (AI) elements in motor therapy curriculum primarily manifests in three dimensions: introduction of basic theories, auxiliary practical operations, and interdisciplinary curriculum design. Firstly, in curriculum modules, foundational AI knowledge—such as machine learning principles, data analysis methods, and intelligent system architectures—has been incorporated into the teaching framework to help students establish a basic understanding of AI technology. For example, medical physics courses have explicitly included AI-related content (including medical image analysis and big data processing) as core teaching material, enhancing students' cognition of AI applications in healthcare15. This practice provides a reference for motor therapy education to cultivate professionals with AI literacy. Secondly, the introduction of AI-assisted equipment in practical courses has significantly improved students' operational skills and clinical judgment capabilities. Low-cost AI-driven wearable devices are used in musculoskeletal rehabilitation training, combined with AI chatbots to assist patients in completing home-based motor rehabilitation, thereby enhancing students' understanding of technology-assisted rehabilitation16. Additionally, AI-based VR systems are applied in rehabilitation training to support remote monitoring and real-time feedback, facilitating students' mastery of modern digital rehabilitation technologies17. These practical sessions not only enrich curriculum content but also provide students with opportunities to engage with cutting-edge technologies. Finally, interdisciplinary curriculum design has gradually become another important direction for AI element integration. The increasing integration of motor therapy with computer science and data science has promoted the development of comprehensive courses such as intelligent exercise prescription, exercise data analysis, and exercise performance evaluation. For instance, incorporating AI technology into cardiovascular rehabilitation courses—using machine learning models to optimize exercise prescriptions and monitor patients' physiological indicators— demonstrates the advantages of interdisciplinary teaching18. Furthermore, curriculum design in intelligent healthcare emphasizes the combination of motor therapy and AI technology to equip students with future-oriented comprehensive capabilities19. Through the aforementioned multi-dimensional and multi-angle integration of AI elements, the motor therapy curriculum has achieved dual goals of content innovation and skill enhancement. 2.2 Typical Case Analysis and Teaching Effect Evaluation in Motor Therapy Courses Numerous typical cases of AI technology integration in motor therapy courses at universities worldwide exist, with teaching effects quantitatively evaluated through multi-dimensional indicators. Taking cervical spine disease prevention and rehabilitation as an example, a university-developed AI-based intelligent cervical spine prevention system—integrating accelerometers and AI motion recognition modules—accurately identifies neck postures and guides patients in performing effective exercises. Educational practice has shown that this system enhances students' understanding and application of intelligent motion assessment13. In another case, an AI-supported motor rehabilitation app demonstrated significant reductions in pain intensity and functional impairment among patients with neck pain in clinical trials. Introducing this case into teaching helps students understand the practical value of AI-based personalized exercise prescriptions14. Quantitative evaluation indicators of teaching effects include student satisfaction, skill mastery, and improvement in clinical application capabilities. Surveys indicate that courses incorporating AI-assisted equipment and VR technology significantly improve students' operational proficiency and clinical decision-making abilities20. In VR-assisted training, students' learning interest and engagement are notably enhanced, with overall teaching satisfaction generally higher than