{"paper_id":"0b0d045b-e9e2-4ba9-ae79-5871d22da101","body_text":"AI-Driven Case-Based Learning for English-Medium Medical Students: Applications in Teaching Benign Prostatic Hyperplasia | 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 AI-Driven Case-Based Learning for English-Medium Medical Students: Applications in Teaching Benign Prostatic Hyperplasia Wan-Zhang Liu, Kai-Ning Lu, Ze-Jun Yan, Jun-Hai Qian This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7944588/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 Learning (CBL) was widely used in medical education to develop clinical reasoning and knowledge application. However, English-Medium Instruction (EMI) environments presented additional linguistic and cognitive challenges. The emergence of large language models such as ChatGPT offered new opportunities to enhance both disciplinary and language learning. This study evaluated the educational impact of ChatGPT-assisted CBL in teaching benign prostatic hyperplasia to EMI medical students. Methods A cluster-randomized controlled trial was conducted among 64 undergraduate medical students enrolled in an EMI urology course. Participants were assigned to either a ChatGPT-assisted CBL group or a traditional CBL group. The AI-assisted group used ChatGPT to generate patient cases, clarify medical terminology, provide reasoning prompts, and summarize key learning points. Outcomes included knowledge acquisition, clinical reasoning, English communication performance, and learning satisfaction. Quantitative data were analyzed using paired and independent t-tests and ANCOVA, while qualitative data from interviews were thematically analyzed. Results Before the intervention, no significant differences were found between the ChatGPT-assisted CBL and traditional CBL groups (all p > 0.05). After four weeks, the ChatGPT-assisted group showed significantly greater improvements in knowledge, clinical reasoning, and overall clinical ability (all p < 0.05). They also achieved higher scores in English presentation, confidence, and self-assessment, with greater satisfaction and perceived usefulness for medical and EMI learning. These findings indicated that AI-assisted CBL enhanced students’ learning outcomes and engagement. Conclusion AI-assisted CBL effectively improved students’ knowledge acquisition, clinical reasoning, communication, and engagement in EMI medical education. Integrating ChatGPT into CBL provided a supportive and interactive learning environment, demonstrating its potential as an innovative educational tool when applied with appropriate guidance and supervision. Artificial intelligence ChatGPT case-based learning English-medium instruction medical education benign prostatic hyperplasia 1. Introduction Case-Based Learning (CBL) had become a staple of medical education as it placed learners in authentic clinical scenarios to develop diagnostic reasoning, critical thinking, and the application of basic science knowledge. Recent reviews had highlighted the widespread adoption of CBL across medical disciplines and its adaptability to online and hybrid formats, yet they also noted variation in design quality, especially when it was delivered remotely [ 1 , 2 , 3 ] . At the same time, English-Medium Instruction (EMI) programme in medical education had expanded globally. However, students in EMI settings often faced dual challenges: mastering disciplinary knowledge while managing language demands that impeded active small-group discussion, participation, and learning efficiency [ 4 ] . This situation underscored the need for scaffolding measures that supported both linguistic and disciplinary mastery within active pedagogies such as CBL. The emergence of large language models (LLMs) such as ChatGPT introduced a new dimension to CBL in EMI contexts. These tools generated richly detailed clinical cases, provided immediate explanations of medical terminology in English, and offered prompts that scaffolded reasoning, thereby reducing the extraneous cognitive load associated with language barriers. Early literature on LLMs in medical education suggested strong potential but emphasized the need for rigorous evaluation of learning outcomes, language performance, and implementation challenges [ 5 , 6 ] . Considering that benign prostatic hyperplasia (BPH) was one of the most prevalent and clinically relevant urological conditions—as well as a representative topic for integrating pathophysiology, clinical reasoning, and communication training—it provided an ideal context for exploring the pedagogical value of artificial intelligence (AI)-assisted CBL. Given these convergent findings, investigating AI-enhanced CBL specifically for EMI medical students through the lens of BPH teaching was considered timely and important for advancing both pedagogical innovation and equity in globalised medical training. 2. Methods 2.1. Study Design This study adopted a cluster-randomized controlled trial design with parallel groups to evaluate the educational impact of ChatGPT-assisted CBL among medical students enrolled in an EMI urology module. Eight learning clusters, each comprising eight students, were randomly assigned to two conditions: the experimental group (ChatGPT-assisted CBL) and the control group (traditional CBL without AI support). Two experienced instructors facilitated the sessions, each supervising four clusters—two experimental and two control.The intervention was implemented throughout the urology system module over one academic semester, integrating a CBL session focused on BPH aligned with the standard curriculum objectives. 2.2. Participants A total of 64 undergraduate medical students participated in the study. Students were allocated into eight pre-existing learning clusters of equal size (n = 8 per cluster). Group allocation to the experimental or control condition was performed at the cluster level to avoid cross-contamination. All participants were enrolled in the same EMI-based urology course and had no prior exposure to ChatGPT-assisted learning. 2.3. Intervention Students in the experimental group participated in a ChatGPT-assisted CBL session centered on BPH. ChatGPT (GPT-4 model) was integrated as a digital learning assistant to: ①Generate realistic patient cases and clinical data related to BPH. ②Explain relevant medical terminology in English. ③Provide guiding prompts to support students’ clinical reasoning during discussion. ④Summarize reflections and key learning points following the CBL session. The control group followed the same CBL structure, facilitated by instructors only, without AI support. Each CBL case was conducted over a 90-minute session including case analysis, small-group discussion, and instructor feedback. Both groups received identical learning objectives and course materials based on the BPH curriculum content. 2.4. Data Collection and Outcome Measures All participants completed pre- and post-intervention assessments related to the BPH module. (1) Knowledge acquisition: Assessed using a 20-item multiple-choice test covering the pathophysiology, diagnostic work-up, and management principles of BPH, aligned with the module learning outcomes. (2) Clinical reasoning ability: Evaluated through a Script Concordance Test (SCT) composed of authentic BPH case scenarios designed to measure context-dependent clinical decision-making in urology. (3) English communication competence: Measured through oral case presentations on BPH, independently evaluated by two blinded raters using a standardized rubric addressing accuracy of medical terminology, logical organization, and reasoning clarity. (4) Learning satisfaction and perceived usefulness: Assessed using a Likert-scale questionnaire and semi-structured interviews exploring students’ views on the CBL experience. In addition, both instructors participated in interviews and completed an evaluation form regarding their experiences integrating AI tools into the CBL process, providing qualitative insights and recommendations for future teaching practice. 2.5. Data Analysis Quantitative data were analyzed using SPSS (version 26.0). Descriptive statistics were reported as mean ± standard deviation. Between-group differences in pre- and post-test scores were compared using independent-sample t-tests and ANCOVA, controlling for baseline performance. Within-group changes were examined using paired t-tests. The significance level was set at p < 0.05. Qualitative data from open-ended responses and interviews were analyzed thematically to triangulate quantitative findings. 2.6. Ethical Considerations The study was reviewed and approved by the Institutional Ethics Committee of the First Affiliated Hospital of NingBo University. Participation was voluntary, and written informed consent was obtained from all students. Data were anonymized prior to analysis, and ChatGPT interactions were restricted to academic content to ensure privacy and data security. 