- Visibility 259 Views
- Downloads 218 Downloads
- Permissions
- DOI 10.18231/j.jeths.v.12.i.2.3
-
CrossMark
Utility of generative AI for a medical teacher: Adopting LLMs in practice
- Author Details:
-
Devi Prasad Mohapatra
-
Madhusmita Mohanty Mohapatra *
Devi Prasad Mohapatra
Madhusmita Mohanty Mohapatra *
Background: Generative AI (Artificial Intelligence), particularly Large Language Models (LLMs), have emerged as transformative tools in medical education since the release of ChatGPT by OpenAI in November 2022. These models, including Gemini by Google, Claude by Anthropic, and others, excel at generating coherent text responses and have demonstrated advanced reasoning abilities. They are capable of tasks such as answering questions, summarizing documents, translating languages, drafting clinical case studies and generating images.
Materials and Methods: This is a narrative review exploring the utility of Generative AI LLMs in medical education enhanced by personal experience and supported by literature. We present a qualitative, experiential, and thematic approach, including theoretical perspectives with practical applications observed over the last two years and three months from December 2022 to March 2025.
Results: Multiple databases were explored and selective manuscripts were identified to understand broad use cases for medical educators as well as adoption of these models in non-biomedical domains. A thematic framework was used to organize our observations and literature into four key domains of LLM usage in medical education: (1) Automated Content Synthesis, (2) Automation of Routine Tasks, (3) Assistance in Teaching and Research, and (4) Accessibility Enhancement.
Discussion: The enthusiasm to understand the potential of LLMs for potentially transforming medical training, it's important to critically assess their role in education, acknowledging both their benefits and limitations. LLM-based chatbots like ChatGPT (GPT-4) have demonstrated advanced reasoning and language abilities, achieving scores at or near the passing threshold of the United States Medical Licensing Examination (USMLE) without medical-specific tuning. Various models have been released so far varying in scale and training, but all share the core capability of generating conversational human-like content on demand.
Conclusion: Generative AI is an exciting area under development with potential to revolutionize the landscape of medical education by shifting the traditional mode of information delivery to AI-driven student-centred practices. Medical teachers gain new relevance in this changing landscape. Generative AI can become a powerful tool in medical education through collaboration among educators, learners, AI developers, and policymakers, promoting innovative and human-centered training for future physicians.
References
- Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need [Internet]. 2017 Available from: https://arxiv.org/pdf/1706.03762.
- Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, Aleman FL, et al. Gpt-4 technical report [Internet]. 2023 Available from: https://arxiv.org/abs/2303.08774.
- Lang G, Triantoro T, Sharp JH. Large language models as AI- powered educational assistants: comparing GPT-4 and Gemini for writing teaching cases. J Inf Syst Educ. 2024;35(3):390–407.
- Safranek CW, Sidamon-Eristoff AE, Gilson A, Chartash D. The role of large language models in medical education: applications and implications. JMIR Med Educ. 2023;9:e50945.
- Janumpally R, Nanua S, Ngo A, Youens K. Generative artificial intelligence in graduate medical education. Front Med (Lausanne). 2025;11:1525604.
- Mohapatra DP, Thiruvoth FM, Tripathy S, Rajan S, Vathulya M, Lakshmi P, et al. Leveraging large language models (LLM) for the plastic surgery resident training: do they have a role? Indian J Plast Surg. 2023;56(5):413–20.
- Abd-Alrazaq A, AlSaad R, Alhuwail D, Ahmed A, Healy PM, Latifi S, et al. Large language models in medical education: opportunities, challenges, and future directions. JMIR Med Educ. 2023;9:e48291.
- Lucas HC, Upperman JS, Robinson JR. A systematic review of large language models and their implications in medical education. Med Educ. 2024;58(11):1276–85.
- Hamad ZT, Jamil N, Belkacem AN. ChatGPT’s impact on education and healthcare: insights, challenges, and ethical consideration. IEEE Access. 2024;12:114858–77.