that of traditional teaching methods21. Additionally, courses combining case-based teaching with AI technology effectively foster Research Paper This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. DOI: 10.5281/zenodo.17971271 Page 22 students' critical thinking and clinical reasoning skills, improving their comprehensive professional literacy2223. However, the cases also present several issues and areas for improvement. On one hand, some AI systems pose safety risks when addressing complex functional impairments, requiring strengthened interdisciplinary expert collaboration to optimize algorithms24. On the other hand, the high cost and technical barriers of AI technology limit its widespread application in some educational institutions; thus, enhancing teacher training and resource sharing is recommended19. Furthermore, students' depth of understanding and practical experience with AI technology still have room for improvement, necessitating the design of additional practical sessions and interdisciplinary projects to promote the development of comprehensive abilities20. In summary, typical cases provide empirical support for AI integration in motor therapy curricula with positive teaching effects, but continuous optimization is required to address issues related to safety, accessibility, and teaching depth. 3. Opportunities for AI-Driven Motor Therapy Curriculum Reform 3.1 Innovation and Diversification of Teaching Content The development of artificial intelligence (AI) technology has provided unprecedented opportunities for the innovation and diversification of motor therapy curriculum content. Firstly, AI has introduced numerous new knowledge points and skill requirements, enriching the curriculum system. For example, cutting-edge technologies such as digital health interventions, virtual reality (VR), augmented reality (AR), big data analytics, and intelligent diagnosis have become essential components of modern medical education2526. In curriculum design, big data analytics enables dynamic curriculum adjustment and personalized teaching, improving teaching efficiency and student learning experiences2728. Additionally, the integration of AI with virtual simulation technology has injected immersive and interactive experiences into motor therapy teaching—such as virtual clinical simulations and intelligent teaching platforms—enhancing students' understanding of complex motor functions and pathological mechanisms2930. Through these technologies, educators can design diversified teaching plans tailored to different student needs, promoting the deep integration of knowledge transmission and skill development, thereby advancing the curriculum system toward intelligence and precision31. 3.2 Enhancing Students' Practical Capabilities and Clinical Adaptability AI-assisted simulation training environments have greatly enhanced the realism and safety of students' clinical operations. For instance, in medical imaging practice teaching, AI-assisted diagnostic software based on Volume Data Reconstruction (VDR) technology provides 3D images and lesion annotations, significantly improving students' image interpretation abilities and academic confidence32. Intelligent feedback systems facilitate students' self-assessment and continuous improvement by leveraging real-time data analysis and personalized recommendations to help students identify weaknesses and develop improvement plans3334. Cultivating interdisciplinary collaboration skills has also become a key goal of AI-driven curriculum reform. Students need to adapt to the working model of diverse healthcare teams in the future, and AI platforms promote the integration and collaboration of knowledge from different disciplines35. Furthermore, VR and AR technologies not only enhance the immersion of operational skill training but also reduce the risks associated with operational errors in traditional clinical practice, allowing students to practice repeatedly in a safe environment and improving their clinical adaptability and decisionmaking abilities36. 