3. Results 3.1. Assessment of students Before the intervention, no significant differences were observed between the ChatGPT-assisted CBL group and the traditional CBL group in gender distribution, baseline knowledge scores, or clinical reasoning ability (all p > 0.05), indicating comparable starting levels between groups(Table.1). After the 4-week intervention, students in the ChatGPT-assisted CBL group achieved significantly higher post-test scores in knowledge (17.4 ± 1.0 vs. 16.8 ± 1.3, p = 0.02) and clinical reasoning (46.0 ± 2.6 vs. 43.2 ± 2.0, p < 0.01) compared with the traditional CBL group. Their overall clinical ability also improved significantly in the ChatGPT-assisted CBL group (32.9 ± 3.5 vs. 27.0 ± 4.2, p < 0.01), particularly in medical history taking, treatment strategy, and humanistic care (all p < 0.01). English presentation performance was superior in the ChatGPT-assisted group (34.2 ± 3.3 vs. 29.6 ± 4.2, p < 0.01), especially in content quality, confidence, and identification of learning issues, while fluency and use of professional language showed no significant differences (p > 0.05). Students in the ChatGPT-assisted group also reported higher self-assessment scores (38.3 ± 3.0 vs. 31.1 ± 3.0, p < 0.01), greater understanding of course content, and stronger perceptions of usefulness for medical learning and EMI study (all p < 0.01). Overall satisfaction was significantly higher among these students (p < 0.01), suggesting that AI-assisted CBL enhanced learning outcomes, engagement, and confidence in EMI medical education.. 3.2. Assessment of facilitators Both facilitators expressed high satisfaction with the AI-assisted CBL sessions for EMI students (Supplement File.1). They identified several key advantages of AI integration: (1) enhanced student engagement and motivation, particularly in English-medium discussions; (2) improved clinical reasoning quality through AI-generated prompts that encouraged deeper analysis; (3) reduced preparation workload, as AI supported case development and supplementary materials; and (4) immediate feedback on language and conceptual understanding, aiding bilingual learners. Despite these positive outcomes, facilitators also reported several challenges: (1) occasional inaccuracy of AI outputs in complex clinical contexts; (2) potential student overreliance on AI-generated content without critical evaluation; and (3) the need for ongoing faculty training and institutional technical support to optimize AI use in teaching. 4. Discussion This study examined the impact of integrating AI—particularly LLMs such as ChatGPT—into CBL within an EMI medical curriculum. The findings demonstrated that AI-assisted CBL significantly enhanced students’ knowledge acquisition, clinical reasoning, communication confidence, and overall satisfaction compared with traditional CBL. These outcomes suggested that AI functioned as an effective pedagogical support, promoting both cognitive and linguistic engagement among medical students [ 7 , 8 ] . From the learners’ perspective, ChatGPT served as an accessible, interactive assistant that facilitated comprehension of complex clinical scenarios and the articulation of medical terminology in English. This finding was consistent with Chow et al [ 9 ] , who reported that LLMs improved personalized feedback and encouraged exploratory learning. The observed improvement in students’ confidence and participation reflected AI’s role in fostering an active and collaborative learning environment. Similarly, Shaw [ 10 ] found that interactive AI systems promoted reflection and self-directed learning through dynamic dialogue-based interaction. From the facilitators’ viewpoint, AI supported the preparation and refinement of case materials, saving instructional time and enabling educators to focus more on guiding reasoning and discussion. Comparable results were reported by Preiksaitis et al [ 12 ] , who highlighted that generative AI could assist with formative assessment and scenario creation but required careful verification to ensure accuracy. In this study, while instructors recognized the efficiency of AI-assisted preparation, they also expressed concerns regarding factual reliability and potential bias in AI-generated content, underscoring the need for expert oversight. Ethical and professional considerations remained central to sustainable implementation. Concerns regarding plagiarism, misinformation, and overreliance on AI mirrored those discussed by Patino et al [ 13 ] , emphasizing the importance of digital literacy, transparency, and academic integrity in AI integration. The present results reinforced that structured training and institutional guidelines were essential to ensure responsible use of AI in medical education. Furthermore, this study highlighted the evolving role of instructors in AI-enhanced learning environments. Educators were required to transition from knowledge transmitters to critical moderators, guiding learners to evaluate, verify, and ethically apply AI-generated information. This aligns with Liu et al [ 14 ] , who emphasized the importance of fostering “AI literacy” among both students and faculty to promote reflective and critical use of generative tools. Future work should examine the long-term effects of AI-assisted CBL on knowledge retention, reasoning development, and independent problem-solving ability. Overreliance on AI could potentially diminish learners’ critical thinking, underscoring the need for balanced integration and pedagogical design. Additionally, institutional frameworks should be strengthened to ensure data security, bias mitigation, and accountability, while interdisciplinary collaboration among educators, clinicians, and computer scientists will be crucial to developing pedagogically sound and ethically responsible AI systems [ 15 – 18 ] . 5. Conclusion This study demonstrated that large language model–based AI tools such as ChatGPT could enhance case-based learning in medical education by promoting learner engagement, supporting English language expression, and assisting facilitators in instructional design. However, issues of data reliability, ethical integrity, and overreliance remained significant challenges. The findings underscored that AI should be positioned as a pedagogical supplement rather than a replacement for human expertise. Establishing clear institutional guidelines, fostering AI literacy, and ensuring continuous evaluation of AI integration were essential to achieve sustainable and ethical use in medical training. Future studies with larger, multi-institutional samples and objective outcome measures were warranted to validate these preliminary results and explore long-term impacts on clinical reasoning and professional competence. Abbreviations BPH Benign Prostatic Hyperplasia CBL Case-Based Learning EMI English-Medium Instruction LLMs Large Language Models AI Artificial Intelligence SCT Script Concordance Test Declarations Author contribution WZ Liu: Data analysis, Manuscript writing and editing; KN Lu: Data collection and analysis; ZJ Yan: Revision of manuscript; JH Qian: Protocol, project development. Ethics approval and consent to participate: The study (involving humans) was performed in accordance with the Declaration of Helsinki. Ethical approval was granted by the Ethics Committee of the First Affiliated Hospital of NingBo University. Informed consent to participate in the study was obtained from all the subjects. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests. Availability of Data and Materials: The datasets generated and/or analysed during the current study are not publicly available due to an agreement with the subjects but are available from the corresponding author on reasonable request. Clinical trial number: Not applicable. Funding Information: 1. Ningbo Clinical Research Center for Urological Disease, NO.2019A21001; 2. Ningbo Top Medical and Health Research Program, No.2022020203; 3. Zhejiang Engineering Research Center of Innovative technologies and diagnostic and therapeutic equipment for urinary system diseases. References Bruen C, Illing J, Daly R, et al. Medical student experiences of Case-Based Learning (CBL) at a multicultural medical school. BMC Med Educ. 2025;25(1):152. 10.1186/s12909-024-06585-7 . Published 2025 Jan 30. Yue J, Shang Y, Cui H et al. Visualization analysis of CBL application in Chinese and international medical education based on big data mining. BMC Med Educ. 2025;25(1):402. Published 2025 Mar 19. 10.1186/s12909-025-06933-1 Yu Z, Zhao Z, Chen X, et al. Effects of standardised patients (SP) combined with case-based learning (CBL) in Chinese clinical education: a systematic review and meta-analysis. BMJ Open. 2025;15(9):e095705. 