Preserving Scientific Reasoning in Generative AI-Assisted Learning: A Proposed RPVR Framework for Basic Medical Sciences Education

Integration of generative artificial intelligence (GenAI) in higher education offers substantial opportunities for personalised education that tailors to the needs, interests and learning of each student. However, unrestricted reliance on GenAI has been found to be a source of academic stress and is associated with low self-esteem. Moreover, in subjects that require students to develop critical thinking or scientific reasoning, such as basic medical sciences (BMS), high dependence on AI may limit students’ opportunities to engage in independent knowledge construction and critical evaluation. This concept paper proposes an integration of GenAI into BMS education through the Reason–Prompt–Verify–Reconstruct (RPVR) framework. The framework’s approach is at both the learner and educator levels, with the main aims of preserving active scientific reasoning. Comprises of four sequential stages: Reason, stage where learners independently analyse a problem and formulate an initial explanation before using GenAI; Prompt, a stage where the use of GenAI is allow to challenge, clarify, or extend the learner’s reasoning; Verify, stage which requires critical appraisal of AI-generated information against standard academic and scientific sources; and Reconstruct, where learners identify misconceptions, reflect their understanding independently, and transfer the verified concept to a novel problem. Problem-based learning (PBL) is proposed to illustrate the implementation of RPVR, using a sequence of AI-off–AI-on–verification–AI-off to ensure that learners generate initial hypotheses before AI integration and subsequently demonstrate understanding through explanation, mechanistic reconstruction, and transfer to unfamiliar scenarios. As physiology strongly depends on causal and mechanistic reasoning, this subject is used as the primary illustrative discipline, while the framework is potentially transferable to any other BMS disciplines. By repositioning GenAI from an answer-generating tool, RPVR aims to promote adaptive cognitive offloading and broaden the use of AI in higher education. Future empirical studies should evaluate whether RPVR-guided GenAI use, particularly within PBL, improves reasoning, knowledge transfer, and learning outcomes compared with unstructured GenAI-assisted learning.

AI-assisted learning; basic medical sciences education; problem-based learning; physiology education.

1. Acar, O. A. (2023). Are Your Students Ready for AI? A Four-Step Framework to Prepare Learners for a ChatGPT World. Harvard Business Publishing Education. https://hbsp.harvard.edu/inspiring-minds/are-your-students-ready-for-ai? [Google Scholar] [Crossref]

2. Basil, M., et al. (2026). A scoping review of the use of generative artificial intelligence tools in health profession education. BMC Medical Education, 26(1), 291. [Google Scholar] [Crossref]

3. Bloch, R. R., et al. (2025). Causal Mechanistic Reasoning as a Tool to Explore Medical Students’ Predictions of Pharmacology Phenomenon: Connecting Core Concepts with Clinical Applications. Medical Science Educator, 35(5), 2329-2342. [Google Scholar] [Crossref]

4. Cheng, D., Chan, E. Y. S., Song, Y., Cui, A., Chang, A., & Wang, W. (2026). Framework for AI integration into the undergraduate medical curricula: a scoping review. BMC medical education, 26(1), 465. https://doi.org/10.1186/s12909-026-08620-1 [Google Scholar] [Crossref]

5. Elsamanoudy, A., et al. (2026). Implementation and evaluation of customized artificial intelligence personal tutor (chat GPT physiology companion) for medical students in the reproduction module. BMC Medical Education, 26(1), 832. [Google Scholar] [Crossref]

6. Feigerlova, E., et al. (2025). A systematic review of the impact of artificial intelligence on educational outcomes in health professions education. BMC Medical Education, 25(1), 129. [Google Scholar] [Crossref]

7. Mengesha, Z., et al. (2026). ASPIRE: a pedagogical framework for integrating generative artificial intelligence in public health education. Paper presented at the Frontiers in Education. [Google Scholar] [Crossref]

8. Morales-Luque, C., et al. (2026). Problem-based learning promotes causal physiological reasoning in first-year medical students before formal cardiovascular instruction. Frontiers in Physiology, 17, 1897473. [Google Scholar] [Crossref]

9. Pham, T. D., et al. (2025). The impact of generative AI on health professional education: A systematic review in the context of student learning. Medical Education, 59(12), 1280-1289. doi:https://doi.org/10.1111/medu.15746 [Google Scholar] [Crossref]

10. Simoni, J., et al. (2025). Artificial intelligence in undergraduate medical education: an updated scoping review. BMC Medical Education, 25(1), 1609. [Google Scholar] [Crossref]

11. Su , J., & Yang , W. (2023). Unlocking the Power of ChatGPT: A Framework for Applying Generative AI in Education. ECNU Review of Education, 6(3), 355-366. doi:10.1177/20965311231168423 [Google Scholar] [Crossref]

12. Su, T., et al. (2025). The effectiveness of problem-based learning (PBL) in enhancing critical thinking skills in medical education: a systematic review and meta-analysis. Frontiers in Education, Volume 10 - 2025. doi:10.3389/feduc.2025.1565556 [Google Scholar] [Crossref]

13. Tong, X., et al. (2025). The application of problem-based learning (PBL) guided by ChatGPT in clinical education in the Department of Nephrology. BMC Medical Education, 25(1), 1048. doi:10.1186/s12909-025-07427-w [Google Scholar] [Crossref]

• Assessment of the Role of Artificial Intelligence in Repositioning TVET for Economic Development in Nigeria
• Teachers’ Use of Assure Model Instructional Design on Learners’ Problem Solving Efficacy in Secondary Schools in Bungoma County, Kenya
• “E-Booksan Ang Kaalaman”: Development, Validation, and Utilization of Electronic Book in Academic Performance of Grade 9 Students in Social Studies
• Analyzing EFL University Students’ Academic Speaking Skills Through Self-Recorded Video Presentation
• Major Findings of The Study on Total Quality Management in Teachers’ Education Institutions (TEIs) In Assam – An Evaluative Study