3.3 Promoting the Digital Transformation of Educational Models The application of AI technology has accelerated the digital transformation of motor therapy educational models. The promotion of online teaching platforms and intelligent teaching management systems has improved the efficiency of teaching resource sharing and utilization, breaking geographical and temporal limitations37. The realization of distance education and virtual experiments has expanded the coverage of high-quality educational resources, enabling more students to access personalized and high-quality motor therapy education. Meanwhile, AI technology has made intelligent monitoring of teaching processes and personalized tutoring possible. Systems can real-time track students' learning status, dynamically adjust teaching strategies, and enhance learning outcomes38. Additionally, AI-driven content generation tools such as ChatGPT play an important role in the rapid generation and updating of teaching content, improving teaching efficiency and assisting educators in curriculum design and instruction3940. In the future, educational institutions need to further improve the AI education system, standardize technology application, and ensure the simultaneous improvement of teaching quality and equity during the digital transformation process4142. 4. Challenges Facing AI-Driven Motor Therapy Curriculum Reconstruction 4.1 Technical Limitations and Risks Although artificial intelligence (AI) technology offers significant advantages in reconstructing motor therapy curriculum content, its technical limitations and risks cannot be ignored. Firstly, AI algorithms generally exhibit a "black box" characteristic—their decision-making processes lack transparency and interpretability, leading to insufficient explainability of teaching content and thus hindering students' in-depth understanding of knowledge. For example, while ChatGPT demonstrates high quality and efficiency in generating professional medical education content (even outperforming some clinical trainers), it still has shortcomings in integrating key points and citing literature. This lack of information interpretability may impede the development of students' critical thinking39. Secondly, the use of patient data in teaching applications raises data privacy and security concerns. The widespread adoption of Electronic Health Records (EHRs) has improved information access efficiency but also introduced numerous ethical and legal risks, such as data breaches and unauthorized access. These issues require heightened attention during technology deployment and maintenance, particularly regarding the protection of patient privacy43. Additionally, AI-driven teaching equipment is costly and complex to maintain, becoming a major bottleneck limiting its popularization in some educational institutions. High costs not only affect hardware procurement but also increase the burden of subsequent maintenance and software updates, making it difficult for resource-constrained institutions to popularize relevant technologies44. Overall, technical limitations and risks require educational institutions to balance technical interpretability, data security, and economic feasibility when introducing AI technology, ensuring the equilibrium between teaching quality and student interests. 4.2 Insufficient Educational Adaptability and Faculty Research Paper This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. DOI: 10.5281/zenodo.17971271 Page 23 Capacity AI-driven curriculum reconstruction places higher demands on educational adaptability and faculty capacity, but significant deficiencies exist currently. Firstly, traditional educators generally have limited understanding and application capabilities of AI technology, directly impacting curriculum implementation outcomes. During the COVID-19 pandemic, teachers' adaptability to distance teaching tools was widely tested. Data showed that teachers—especially female teachers and those from low socioeconomic status schools—were more vulnerable, reflecting disparities in technological application capabilities45. Secondly, curriculum