10.1136/bmjopen-2024-095705 . Published 2025 Sep 3. Liu R, Lin J, Chen X et al. From challenge to competence: the role of learning engagement in mediating stress and performance among clinical medical students in English-medium dental education. Front Med (Lausanne). 2025;12:1675855. Published 2025 Sep 10. 10.3389/fmed.2025.1675855 Aster A, Laupichler MC, Rockwell-Kollmann T, et al. ChatGPT and Other Large Language Models in Medical Education - Scoping Literature Review. Med Sci Educ. 2024;35(1):555–67. 10.1007/s40670-024-02206-6 . Published 2024 Nov 13. Xu T, Weng H, Liu F, et al. Current Status of ChatGPT Use in Medical Education: Potentials, Challenges, and Strategies. J Med Internet Res. 2024;26:e57896. 10.2196/57896 . Published 2024 Aug 28. Rao SJ, Isath A, Krishnan P et al. ChatGPT: A Conceptual Review of Applications and Utility in the Field of Medicine. J Med Syst. 2024;48(1):59. Published 2024 Jun 5. 10.1007/s10916-024-02075-x。 Meng X, Yan X, Zhang K, et al. The application of large language models in medicine: A scoping review. iScience. 2024;27(5):109713. 10.1016/j.isci.2024.109713。 . Published 2024 Apr 23. Chow M, Ng O. Beyond Chatbots: Moving Toward Multistep Modular AI Agents in Medical Education. JMIR Med Educ. 2025;11:e76661. 10.2196/7666 . Published 2025 Oct 2. Shaw K, Henning MA, Webster CS. Artificial Intelligence in Medical Education: a Scoping Review of the Evidence for Efficacy and Future Directions. Med Sci Educ. 2025;35(3):1803–16. 10.1007/s40670-025-02373-0 . Published 2025 Apr 2. Li X, Yan X, Lai H. The ethical challenges in the integration of artificial intelligence and large language models in medical education: A scoping review. PLoS One. 2025;20(10):e0333411. Published 2025 Oct 22. 10.1371/journal.pone.0333411 Preiksaitis C, Rose C. Opportunities, Challenges, and Future Directions of Generative Artificial Intelligence in Medical Education: Scoping Review. JMIR Med Educ. 2023;9:e48785. Published 2023 Oct 20. 10.2196/48785 Patino GA, Amiel JM, Brown M, et al. The Promise and Perils of Artificial Intelligence in Health Professions Education Practice and Scholarship. Acad Med. 2024;99(5):477–81. 10.1097/ACM.0000000000005636 . Liu H, Azam M, Bin Naeem S, et al. An overview of the capabilities of ChatGPT for medical writing and its implications for academic integrity. Health Info Libr J. 2023;40(4):440–6. 10.1111/hir.12509 . Su JM, Hsu SY, Fang TY, et al. Developing and validating a knowledge-based AI assessment system for learning clinical core medical knowledge in otolaryngology. Comput Biol Med. 2024;178:108765. 10.1016/j.compbiomed.2024.108765 . Francis NJ, Jones S, Smith DP. Generative AI in Higher Education: Balancing Innovation and Integrity. Br J Biomed Sci. 2025;81:14048. 10.3389/bjbs.2024.14048 . Published 2025 Jan 9. Currie GM. Academic integrity and artificial intelligence: is ChatGPT hype, hero or heresy? Semin Nucl Med. 2023;53(5):719–30. 10.1053/j.semnuclmed.2023.04.008 . Greengrass C. Navigating the AI Revolution in Medicine-Adopting Strategies for Medical Education. Med Sci Educ. 2024;35(2):1055–61. 10.1007/s40670-024-02257-9 . Published 2024 Dec 27. Tables Table.1 Basic Characteristics of Students Items ChatGPT-assisted CBL Traditional CBL statistic, p Gender Male 15 17 x 2 =0.25, p=0.61 Female 17 15 Knowledge-Pre 11.1±1.7 11.2± 2.0 t=-0.20, p=0.42 Reasoning-Pre 32.3±3.5 31.9±2.4 t=0.63, p=0.27 Table.2 Assessment of students Items ChatGPT-assisted CBL Traditional CBL statistic, p Knowledge-Post 17.4±1.0 16.8±1.3 t=2.1, p=0.02 Reasoning-Post 46.0±2.6 43.2±2.0 t=4.8, p<0.01 Clinical ability 32.9±3.5 27.0±4.2 t=6.1, p<0.01 Medical history 7.2±1.0 5.3±1.4 t=6.4, p<0.01 Analyze of examination 5.8±1.1 5.8±1.5 t=0.1, p=0.46 Differential diagnosis 5.3±1.2 5.3±1.4 t=0.1, p=0.46 Treatment strategy 7.1±1.3 6.3±1.4 t=2.4, p<0.01 Humanistic care 7.5±1.4 4.4±1.7 t=8.0, p<0.01 English Presentation 34.2±3.3 29.6±4.2 t=4.8, p<0.01 Professional languages 5.4±1.3 5.1±1.4 t=1.1, p=0.14 Contents 8.2±1.0 6.7±1.4 t=5.0, p<0.01 Learning issues 6.1±1.3 5.4±1.7 t=1.9, p=0.03 Fluently 6.1±1.1 6.1±1.3 t=-0.1, p=0.56 Confident 8.3±1.0 6.3±1.4 t=6.7, p<0.01 Self-assessment 38.3±3.0 31.1±3.0 t=9.6, p<0.01 Understanding 8.2±1.3 7.2±1.0 t=3.4, p<0.01 Useful for medical learning 7.3±1.7 4.4±1.7 t=6.9, p<0.01 Useful for professional English learning 8.3±0.7 8.1±0.4 t=1.2, p=0.11 Recommendation for EMI study 7.6±0.5 6.2±0.6 t=10.4, p<0.01 Satisfaction 7.3±1.0 5.3±1.4 t=6.7, p<0.01 Additional Declarations No competing interests reported. Supplementary Files EnglishInterviewGuide.pdf 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-7944588\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":true,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":578298266,\"identity\":\"ec5b039a-18c9-4b8d-b87e-e8ca6cb06df2\",\"order_by\":0,\"name\":\"Wan-Zhang Liu\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"The First Affiliated Hospital of Ningbo University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Wan-Zhang\",\"middleName\":\"\",\"lastName\":\"Liu\",\"suffix\":\"\"},{\"id\":578298267,\"identity\":\"5e463a2b-7ef5-4f88-b278-57408f342f3d\",\"order_by\":1,\"name\":\"Kai-Ning Lu\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"The First Affiliated Hospital of Ningbo University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Kai-Ning\",\"middleName\":\"\",\"lastName\":\"Lu\",\"suffix\":\"\"},{\"id\":578298268,\"identity\":\"baec90ab-30c4-4aae-9484-2e421671b7df\",\"order_by\":2,\"name\":\"Ze-Jun Yan\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"The First Affiliated Hospital of Ningbo University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Ze-Jun\",\"middleName\":\"\",\"lastName\":\"Yan\",\"suffix\":\"\"},{\"id\":578298269,\"identity\":\"4186bc0b-3d70-4d41-a7a4-b11d5e245de4\",\"order_by\":3,\"name\":\"Jun-Hai Qian\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwElEQVRIiWNgGAWjYBACfvaGhAMJFTZyQAaRWiR7Djw88OBMmjGQQaQWgxmOjw8+bDucuOFGArFaJJiBDjvDbCw58/HGGww1NtEEtZhLt4H8wibHL51WbMFwLC23gZAWyzlnQLbwGEvOzjGTYGw4TFiLwY38DwcS2yQSN9w8Q7SWhASgFgOg93mI1AIMW5DDEoCBDPRLAjF+AcZg8scfFf+BUXl4440PNTaEtaA4UiKBFOUQLaTqGAWjYBSMgpEBAFD3Sp/kEFDYAAAAAElFTkSuQmCC\",\"orcid\":\"\",\"institution\":\"The First Affiliated Hospital of Ningbo University\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Jun-Hai\",\"middleName\":\"\",\"lastName\":\"Qian\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2025-10-27 08:03:03\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-7944588/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-7944588/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":100877226,\"identity\":\"6086bb35-0bd3-4afb-9cff-291232bd305b\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 10:30:16\",\"extension\":\"docx\",\"order_by\":0,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":37715,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Mainfilewithtitleandtables.docx\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7944588/v1/a8bfde1cb1984e01bfd6ea9d.docx\"},{\"id\":100949722,\"identity\":\"fb1efbd5-cbba-4e60-8d6d-7f3ab5d5da29\",\"added_by\":\"auto\",\"created_at\":\"2026-01-23 07:05:13\",\"extension\":\"json\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":6423,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"499df8b97a0f4de6a4930e1300ac2d36.json\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7944588/v1/e64cacd552db7c8657c88974.json\"},{\"id\":100877227,\"identity\":\"12a79243-fb08-4b03-9373-d6fddcf55385\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 10:30:16\",\"extension\":\"pdf\",\"order_by\":2,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":46040,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"EnglishInterviewGuide.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7944588/v1/f5782fe5d5f64d9084a3a51e.pdf\"},{\"id\":100877228,\"identity\":\"02d6a341-d220-4c6a-b680-e665c3cab596\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 10:30:16\",\"extension\":\"xml\",\"order_by\":3,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":65388,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"499df8b97a0f4de6a4930e1300ac2d361enriched.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7944588/v1/6c4d0b816c862a01ceaa278a.xml\"},{\"id\":101202468,\"identity\":\"24343501-6f0b-4289-8d65-9523e4336a15\",\"added_by\":\"auto\",\"created_at\":\"2026-01-27 09:34:05\",\"extension\":\"xml\",\"order_by\":4,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":62573,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"499df8b97a0f4de6a4930e1300ac2d361structuring.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7944588/v1/6c39810050db2299e9976439.xml\"},{\"id\":100877229,\"identity\":\"8914b766-6f64-42ec-88e1-9a647d717bac\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 10:30:16\",\"extension\":\"html\",\"order_by\":5,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":73036,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"earlyproof.html\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7944588/v1/fca9ae937ce96e65f8aae6ec.html\"},{\"id\":101207506,\"identity\":\"e224a62a-3e0c-4364-8ae4-ce22caec4bdb\",\"added_by\":\"auto\",\"created_at\":\"2026-01-27 10:05:19\",\"extension\":\"pdf\",\"order_by\":0,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":557442,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"manuscript.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7944588/v1/2c788846-dc4c-429f-ac3a-20efa9758e9c.pdf\"},{\"id\":100877224,\"identity\":\"0ebc7633-42a7-4fb2-b396-c4990facd51f\",\"added_by\":\"auto\",\"created_at\":\"2026-01-22 10:30:16\",\"extension\":\"pdf\",\"order_by\":0,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"supplement\",\"size\":46040,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"EnglishInterviewGuide.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7944588/v1/a2334a8886ba5ff677eee665.pdf\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"AI-Driven Case-Based Learning for English-Medium Medical Students: Applications in Teaching Benign Prostatic Hyperplasia\",\"fulltext\":[{\"header\":\"1. Introduction\",\"content\":\"\\u003cp\\u003eCase-Based Learning (CBL) had become a staple of medical education as it placed learners in authentic clinical scenarios to develop diagnostic reasoning, critical thinking, and the application of basic science knowledge. Recent reviews had highlighted the widespread adoption of CBL across medical disciplines and its adaptability to online and hybrid formats, yet they also noted variation in design quality, especially when it was delivered remotely\\u003csup\\u003e[\\u003cspan citationid=\\\"CR1\\\" class=\\\"CitationRef\\\"\\u003e1\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR2\\\" class=\\\"CitationRef\\\"\\u003e2\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR3\\\" class=\\\"CitationRef\\\"\\u003e3\\u003c/span\\u003e]\\u003c/sup\\u003e.\\u003c/p\\u003e \\u003cp\\u003eAt the same time, English-Medium Instruction (EMI) programme in medical education had expanded globally. However, students in EMI settings often faced dual challenges: mastering disciplinary knowledge while managing language demands that impeded active small-group discussion, participation, and learning efficiency\\u003csup\\u003e[\\u003cspan citationid=\\\"CR4\\\" class=\\\"CitationRef\\\"\\u003e4\\u003c/span\\u003e]\\u003c/sup\\u003e. This situation underscored the need for scaffolding measures that supported both linguistic and disciplinary mastery within active pedagogies such as CBL.\\u003c/p\\u003e \\u003cp\\u003eThe emergence of large language models (LLMs) such as ChatGPT introduced a new dimension to CBL in EMI contexts. These tools generated richly detailed clinical cases, provided immediate explanations of medical terminology in English, and offered prompts that scaffolded reasoning, thereby reducing the extraneous cognitive load associated with language barriers. Early literature on LLMs in medical education suggested strong potential but emphasized the need for rigorous evaluation of learning outcomes, language performance, and implementation challenges\\u003csup\\u003e[\\u003cspan citationid=\\\"CR5\\\" class=\\\"CitationRef\\\"\\u003e5\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR6\\\" class=\\\"CitationRef\\\"\\u003e6\\u003c/span\\u003e]\\u003c/sup\\u003e. Considering that benign prostatic hyperplasia (BPH) was one of the most prevalent and clinically relevant urological conditions\\u0026mdash;as well as a representative topic for integrating pathophysiology, clinical reasoning, and communication training\\u0026mdash;it provided an ideal context for exploring the pedagogical value of artificial intelligence (AI)-assisted CBL. Given these convergent findings, investigating AI-enhanced CBL specifically for EMI medical students through the lens of BPH teaching was considered timely and important for advancing both pedagogical innovation and equity in globalised medical training.\\u003c/p\\u003e\"},{\"header\":\"2. Methods\",\"content\":\"\\u003cdiv id=\\\"Sec3\\\" class=\\\"Section2\\\"\\u003e\\n \\u003ch2\\u003e2.1. Study Design\\u003c/h2\\u003e\\n \\u003cp\\u003eThis study adopted a cluster-randomized controlled trial design with parallel groups to evaluate the educational impact of ChatGPT-assisted CBL among medical students enrolled in an EMI urology module. Eight learning clusters, each comprising eight students, were randomly assigned to two conditions: the experimental group (ChatGPT-assisted CBL) and the control group (traditional CBL without AI support). Two experienced instructors facilitated the sessions, each supervising four clusters\\u0026mdash;two experimental and two control.The intervention was implemented throughout the urology system module over one academic semester, integrating a CBL session focused on BPH aligned with the standard curriculum objectives.\\u003c/p\\u003e\\n\\u003c/div\\u003e\\n\\u003cdiv id=\\\"Sec4\\\" class=\\\"Section2\\\"\\u003e\\n \\u003ch2\\u003e2.2. Participants\\u003c/h2\\u003e\\n \\u003cp\\u003eA total of 64 undergraduate medical students participated in the study. Students were allocated into eight pre-existing learning clusters of equal size (n\\u0026thinsp;=\\u0026thinsp;8 per cluster). Group allocation to the experimental or control condition was performed at the cluster level to avoid cross-contamination. All participants were enrolled in the same EMI-based urology course and had no prior exposure to ChatGPT-assisted learning.\\u003c/p\\u003e\\n \\u003ch2\\u003e2.3. Intervention\\u003c/h2\\u003eStudents in the experimental group participated in a ChatGPT-assisted CBL session centered on BPH. ChatGPT (GPT-4 model) was integrated as a digital learning assistant to:\\u003cp\\u003e①Generate realistic patient cases and clinical data related to BPH.\\u003c/p\\u003e\\n \\u003cp\\u003e②Explain relevant medical terminology in English.\\u003c/p\\u003e\\n \\u003cp\\u003e③Provide guiding prompts to support students\\u0026rsquo; clinical reasoning during discussion.\\u003c/p\\u003e\\n \\u003cp\\u003e④Summarize reflections and key learning points following the CBL session.\\u003c/p\\u003e\\n \\u003cp\\u003eThe control group followed the same CBL structure, facilitated by instructors only, without AI support. Each CBL case was conducted over a 90-minute session including case analysis, small-group discussion, and instructor feedback. Both groups received identical learning objectives and course materials based on the BPH curriculum content.\\u003c/p\\u003e\\n\\u003c/div\\u003e\\n\\u003cdiv id=\\\"Sec6\\\" class=\\\"Section2\\\"\\u003e\\n \\u003ch2\\u003e2.4. Data Collection and Outcome Measures\\u003c/h2\\u003e\\n \\u003cp\\u003eAll participants completed pre- and post-intervention assessments related to the BPH module.\\u003c/p\\u003e\\n \\u003cp\\u003e(1) Knowledge acquisition: Assessed using a 20-item multiple-choice test covering the pathophysiology, diagnostic work-up, and management principles of BPH, aligned with the module learning outcomes.\\u003c/p\\u003e\\n \\u003cp\\u003e(2) Clinical reasoning ability: Evaluated through a Script Concordance Test (SCT) composed of authentic BPH case scenarios designed to measure context-dependent clinical decision-making in urology.\\u003c/p\\u003e\\n \\u003cp\\u003e(3) English communication competence: Measured through oral case presentations on BPH, independently evaluated by two blinded raters using a standardized rubric addressing accuracy of medical terminology, logical organization, and reasoning clarity.\\u003c/p\\u003e\\n \\u003cp\\u003e(4) Learning satisfaction and perceived usefulness: Assessed using a Likert-scale questionnaire and semi-structured interviews exploring students\\u0026rsquo; views on the CBL experience.\\u003c/p\\u003e\\n \\u003cp\\u003eIn addition, both instructors participated in interviews and completed an evaluation form regarding their experiences integrating AI tools into the CBL process, providing qualitative insights and recommendations for future teaching practice.\\u003c/p\\u003e\\n\\u003c/div\\u003e\\n\\u003cdiv id=\\\"Sec7\\\" class=\\\"Section2\\\"\\u003e\\n \\u003ch2\\u003e2.5. Data Analysis\\u003c/h2\\u003eQuantitative data were analyzed using SPSS (version 26.0). Descriptive statistics were reported as mean\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;standard deviation. Between-group differences in pre- and post-test scores were compared using independent-sample t-tests and ANCOVA, controlling for baseline performance. Within-group changes were examined using paired t-tests. The significance level was set at p\\u0026thinsp;\\u0026lt;\\u0026thinsp;0.05. Qualitative data from open-ended responses and interviews were analyzed thematically to triangulate quantitative findings.