design lacks systematicness and forward-looking, struggling to meet rapidly evolving technological demands. Most curricula remain based on traditional teaching models, lacking instructional design tailored to AI technology characteristics, resulting in delayed content updates and failure to fully leverage AI's advantages in personalized teaching46. Furthermore, significant differences in students' foundational knowledge make comprehensive coverage of personalized teaching challenging. Although AI technology possesses certain personalized recommendation capabilities, matching teaching resources and methods remains difficult due to variations in students' cognitive levels and technology acceptance. This issue is further exacerbated in rural and resource-constrained areas, where teachers' limited digital competencies pose additional barriers47. Therefore, enhancing faculty digital literacy, optimizing curriculum design, and strengthening personalized teaching support for different student groups are key pathways to overcoming insufficient educational adaptability and faculty capacity. 4.3 Ethical and Legal Issues Ethical and legal issues have become unavoidable challenges in the AI-assisted reconstruction of motor therapy curriculum content. Firstly, the attribution of responsibility for AI-assisted decisionmaking in motor therapy remains unclear. AI systems may play important roles in curriculum design and treatment plan recommendations, but in cases of errors or deviations, liability delineation becomes complex— involving educators, developers, and institutions—posing challenges to teaching practice and legal regulation48. Secondly, mechanisms for protecting patient privacy and conducting ethical reviews during teaching remain inadequate. Although relevant ethical and legal frameworks exist in healthcare (such as medical confidentiality principles and patient autonomy protection), the introduction of AI technology requires more robust review and regulatory mechanisms to ensure the legal and compliant use of data, preventing privacy breaches and ethical risks49. Finally, while pursuing technological advancement, curriculum content must balance humanistic care to avoid technological alienation. AI technology should not replace educators' humanistic roles, as this could lead to mechanized teaching processes that overlook students' emotional and psychological needs, ultimately impacting educational quality and student development50. In summary, ethical and legal issues require the establishment of clear responsibility mechanisms, improved privacy protection policies, and the organic integration of technology and humanism in curriculum reconstruction to ensure the healthy development and social acceptance of the curriculum. 5. Conclusion With the rapid advancement of artificial intelligence technology, the reconstruction of motor therapy curriculum content has ushered in unprecedented opportunities. As a senior medical review expert, I believe that AI not only provides abundant resources and tools for curriculum innovation but also promotes the enhancement of practical capabilities and the digital transformation of educational models. This transformation makes teaching content more personalized and precise, better aligning with the needs of modern rehabilitation medicine and thus cultivating high-quality professionals capable of adapting to future healthcare environments. However, despite the numerous positive changes brought about by AI technology, significant challenges persist in the curriculum reconstruction process. Technical limitations—including algorithm accuracy, data privacy protection, and system stability—directly impact teaching effectiveness and the safety of practical applications. Meanwhile, the shortage of faculty and insufficient professional competencies limit the widespread application of AI technology, making it an urgent task to equip educators with the skills to effectively utilize these emerging tools. Additionally, ethical and legal issues—such as patient data protection, transparency of AI