\\n\\u003c/div\\u003e\\n\\u003cdiv id=\\\"Sec8\\\" class=\\\"Section2\\\"\\u003e\\n \\u003ch2\\u003e2.6. Ethical Considerations\\u003c/h2\\u003e\\n \\u003cp\\u003eThe study was reviewed and approved by the Institutional Ethics Committee of the First Affiliated Hospital of NingBo University. Participation was voluntary, and written informed consent was obtained from all students. Data were anonymized prior to analysis, and ChatGPT interactions were restricted to academic content to ensure privacy and data security.\\u003c/p\\u003e\\u003cbr\\u003e\\n\\u003c/div\\u003e\"},{\"header\":\"3. Results\",\"content\":\"\\u003cdiv id=\\\"Sec10\\\" class=\\\"Section2\\\"\\u003e\\n \\u003ch2\\u003e3.1. Assessment of students\\u003c/h2\\u003e\\n \\u003cp\\u003eBefore the intervention, no significant differences were observed between the ChatGPT-assisted CBL group and the traditional CBL group in gender distribution, baseline knowledge scores, or clinical reasoning ability (all p\\u0026thinsp;\\u0026gt;\\u0026thinsp;0.05), indicating comparable starting levels between groups(Table.1).\\u003c/p\\u003e\\n \\u003cp\\u003eAfter the 4-week intervention, students in the ChatGPT-assisted CBL group achieved significantly higher post-test scores in knowledge (17.4\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;1.0 vs. 16.8\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;1.3, p\\u0026thinsp;=\\u0026thinsp;0.02) and clinical reasoning (46.0\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;2.6 vs. 43.2\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;2.0, p\\u0026thinsp;\\u0026lt;\\u0026thinsp;0.01) compared with the traditional CBL group. Their overall clinical ability also improved significantly in the ChatGPT-assisted CBL group (32.9\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;3.5 vs. 27.0\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;4.2, p\\u0026thinsp;\\u0026lt;\\u0026thinsp;0.01), particularly in medical history taking, treatment strategy, and humanistic care (all p\\u0026thinsp;\\u0026lt;\\u0026thinsp;0.01).\\u003c/p\\u003e\\n \\u003cp\\u003eEnglish presentation performance was superior in the ChatGPT-assisted group (34.2\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;3.3 vs. 29.6\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;4.2, p\\u0026thinsp;\\u0026lt;\\u0026thinsp;0.01), especially in content quality, confidence, and identification of learning issues, while fluency and use of professional language showed no significant differences (p\\u0026thinsp;\\u0026gt;\\u0026thinsp;0.05).\\u003c/p\\u003e\\n \\u003cp\\u003eStudents in the ChatGPT-assisted group also reported higher self-assessment scores (38.3\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;3.0 vs. 31.1\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;3.0, p\\u0026thinsp;\\u0026lt;\\u0026thinsp;0.01), greater understanding of course content, and stronger perceptions of usefulness for medical learning and EMI study (all p\\u0026thinsp;\\u0026lt;\\u0026thinsp;0.01). Overall satisfaction was significantly higher among these students (p\\u0026thinsp;\\u0026lt;\\u0026thinsp;0.01), suggesting that AI-assisted CBL enhanced learning outcomes, engagement, and confidence in EMI medical education..\\u003c/p\\u003e\\n\\u003c/div\\u003e\\n\\u003cdiv id=\\\"Sec11\\\" class=\\\"Section2\\\"\\u003e\\n \\u003ch2\\u003e3.2. Assessment of facilitators\\u003c/h2\\u003e\\n \\u003cp\\u003eBoth facilitators expressed high satisfaction with the AI-assisted CBL sessions for EMI students (Supplement File.1). They identified several key advantages of AI integration: (1) enhanced student engagement and motivation, particularly in English-medium discussions; (2) improved clinical reasoning quality through AI-generated prompts that encouraged deeper analysis; (3) reduced preparation workload, as AI supported case development and supplementary materials; and (4) immediate feedback on language and conceptual understanding, aiding bilingual learners.\\u003c/p\\u003e\\n \\u003cp\\u003eDespite these positive outcomes, facilitators also reported several challenges: (1) occasional inaccuracy of AI outputs in complex clinical contexts; (2) potential student overreliance on AI-generated content without critical evaluation; and (3) the need for ongoing faculty training and institutional technical support to optimize AI use in teaching.\\u003c/p\\u003e\\n\\u003c/div\\u003e\"},{\"header\":\"4. Discussion\",\"content\":\"\\u003cp\\u003eThis study examined the impact of integrating AI\\u0026mdash;particularly LLMs such as ChatGPT\\u0026mdash;into CBL within an EMI medical curriculum. The findings demonstrated that AI-assisted CBL significantly enhanced students\\u0026rsquo; knowledge acquisition, clinical reasoning, communication confidence, and overall satisfaction compared with traditional CBL. These outcomes suggested that AI functioned as an effective pedagogical support, promoting both cognitive and linguistic engagement among medical students\\u003csup\\u003e[\\u003cspan class=\\\"CitationRef\\\"\\u003e7\\u003c/span\\u003e, \\u003cspan class=\\\"CitationRef\\\"\\u003e8\\u003c/span\\u003e]\\u003c/sup\\u003e.\\u003c/p\\u003e\\n\\u003cp\\u003eFrom the learners\\u0026rsquo; perspective, ChatGPT served as an accessible, interactive assistant that facilitated comprehension of complex clinical scenarios and the articulation of medical terminology in English. This finding was consistent with Chow et al\\u003csup\\u003e[\\u003cspan class=\\\"CitationRef\\\"\\u003e9\\u003c/span\\u003e]\\u003c/sup\\u003e, who reported that LLMs improved personalized feedback and encouraged exploratory learning. The observed improvement in students\\u0026rsquo; confidence and participation reflected AI\\u0026rsquo;s role in fostering an active and collaborative learning environment. Similarly, Shaw\\u003csup\\u003e[\\u003cspan class=\\\"CitationRef\\\"\\u003e10\\u003c/span\\u003e]\\u003c/sup\\u003e found that interactive AI systems promoted reflection and self-directed learning through dynamic dialogue-based interaction.\\u003c/p\\u003e\\n\\u003cp\\u003eFrom the facilitators\\u0026rsquo; viewpoint, AI supported the preparation and refinement of case materials, saving instructional time and enabling educators to focus more on guiding reasoning and discussion. Comparable results were reported by Preiksaitis et al\\u003csup\\u003e[\\u003cspan class=\\\"CitationRef\\\"\\u003e12\\u003c/span\\u003e]\\u003c/sup\\u003e, who highlighted that generative AI could assist with formative assessment and scenario creation but required careful verification to ensure accuracy. In this study, while instructors recognized the efficiency of AI-assisted preparation, they also expressed concerns regarding factual reliability and potential bias in AI-generated content, underscoring the need for expert oversight.\\u003c/p\\u003e\\n\\u003cp\\u003eEthical and professional considerations remained central to sustainable implementation. Concerns regarding plagiarism, misinformation, and overreliance on AI mirrored those discussed by Patino et al\\u003csup\\u003e[\\u003cspan class=\\\"CitationRef\\\"\\u003e13\\u003c/span\\u003e]\\u003c/sup\\u003e, emphasizing the importance of digital literacy, transparency, and academic integrity in AI integration. The present results reinforced that structured training and institutional guidelines were essential to ensure responsible use of AI in medical education.\\u003c/p\\u003e\\n\\u003cp\\u003eFurthermore, this study highlighted the evolving role of instructors in AI-enhanced learning environments. Educators were required to transition from knowledge transmitters to critical moderators, guiding learners to evaluate, verify, and ethically apply AI-generated information. This aligns with Liu et al\\u003csup\\u003e[\\u003cspan class=\\\"CitationRef\\\"\\u003e14\\u003c/span\\u003e]\\u003c/sup\\u003e, who emphasized the importance of fostering \\u0026ldquo;AI literacy\\u0026rdquo; among both students and faculty to promote reflective and critical use of generative tools.\\u003c/p\\u003e\\n\\u003cp\\u003eFuture work should examine the long-term effects of AI-assisted CBL on knowledge retention, reasoning development, and independent problem-solving ability. Overreliance on AI could potentially diminish learners\\u0026rsquo; critical thinking, underscoring the need for balanced integration and pedagogical design. Additionally, institutional frameworks should be strengthened to ensure data security, bias mitigation, and accountability, while interdisciplinary collaboration among educators, clinicians, and computer scientists will be crucial to developing pedagogically sound and ethically responsible AI systems\\u003csup\\u003e[\\u003cspan class=\\\"CitationRef\\\"\\u003e15\\u003c/span\\u003e\\u0026ndash;\\u003cspan class=\\\"CitationRef\\\"\\u003e18\\u003c/span\\u003e]\\u003c/sup\\u003e.