decision-making, and liability attribution— impose higher requirements on curriculum design and teaching practice. Addressing these challenges requires multi-faceted efforts, including policy formulation, technological research and development, and talent training, to promote multi-stakeholder collaboration and form a synergistic force for solutions. Future development directions should fully leverage the advantages of interdisciplinary collaboration, integrating professional knowledge from medicine, artificial intelligence, education, and other fields to promote the deep integration of curriculum content with AI technology. Improving the faculty training system and enhancing educators' understanding and application capabilities of AI technology are critical steps for the success of curriculum reconstruction. Simultaneously, curriculum design should emphasize the close integration of theory and practice, utilizing AI technology to strengthen the training of clinical thinking and operational skills, and promoting the comprehensive development of students' abilities. By constructing a scientific, systematic, and modern healthcarealigned motor therapy education system, we can continuously cultivate innovative and practically skilled professionals for the field of rehabilitation medicine. REFERENCES 1. Zaina F, Côté P, Cancelliere C, et al. A Systematic Review of Clinical Practice Guidelines for Persons With Nonspecific Low Back Pain With and Without Radiculopathy: Identification of Best Evidence for Rehabilitation to Develop the WHO’s Package of Interventions for Rehabilitation. Arch Phys Med Rehabil. 2023;104(11):1913-1927. doi:10.1016/j.apmr.2023.02.022 https://pubmed.ncbi.nlm.nih.gov/36963709/ 2. Hu J, Ren L, Wang T, Yao P. Artificial IntelligenceAssisted Clinical Decision-Making: A Perspective on Advancing Personalized Precision Medicine for Elderly Diabetes Patients. J Multidiscip Healthc. 18:4643-4651. Published 2025 None. doi:10.2147/JMDH.S529190 https://pubmed.ncbi.nlm.nih.gov/40787142/ 3. Antarsih NR, Siregar KN, Oktivasari P, Siswanto BB. Wearable technology for cardiovascular disease management: A global bibliometric analysis with emerging insights into artificial intelligence integration. Comput Biol Med. 2025;196(Pt B):110752. doi:10.1016/j.compbiomed.2025.110752 https://pubmed.ncbi.nlm.nih.gov/40669283/ 4. Waldmann G, Raab D. Subjective Performance Expectations From and Demographic and Categorical Research Paper This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. DOI: 10.5281/zenodo.17971271 Page 24 Differences in the Acceptance of Virtual Reality or AI Technologies in Rehabilitation Programs: Cross-Sectional Questionnaire Survey With Rehabilitation Patients. J Particip Med. 17:e69350. Published 2025 Aug 8. doi:10.2196/69350 https://pubmed.ncbi.nlm.nih.gov/40778859/ 5. Hamilton A. Artificial Intelligence and Healthcare Simulation: The Shifting Landscape of Medical Education. Cureus. 2024;16(5):e59747. Published 2024 May. doi:10.7759/cureus.59747 https://pubmed.ncbi.nlm.nih.gov/38840993/ 6. Hindhede AL, Andersen VH. The role of AI and personalized medicine in healthcare: balancing technological advancements and the art of medicine. BMC Med Educ. 2025;25(1):1580. Published 2025 Nov 11. doi:10.1186/s12909-025-07771-x https://pubmed.ncbi.nlm.nih.gov/41219950/ 7. Ahmed Z, Mohamed K, Zeeshan S, Dong X. Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine. Database (Oxford). 2020. doi:10.1093/database/baaa010 https://pubmed.ncbi.nlm.nih.gov/32185396/ 8. Lyu G. Data-driven decision making in patient management: a systematic review. BMC Med Inform Decis Mak. 2025;25(1):239. Published 2025 Jul 1. doi:10.1186/s12911-025-03072-x https://pubmed.ncbi.nlm.nih.gov/40598137/ 9. Gong J, Zhao Z, Niu X, et al. AI reshaping life sciences: intelligent transformation, application challenges, and future convergence in neuroscience, biology, and medicine. Front Digit Health. 7:1666415. Published 2025 None. doi:10.3389/fdgth.2025.1666415 https://pubmed.ncbi.nlm.nih.gov/41064793/ 10. Marques M, Almeida A, Pereira H. The Medicine Revolution Through Artificial Intelligence: Ethical Challenges of Machine Learning Algorithms in DecisionMaking. Cureus. 