\\u003c/p\\u003e\"},{\"header\":\"5. Conclusion\",\"content\":\"\\u003cp\\u003eThis study demonstrated that large language model\\u0026ndash;based AI tools such as ChatGPT could enhance case-based learning in medical education by promoting learner engagement, supporting English language expression, and assisting facilitators in instructional design. However, issues of data reliability, ethical integrity, and overreliance remained significant challenges. The findings underscored that AI should be positioned as a pedagogical supplement rather than a replacement for human expertise. Establishing clear institutional guidelines, fostering AI literacy, and ensuring continuous evaluation of AI integration were essential to achieve sustainable and ethical use in medical training. Future studies with larger, multi-institutional samples and objective outcome measures were warranted to validate these preliminary results and explore long-term impacts on clinical reasoning and professional competence.\\u003c/p\\u003e\\n\"},{\"header\":\"Abbreviations\",\"content\":\"\\u003cdiv class=\\\"DefinitionList\\\"\\u003e \\u003cdiv class=\\\"DefinitionListEntry\\\"\\u003e \\u003cdiv class=\\\"Term\\\"\\u003eBPH\\u003c/div\\u003e \\u003cdiv class=\\\"Description\\\"\\u003e \\u003cp\\u003eBenign Prostatic Hyperplasia\\u003c/p\\u003e \\u003c/div\\u003e \\u003c/div\\u003e \\u003cdiv class=\\\"DefinitionListEntry\\\"\\u003e \\u003cdiv class=\\\"Term\\\"\\u003eCBL\\u003c/div\\u003e \\u003cdiv class=\\\"Description\\\"\\u003e \\u003cp\\u003eCase-Based Learning\\u003c/p\\u003e \\u003c/div\\u003e \\u003c/div\\u003e \\u003cdiv class=\\\"DefinitionListEntry\\\"\\u003e \\u003cdiv class=\\\"Term\\\"\\u003eEMI\\u003c/div\\u003e \\u003cdiv class=\\\"Description\\\"\\u003e \\u003cp\\u003eEnglish-Medium Instruction\\u003c/p\\u003e \\u003c/div\\u003e \\u003c/div\\u003e \\u003cdiv class=\\\"DefinitionListEntry\\\"\\u003e \\u003cdiv class=\\\"Term\\\"\\u003eLLMs\\u003c/div\\u003e \\u003cdiv class=\\\"Description\\\"\\u003e \\u003cp\\u003eLarge Language Models\\u003c/p\\u003e \\u003c/div\\u003e \\u003c/div\\u003e \\u003cdiv class=\\\"DefinitionListEntry\\\"\\u003e \\u003cdiv class=\\\"Term\\\"\\u003eAI\\u003c/div\\u003e \\u003cdiv class=\\\"Description\\\"\\u003e \\u003cp\\u003eArtificial Intelligence\\u003c/p\\u003e \\u003c/div\\u003e \\u003c/div\\u003e \\u003cdiv class=\\\"DefinitionListEntry\\\"\\u003e \\u003cdiv class=\\\"Term\\\"\\u003eSCT\\u003c/div\\u003e \\u003cdiv class=\\\"Description\\\"\\u003e \\u003cp\\u003eScript Concordance Test\\u003c/p\\u003e \\u003c/div\\u003e \\u003c/div\\u003e \\u003c/div\\u003e\"},{\"header\":\"Declarations\",\"content\":\"\\u003cp\\u003e\\u003cstrong\\u003eAuthor contribution\\u003c/strong\\u003e\\u003c/p\\u003e\\n\\u003cp\\u003eWZ Liu: Data analysis, Manuscript writing and editing;\\u003c/p\\u003e\\n\\u003cp\\u003eKN Lu: Data collection and analysis;\\u003c/p\\u003e\\n\\u003cp\\u003eZJ Yan: Revision of manuscript;\\u003c/p\\u003e\\n\\u003cp\\u003eJH Qian: Protocol, project development.\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eEthics approval and consent to participate:\\u003c/strong\\u003e The study (involving humans) was performed in accordance with the Declaration of Helsinki. Ethical approval was granted by the Ethics Committee of the First Affiliated Hospital of NingBo University. Informed consent to participate in the study was obtained from all the subjects.\\u0026nbsp;\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eConsent for publication:\\u003c/strong\\u003e Not applicable.\\u0026nbsp;\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eCompeting interests:\\u003c/strong\\u003e The authors declare no competing interests.\\u0026nbsp;\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eAvailability of Data and Materials:\\u0026nbsp;\\u003c/strong\\u003eThe datasets generated and/or analysed during the current study are not publicly available due to an agreement with the subjects but are available from the corresponding author on reasonable request.\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eClinical trial number:\\u003c/strong\\u003e Not applicable.\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eFunding Information: \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp; \\u0026nbsp;\\u0026nbsp;\\u003c/strong\\u003e\\u003c/p\\u003e\\n\\u003cp\\u003e1. Ningbo Clinical Research Center for Urological Disease, NO.2019A21001;\\u003c/p\\u003e\\n\\u003cp\\u003e2. Ningbo Top Medical and Health Research Program, No.2022020203;\\u003c/p\\u003e\\n\\u003cp\\u003e3. Zhejiang Engineering Research Center of Innovative technologies and diagnostic and therapeutic equipment for urinary system diseases.\\u003c/p\\u003e\"},{\"header\":\"References\",\"content\":\"\\u003col\\u003e\\u003cli\\u003e\\u003cspan\\u003eBruen C, Illing J, Daly R, et al. Medical student experiences of Case-Based Learning (CBL) at a multicultural medical school. BMC Med Educ. 2025;25(1):152. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1186/s12909-024-06585-7\\u003c/span\\u003e\\u003cspan address=\\\"10.1186/s12909-024-06585-7\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e. Published 2025 Jan 30.\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eYue J, Shang Y, Cui H et al. Visualization analysis of CBL application in Chinese and international medical education based on big data mining. BMC Med Educ. 2025;25(1):402. Published 2025 Mar 19. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1186/s12909-025-06933-1\\u003c/span\\u003e\\u003cspan address=\\\"10.1186/s12909-025-06933-1\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eYu Z, Zhao Z, Chen X, et al. Effects of standardised patients (SP) combined with case-based learning (CBL) in Chinese clinical education: a systematic review and meta-analysis. BMJ Open. 2025;15(9):e095705. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1136/bmjopen-2024-095705\\u003c/span\\u003e\\u003cspan address=\\\"10.1136/bmjopen-2024-095705\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e. Published 2025 Sep 3.\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eLiu R, Lin J, Chen X et al. From challenge to competence: the role of learning engagement in mediating stress and performance among clinical medical students in English-medium dental education. Front Med (Lausanne). 2025;12:1675855. Published 2025 Sep 10. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.3389/fmed.2025.1675855\\u003c/span\\u003e\\u003cspan address=\\\"10.3389/fmed.2025.1675855\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eAster A, Laupichler MC, Rockwell-Kollmann T, et al. ChatGPT and Other Large Language Models in Medical Education - Scoping Literature Review. Med Sci Educ. 2024;35(1):555\\u0026ndash;67. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s40670-024-02206-6\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s40670-024-02206-6\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e. Published 2024 Nov 13.\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eXu T, Weng H, Liu F, et al. Current Status of ChatGPT Use in Medical Education: Potentials, Challenges, and Strategies. J Med Internet Res. 2024;26:e57896. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.2196/57896\\u003c/span\\u003e\\u003cspan address=\\\"10.2196/57896\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e. Published 2024 Aug 28.\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eRao SJ, Isath A, Krishnan P et al. ChatGPT: A Conceptual Review of Applications and Utility in the Field of Medicine. J Med Syst. 2024;48(1):59. Published 2024 Jun 5. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s10916-024-02075-x。\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s10916-024-02075-x。\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eMeng X, Yan X, Zhang K, et al. The application of large language models in medicine: A scoping review. iScience. 2024;27(5):109713. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.isci.2024.109713。\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.isci.2024.109713。\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e. Published 2024 Apr 23.\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eChow M, Ng O. Beyond Chatbots: Moving Toward Multistep Modular AI Agents in Medical Education. JMIR Med Educ. 2025;11:e76661. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.2196/7666\\u003c/span\\u003e\\u003cspan address=\\\"10.2196/7666\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e. Published 2025 Oct 2.