2024;16(9):e69405. Published 2024 Sep. doi:10.7759/cureus.69405 https://pubmed.ncbi.nlm.nih.gov/39411643/ 11. Hendricks-Sturrup R, Simmons M, Anders S, et al. Developing Ethics and Equity Principles, Terms, and Engagement Tools to Advance Health Equity and Researcher Diversity in AI and Machine Learning: Modified Delphi Approach. JMIR AI. 2:e52888. Published 2023 Dec 6. doi:10.2196/52888 https://pubmed.ncbi.nlm.nih.gov/38875540/ 12. Wolden B, Palm D, Wolden M. Effects of High-Fidelity Simulation-Based Learning on Physical Therapy Student Learning and Performance: A Systematic Review. J Phys Ther Educ. . Published online Aug 15,2025. doi:10.1097/JTE.0000000000000440 https://pubmed.ncbi.nlm.nih.gov/40814141/ 13. Wittbecker LM, von Spreckelsen R, Bandholz TC, Lehmhaus FW, Schwarz T, Gläser R. From the (skin) doctor’s office to the lecture hall: An innovative, practiceoriented, media-supported teaching project with supraregional interdisciplinary usage options. J Dtsch Dermatol Ges. 2021;19(5):694-705. doi:10.1111/ddg.14330 https://pubmed.ncbi.nlm.nih.gov/33951276/ 14. Li S, Zhou P, Xiao W, Zhou G. [A Wearable System for Cervical Spondylosis Prevention Based on Artificial Intelligence]. Zhongguo Yi Liao Qi Xie Za Zhi. 2020;44(1):33-37. doi:10.3969/j.issn.16717104.2020.01.007 https://pubmed.ncbi.nlm.nih.gov/32343063/ 15. Annika G, Rica H, Florian A, Christoff Z, Kerstin L. Effects of an artificial intelligence-based exercise program on pain intensity and disability in patients with neck pain compared with group exercise therapy: A cohort study. J Bodyw Mov Ther. 42:1031-1038. doi:10.1016/j.jbmt.2025.02.018 https://pubmed.ncbi.nlm.nih.gov/40325632/ 16. Zanca F, Hernandez-Giron I, Avanzo M, et al. Expanding the medical physicist curricular and professional programme to include Artificial Intelligence. Phys Med. 83:174-183. doi:10.1016/j.ejmp.2021.01.069 https://pubmed.ncbi.nlm.nih.gov/33798903/ 17. Mumuni I, Player D, Tehrany R, Carlson T. An AIEnabled Low-Cost Wearable to Support Musculoskeletal Rehabilitation: A Proof of Concept. Annu Int Conf IEEE Eng Med Biol Soc. 2025:1-7. doi:10.1109/EMBC58623.2025.11253465 https://pubmed.ncbi.nlm.nih.gov/41337264/ 18. Jung S, Zhou M, Ma J, et al. Wearable Body Sensors Integrated into a Virtual Reality Environment - A Modality for Automating the Rehabilitation of the Motor Control System. Annu Int Conf IEEE Eng Med Biol Soc. 2024:1-4. doi:10.1109/EMBC53108.2024.10782207 https://pubmed.ncbi.nlm.nih.gov/40039352/ 19. Deligiannis A, Sotiriou P, Deligiannis P, Kouidi E. The Role of Artificial Intelligence in Exercise-Based Cardiovascular Health Interventions: A Scoping Review. J Funct Morphol Kinesiol. 2025;10(4). Published 2025 Oct 21. doi:10.3390/jfmk10040409 https://pubmed.ncbi.nlm.nih.gov/41133599/ 20. Bulan PMP, Kuizon DAY, Casaña RSE, Fuentes CG, Pestaño NY, Suerte JRO. A Scoping Review on Artificial Intelligence in Occupational Therapy. OTJR (Thorofare N J). :15394492251379332. Published online Oct 21,2025. doi:10.1177/15394492251379332 https://pubmed.ncbi.nlm.nih.gov/41121544/ 21. Yang Z, Zhen S, Pan B, et al. Investigating the use of the HIS-based BOPPPS teaching model in medical imaging experimental course instruction. BMC Med Educ. 2025;25(1):996. Published 2025 Jul 2. doi:10.1186/s12909-025-07607-8 https://pubmed.ncbi.nlm.nih.gov/40604761/ 22. Li J, Hou C, Yang D, et al. Enhancing forensic clinical competence through scenario-based simulation: A comparative study of educational outcomes in Chinese medical students. PLoS One. 2025;20(11):e0336273. Published 2025 None. doi:10.1371/journal.pone.0336273 https://pubmed.ncbi.nlm.nih.gov/41231894/ 23. Yan J, Wen Y, Liu X, et al. The effectiveness of problembased learning and case-based learning teaching methods in clinical practical teaching in TACE treatment for hepatocellular carcinoma in China: a bayesian network meta-analysis. BMC Med Educ. 2024;24(1):665. Published 2024 Jun 17. doi:10.1186/s12909-024-05615-8 https://pubmed.ncbi.nlm.nih.gov/38886707/ 24. Du L, Zheng R, Zhu X, Jia J, Yang Z. Effectiveness of Case-Based Narrative Medicine Education in the Standardized Training of Obstetric Residents. Adv Med Educ Pract. 