\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eShaw K, Henning MA, Webster CS. Artificial Intelligence in Medical Education: a Scoping Review of the Evidence for Efficacy and Future Directions. Med Sci Educ. 2025;35(3):1803\\u0026ndash;16. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s40670-025-02373-0\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s40670-025-02373-0\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e. Published 2025 Apr 2.\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eLi X, Yan X, Lai H. The ethical challenges in the integration of artificial intelligence and large language models in medical education: A scoping review. PLoS One. 2025;20(10):e0333411. Published 2025 Oct 22. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1371/journal.pone.0333411\\u003c/span\\u003e\\u003cspan address=\\\"10.1371/journal.pone.0333411\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003ePreiksaitis C, Rose C. Opportunities, Challenges, and Future Directions of Generative Artificial Intelligence in Medical Education: Scoping Review. JMIR Med Educ. 2023;9:e48785. Published 2023 Oct 20. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.2196/48785\\u003c/span\\u003e\\u003cspan address=\\\"10.2196/48785\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003ePatino GA, Amiel JM, Brown M, et al. The Promise and Perils of Artificial Intelligence in Health Professions Education Practice and Scholarship. Acad Med. 2024;99(5):477\\u0026ndash;81. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1097/ACM.0000000000005636\\u003c/span\\u003e\\u003cspan address=\\\"10.1097/ACM.0000000000005636\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e.\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eLiu H, Azam M, Bin Naeem S, et al. An overview of the capabilities of ChatGPT for medical writing and its implications for academic integrity. Health Info Libr J. 2023;40(4):440\\u0026ndash;6. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1111/hir.12509\\u003c/span\\u003e\\u003cspan address=\\\"10.1111/hir.12509\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e.\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eSu JM, Hsu SY, Fang TY, et al. Developing and validating a knowledge-based AI assessment system for learning clinical core medical knowledge in otolaryngology. Comput Biol Med. 2024;178:108765. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.compbiomed.2024.108765\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.compbiomed.2024.108765\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e.\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eFrancis NJ, Jones S, Smith DP. Generative AI in Higher Education: Balancing Innovation and Integrity. Br J Biomed Sci. 2025;81:14048. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.3389/bjbs.2024.14048\\u003c/span\\u003e\\u003cspan address=\\\"10.3389/bjbs.2024.14048\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e. Published 2025 Jan 9.\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eCurrie GM. Academic integrity and artificial intelligence: is ChatGPT hype, hero or heresy? Semin Nucl Med. 2023;53(5):719\\u0026ndash;30. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1053/j.semnuclmed.2023.04.008\\u003c/span\\u003e\\u003cspan address=\\\"10.1053/j.semnuclmed.2023.04.008\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e.\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eGreengrass C. Navigating the AI Revolution in Medicine-Adopting Strategies for Medical Education. Med Sci Educ. 2024;35(2):1055\\u0026ndash;61. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s40670-024-02257-9\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s40670-024-02257-9\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e. Published 2024 Dec 27.\\u003c/span\\u003e\\u003c/li\\u003e\\u003c/ol\\u003e\"},{\"header\":\"Tables\",\"content\":\"\\u003ctable border=\\\"1\\\" cellspacing=\\\"0\\\" cellpadding=\\\"0\\\"\\u003e\\n \\u003ctbody\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd colspan=\\\"5\\\" style=\\\"width: 568px;\\\"\\u003e\\n \\u003cp\\u003eTable.1 Basic Characteristics of Students\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd colspan=\\\"2\\\" style=\\\"width: 165px;\\\"\\u003e\\n \\u003cp\\u003eItems\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 155px;\\\"\\u003e\\n \\u003cp\\u003eChatGPT-assisted CBL\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 117px;\\\"\\u003e\\n \\u003cp\\u003eTraditional CBL\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 132px;\\\"\\u003e\\n \\u003cp\\u003estatistic, p\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd rowspan=\\\"2\\\" style=\\\"width: 82px;\\\"\\u003e\\n \\u003cp\\u003eGender\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 82px;\\\"\\u003e\\n \\u003cp\\u003eMale\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 155px;\\\"\\u003e\\n \\u003cp\\u003e15\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 117px;\\\"\\u003e\\n \\u003cp\\u003e17\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd rowspan=\\\"2\\\" style=\\\"width: 132px;\\\"\\u003e\\n \\u003cp\\u003ex\\u003csup\\u003e2\\u003c/sup\\u003e=0.25, p=0.61\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 82px;\\\"\\u003e\\n \\u003cp\\u003eFemale\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 155px;\\\"\\u003e\\n \\u003cp\\u003e17\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 117px;\\\"\\u003e\\n \\u003cp\\u003e15\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd colspan=\\\"2\\\" style=\\\"width: 165px;\\\"\\u003e\\n \\u003cp\\u003eKnowledge-Pre\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 155px;\\\"\\u003e\\n \\u003cp\\u003e11.1\\u0026plusmn;1.7\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 117px;\\\"\\u003e\\n \\u003cp\\u003e11.2\\u0026plusmn; 2.0\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 132px;\\\"\\u003e\\n \\u003cp\\u003et=-0.20, p=0.42\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd colspan=\\\"2\\\" style=\\\"width: 165px;\\\"\\u003e\\n \\u003cp\\u003eReasoning-Pre\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 155px;\\\"\\u003e\\n \\u003cp\\u003e32.3\\u0026plusmn;3.5\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 117px;\\\"\\u003e\\n \\u003cp\\u003e31.9\\u0026plusmn;2.4\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 132px;\\\"\\u003e\\n \\u003cp\\u003et=0.63, p=0.27\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003c/tbody\\u003e\\n\\u003c/table\\u003e\\n\\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n\\u003ctable border=\\\"1\\\" cellspacing=\\\"0\\\" cellpadding=\\\"0\\\"\\u003e\\n \\u003ctbody\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd colspan=\\\"5\\\" style=\\\"width: 568px;\\\"\\u003e\\n \\u003cp\\u003eTable.2 Assessment of students\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd colspan=\\\"2\\\" style=\\\"width: 164px;\\\"\\u003e\\n \\u003cp\\u003eItems\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003eChatGPT-assisted CBL\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003eTraditional CBL\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003estatistic, p\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd colspan=\\\"2\\\" style=\\\"width: 164px;\\\"\\u003e\\n \\u003cp\\u003eKnowledge-Post\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e17.4\\u0026plusmn;1.0\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e16.8\\u0026plusmn;1.3\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=2.1, p=0.02\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd colspan=\\\"2\\\" style=\\\"width: 164px;\\\"\\u003e\\n \\u003cp\\u003eReasoning-Post\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e46.0\\u0026plusmn;2.6\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e43.2\\u0026plusmn;2.0\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=4.8, p\\u0026lt;0.01\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd colspan=\\\"2\\\" style=\\\"width: 164px;\\\"\\u003e\\n \\u003cp\\u003eClinical ability\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e32.9\\u0026plusmn;3.5\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e27.0\\u0026plusmn;4.2\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=6.1, p\\u0026lt;0.01\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eMedical history\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e7.2\\u0026plusmn;1.0\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e5.3\\u0026plusmn;1.4\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=6.4, p\\u0026lt;0.01\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eAnalyze of examination\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e5.8\\u0026plusmn;1.1\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e5.8\\u0026plusmn;1.5\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=0.1, p=0.46\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eDifferential