16:1511-1520. Published 2025 None. doi:10.2147/AMEP.S538754 Research Paper This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. DOI: 10.5281/zenodo.17971271 Page 25 https://pubmed.ncbi.nlm.nih.gov/40874176/ 25. Xu Y, Liu Q, Pang J, et al. Assessment of Personalized Exercise Prescriptions Issued by ChatGPT 4.0 and Intelligent Health Promotion Systems for Patients with Hypertension Comorbidities Based on the Transtheoretical Model: A Comparative Analysis. J Multidiscip Healthc. 17:5063-5078. Published 2024 None. doi:10.2147/JMDH.S477452 https://pubmed.ncbi.nlm.nih.gov/39539514/ 26. Comulada WS, McQueen C, Lang CM. Empowering tomorrow’s public health researchers and clinicians to develop digital health interventions using chatbots, virtual reality, and other AI technologies. Front Public Health. 13:1577076. Published 2025 None. doi:10.3389/fpubh.2025.1577076 https://pubmed.ncbi.nlm.nih.gov/40697845/ 27. Doherty G, Hughes C, McConnell J, Bond R, McLaughlin L, McFadden S. Integrating AI into medical imaging curricula: Insights from UK HEIs. Radiography (Lond). 2025;31(3):102957. doi:10.1016/j.radi.2025.102957 https://pubmed.ncbi.nlm.nih.gov/40280036/ 28. Fang J, Jia W. Applying information mining technology in online entrepreneurship training course. Sci Rep. 2024;14(1):22740. Published 2024 Sep 30. doi:10.1038/s41598-024-73491-9 https://pubmed.ncbi.nlm.nih.gov/39349748/ 29. Pathak DK, Rani C, Sati A, Kumar R. Developments in Raman Spectromicroscopy for Strengthening Materials and Natural Science Research: Shaping the Future of Physical Chemistry. ACS Phys Chem Au. 2024;4(5):430438. Published 2024 Sep 25. doi:10.1021/acsphyschemau.4c00017 https://pubmed.ncbi.nlm.nih.gov/39346605/ 30. Alsharari AF, Salihu D, Alshammari FF. Effectiveness of virtual clinical learning in nursing education: a systematic review. BMC Nurs. 2025;24(1):432. Published 2025 Apr 16. doi:10.1186/s12912-025-03076-y https://pubmed.ncbi.nlm.nih.gov/40241119/ 31. Aiello S, Cochrane T, Sevigny C. The affordances of clinical simulation immersive technology within healthcare education: a scoping review. Virtual Real. :119. Published online Jan 14,2023. doi:10.1007/s10055022-00745-0 https://pubmed.ncbi.nlm.nih.gov/36686614/ 32. Blusi M, Nilsson I, Fischl C, Lindgren H. Future Domain Experts - Integrating AI Education into Existing Master Programs for Health Professions. Stud Health Technol Inform. 332:299-303. doi:10.3233/SHTI251549 https://pubmed.ncbi.nlm.nih.gov/41041793/ 33. Wang D, Huai B, Ma X, et al. Application of artificial intelligence-assisted image diagnosis software based on volume data reconstruction technique in medical imaging practice teaching. BMC Med Educ. 2024;24(1):405. Published 2024 Apr 11. doi:10.1186/s12909-024-05382-6 https://pubmed.ncbi.nlm.nih.gov/38605345/ 34. Thesen T, Park SH. A generative AI teaching assistant for personalized learning in medical education. NPJ Digit Med. 2025;8(1):627. Published 2025 Nov 4. doi:10.1038/s41746-025-02022-1 https://pubmed.ncbi.nlm.nih.gov/41188616/ 35. Li K, Li Q, Wang L, Wang X, Ding X, Liu B. Virtual simulation experiments in medical education: technology acceptance, learning outcomes, and motivational impacts. BMC Med Educ. 2025;25(1):1462. Published 2025 Oct 21. doi:10.1186/s12909-025-08025-6 https://pubmed.ncbi.nlm.nih.gov/41121033/ 36. Tjardes T, Marche B, Imach S. Mangled extremity: limb salvage for reconstruction versus primary amputation. Curr Opin Crit Care. 2023;29(6):682-688. doi:10.1097/MCC.0000000000001108 https://pubmed.ncbi.nlm.nih.gov/37909372/ 37. [46] Lee E, Baek G. Development and Effects of a Virtual Reality Simulation Nursing Education Program Combined With Clinical Practice Based on an Information Processing Model. Comput Inform Nurs. 2023;41(12):1016-1025. Published 2023 Dec 1. doi:10.1097/CIN.0000000000001051 https://pubmed.ncbi.nlm.nih.gov/37647622/ 38. Yang Y, Ouyang T, Zhang L, Wang J. Study on blended teaching mode and its application based on the ARCS motivational model: Taking bioinformatics course as an example. Medicine (Baltimore). 2022;101(40):e30801. doi:10.1097/MD.0000000000030801 https://pubmed.ncbi.nlm.nih.gov/36221395/ 39. Black RW, Tomlinson B. University students describe how they adopt AI for writing and research in a general education course. Sci Rep. 2025;15(1):8799. Published 2025 Mar 14. doi:10.1038/s41598-025-92937-2 https://pubmed.ncbi.nlm.nih.gov/40087463/ 40. DeCook R, Muffly BT, Mahmood S, et al. AI-Generated Graduate Medical Education Content for Total Joint Arthroplasty: Comparing ChatGPT Against Orthopaedic Fellows. Arthroplast Today. 27:101412. Published 2024 Jun. doi:10.1016/j.artd.2024.101412 https://pubmed.ncbi.nlm.nih.gov/38912098/ 41. Zhao R, Xiong X, Li Z, Zhang L, Yang H, Ye Z. Recent advances and educational strategies in diagnostic imaging for temporomandibular disorders: a narrative literature review. Front Neurol. 16:1597312. Published 2025 None. doi:10.3389/fneur.2025.1597312 https://pubmed.ncbi.nlm.nih.gov/40492175/ 42. [55] Das LS, Das D, Chandrakar D, Bhavani P, Dubepuria A, Barik S. Exploring the role of artificial intelligence in orthopedic medical education: A narrative review. J Clin Orthop Trauma. 69:103100. Published 2025 Oct. doi:10.1016/j.jcot.2025.103100 https://pubmed.ncbi.nlm.nih.gov/40620691/ 43. Manohar N, Prasad SS. Real-World Application of an AIAssisted Digital Workflow for Clinical Observational Data Collection in Dermatology Residency Programs: An Innovative Pilot Report From India. Cureus. 2025;17(10):e94688. Published 2025 Oct. doi:10.7759/cureus.94688 https://pubmed.ncbi.nlm.nih.gov/41246753/ 44. Janarthanan V, Kumaran M S, Nagrale NV, Singh OG, Raj KV. Legal and Ethical Issues Associated With Challenges in the Implementation of the Electronic Medical Record System and Its Current Laws in India. Cureus. 2024;16(3):e56518. Published 2024 Mar. doi:10.7759/cureus.56518 https://pubmed.ncbi.nlm.nih.gov/38646271/ 45. Moncion A, Bryant AK, Cardenas CE, et al. Quantifying the Risk of Technology-Driven Health Disparities in Radiation Oncology. Pract Radiat Oncol. 2024 NovDec;14(6):e522-e529. doi:10.1016/j.prro.2024.06.009 https://pubmed.ncbi.nlm.nih.gov/38992491/ 46. Panadero E, Fraile J, Pinedo L, Rodríguez-Hernández C, Research Paper This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. DOI: 10.5281/zenodo.17971271 Page 26 Balerdi E, Díez F. Teachers’ Well-Being, Emotions, and Motivation During Emergency Remote Teaching Due to COVID-19. Front Psychol. 13:826828. Published 2022 None. doi:10.3389/fpsyg.2022.826828 https://pubmed.ncbi.nlm.nih.gov/35418912/ 47. Consorti F, Kanter SL, Basili S, Ho MJ. A SWOT analysis of Italian medical curricular adaptations to the COVID-19 pandemic: A nationwide survey of medical school leaders. Med Teach. 2021;43(5):546-553. doi:10.1080/0142159X.2021.1877266 https://pubmed.ncbi.nlm.nih.gov/33556296/ 48. Fernández-Arias P, Sánchez-Jiménez M, Antón-Sancho Á, Nieto-Sobrino M, Vergara D. Digital Competence of Rural Teachers in Depopulated Regions of Spain: A Bibliometric Review. Eur J Investig Health Psychol Educ. 2025;15(1). Published 2025 Jan 7. doi:10.3390/ejihpe15010005 https://pubmed.ncbi.nlm.nih.gov/39852188/ 49. Corfmat M, Martineau JT, Régis C. High-reward, highrisk technologies? An ethical and legal account of AI development in healthcare. BMC Med Ethics. 2025;26(1):4. Published 2025 Jan 15. doi:10.1186/s12910024-01158-1 https://pubmed.ncbi.nlm.nih.gov/39815254/ 50. Predeina I, Bobrovskaya O, Kaletskiy E, Sergeyev Y. Chapitre 3. On some issues of ensuring the rights of minor patients in Russian medical law: ethical and legal aspects of autonomy. J Int Bioethique Ethique Sci. 2023;34(1):4556. doi:10.3917/jibes.341.0045 https://pubmed.ncbi.nlm.nih.gov/37147176/ 51. Qadir HM, Khan RA, Rasool M, Sohaib M, Shah MA, Hasan MJ. An adaptive feedback system for the improvement of learners. Sci Rep. 2025;15(1):17242. Published 2025 May 18. doi:10.1038/s41598-025-01429w https://pubmed.ncbi.nlm.nih.gov/40383780/