diagnosis\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e5.3\\u0026plusmn;1.2\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e5.3\\u0026plusmn;1.4\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=0.1, p=0.46\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eTreatment strategy\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e7.1\\u0026plusmn;1.3\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e6.3\\u0026plusmn;1.4\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=2.4, p\\u0026lt;0.01\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eHumanistic care\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e7.5\\u0026plusmn;1.4\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e4.4\\u0026plusmn;1.7\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=8.0, p\\u0026lt;0.01\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd colspan=\\\"2\\\" style=\\\"width: 164px;\\\"\\u003e\\n \\u003cp\\u003eEnglish Presentation\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e34.2\\u0026plusmn;3.3\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e29.6\\u0026plusmn;4.2\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=4.8, p\\u0026lt;0.01\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eProfessional languages\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e5.4\\u0026plusmn;1.3\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e5.1\\u0026plusmn;1.4\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=1.1, p=0.14\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eContents\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e8.2\\u0026plusmn;1.0\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e6.7\\u0026plusmn;1.4\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=5.0, p\\u0026lt;0.01\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eLearning issues\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e6.1\\u0026plusmn;1.3\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e5.4\\u0026plusmn;1.7\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=1.9, p=0.03\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eFluently\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e6.1\\u0026plusmn;1.1\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e6.1\\u0026plusmn;1.3\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=-0.1, p=0.56\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eConfident\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e8.3\\u0026plusmn;1.0\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e6.3\\u0026plusmn;1.4\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=6.7, p\\u0026lt;0.01\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd colspan=\\\"2\\\" style=\\\"width: 164px;\\\"\\u003e\\n \\u003cp\\u003eSelf-assessment\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e38.3\\u0026plusmn;3.0\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e31.1\\u0026plusmn;3.0\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=9.6, p\\u0026lt;0.01\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eUnderstanding\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e8.2\\u0026plusmn;1.3\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e7.2\\u0026plusmn;1.0\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=3.4, p\\u0026lt;0.01\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eUseful for medical learning\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e7.3\\u0026plusmn;1.7\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e4.4\\u0026plusmn;1.7\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=6.9, p\\u0026lt;0.01\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eUseful for professional English learning\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e8.3\\u0026plusmn;0.7\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e8.1\\u0026plusmn;0.4\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=1.2, p=0.11\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eRecommendation for EMI study\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e7.6\\u0026plusmn;0.5\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e6.2\\u0026plusmn;0.6\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=10.4, p\\u0026lt;0.01\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003ctr\\u003e\\n \\u003ctd style=\\\"width: 52px;\\\"\\u003e\\n \\u003cp\\u003e\\u0026nbsp;\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 113px;\\\"\\u003e\\n \\u003cp\\u003eSatisfaction\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 147px;\\\"\\u003e\\n \\u003cp\\u003e7.3\\u0026plusmn;1.0\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 121px;\\\"\\u003e\\n \\u003cp\\u003e5.3\\u0026plusmn;1.4\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003ctd style=\\\"width: 137px;\\\"\\u003e\\n \\u003cp\\u003et=6.7, p\\u0026lt;0.01\\u003c/p\\u003e\\n \\u003c/td\\u003e\\n \\u003c/tr\\u003e\\n \\u003c/tbody\\u003e\\n\\u003c/table\\u003e\\n\"}],\"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\":\"info@researchsquare.com\",\"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\":\"Artificial intelligence, ChatGPT, case-based learning, English-medium instruction, medical education, benign prostatic hyperplasia\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-7944588/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-7944588/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003ch2\\u003eBackground\\u003c/h2\\u003e \\u003cp\\u003eCase-Based Learning (CBL) was widely used in medical education to develop clinical reasoning and knowledge application. However, English-Medium Instruction (EMI) environments presented additional linguistic and cognitive challenges. The emergence of large language models such as ChatGPT offered new opportunities to enhance both disciplinary and language learning. This study evaluated the educational impact of ChatGPT-assisted CBL in teaching benign prostatic hyperplasia to EMI medical students.\\u003c/p\\u003e\\u003ch2\\u003eMethods\\u003c/h2\\u003e \\u003cp\\u003eA cluster-randomized controlled trial was conducted among 64 undergraduate medical students enrolled in an EMI urology course. Participants were assigned to either a ChatGPT-assisted CBL group or a traditional CBL group. The AI-assisted group used ChatGPT to generate patient cases, clarify medical terminology, provide reasoning prompts, and summarize key learning points. Outcomes included knowledge acquisition, clinical reasoning, English communication performance, and learning satisfaction. Quantitative data were analyzed using paired and independent t-tests and ANCOVA, while qualitative data from interviews were thematically analyzed.\\u003c/p\\u003e\\u003ch2\\u003eResults\\u003c/h2\\u003e \\u003cp\\u003eBefore the intervention, no significant differences were found between the ChatGPT-assisted CBL and traditional CBL groups (all p\\u0026thinsp;\\u0026gt;\\u0026thinsp;0.05). After four weeks, the ChatGPT-assisted group showed significantly greater improvements in knowledge, clinical reasoning, and overall clinical ability (all p\\u0026thinsp;\\u0026lt;\\u0026thinsp;0.05). They also achieved higher scores in English presentation, confidence, and self-assessment, with greater satisfaction and perceived usefulness for medical and EMI learning. These findings indicated that AI-assisted CBL enhanced students\\u0026rsquo; learning outcomes and engagement.\\u003c/p\\u003e\\u003ch2\\u003eConclusion\\u003c/h2\\u003e \\u003cp\\u003eAI-assisted CBL effectively improved students\\u0026rsquo; knowledge acquisition, clinical reasoning, communication, and engagement in EMI medical education. Integrating ChatGPT into CBL provided a supportive and interactive learning environment, demonstrating its potential as an innovative educational tool when applied with appropriate guidance and supervision.\\u003c/p\\u003e\",\"manuscriptTitle\":\"AI-Driven Case-Based Learning for English-Medium Medical Students: Applications in Teaching Benign Prostatic Hyperplasia\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2026-01-22 10:30:09\",\"doi\":\"10.21203/rs.3.rs-7944588/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"27e10a95-70aa-49de-a9ac-ea17e7f3ad4f\",\"owner\":[],\"postedDate\":\"January 22nd, 2026\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"posted\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2026-01-27T04:39:52+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2026-01-22 10:30:09\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-7944588\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-7944588\",\"identity\":\"rs-7944588\",\"version\":[\"v1\"]},\"buildId\":\"XKTyCvWXoU3ODBz1xrDgd\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}