- Mohapatra DP, Thiruvoth FM, Tripathy S, Rajan S, Vathulya M, Lakshmi P, et al. Leveraging large language models (LLM) for the plastic surgery resident training: do they have a role? Indian J Plast Surg. 2023;56(5):413–20.
- Chatgpt. (n.d.). Retrieved 19 April 2025, Available from https://openai.com/chatgpt/overview/
- Introducing Gemini: Our largest and most capable AI model. (2023, December 6). Google. https://blog.google/technology/ai/google-gemini-ai/
- Meet Claude. (n.d.). https://www.anthropic.com/claude. Retrieved April 19, 2025, from https://www.anthropic.com/claude
- Deepseek-ai(Deepseek). (2025, March 27). https://huggingface.co/deepseek-ai
- Mistral ai | frontier ai in your hands. (n.d.). Retrieved 19 April 2025, from https://mistral.ai/
- Llama 4: Leading intelligence. Unrivaled speed and efficiency. (n.d.). https://www.llama.com/. Retrieved February 19, 2025, from https://www.llama.com/
- AI for all humanity. (n.d.). https://x.ai/. Retrieved April 19, 2025, from https://x.ai/
- DALL·E 3. (n.d.). Retrieved 19 April 2025, from https://openai.com/index/dall-e-3/
- Stability ai. (2025, April 16). Stability AI. https://stability.ai
- Midjourney. (n.d.). Midjourney. https://www.midjourney.com/home
- Sora | openai. (n.d.). Retrieved 19 April 2025, from https://openai.com/sora/
- Veo 2. (2025, April 17). Google DeepMind. https://deepmind.google/technologies/veo/veo-2/
- Parente DJ. Generative artificial intelligence and large language models in primary care medical education. Fam Med. 2024;56(9):534–40.
- Horsey J. Write powerful AI prompts using the CRAFT framework [Internet]. Geeky Gadgets; 2024 Jul 14. Available from: https://www.geeky-gadgets.com/ai-prompt-writing/.
- Brexhq/prompt-engineering. [Computer software]. 2025. Available from: https://github.com/brexhq/prompt-engineering (Original work published 2023)
- The art of ai prompt crafting: A comprehensive guide for enthusiasts. (2023, November 11). OpenAI Developer Community. Available from: https://community.openai.com/t/the-art-of-ai-prompt-crafting- a-comprehensive-guide-for-enthusiasts/495144
- Xiao, D. (n.d.). Research guides: Ai-based literature review tools: how to craft prompts. Retrieved 19 April 2025, Available from: https://tamu.libguides.com/c.php?g=1289555&p=9642751
- Wen H, Li Y, Liu G, Zhao S, Yu T, Li T, et al. Empowering LLM to use smartphone for intelligent task automation [Internet]. 2023 Available from: https://arxiv.org/abs/2308.15272.
- Steinert S, Avila KE, Ruzika S, Kuhn J, Küchemann S. Harnessing large language models to develop research-based learning assistants for formative feedback. Smart Learn Environ. 2024;11:62. Mohapatra and Mohapatra / Journal of Education Technology in Health Sciences 2025;12(2):41–49 49
- Hu B, Zhu J, Pei Y, Gu X. Exploring the potential of LLM to enhance teaching plans through teaching simulation. NPJ Sci Learn. 2025;10(1):7.
- Chiang CH, Chen WC, Kuan CY, Yang C, Lee H. Large language model as an assignment evaluator: insights, feedback, and challenges in a 1000+ student course [Internet]. 2024 [cited 2025 Mar 31]. Available from: https://arxiv.org/abs/2407.05216.
- Seo H, Hwang T, Jung J, Kang H, Namgoong H, Lee Y, et al. Large language models as evaluators in education: verification of feedback consistency and accuracy. Appl Sci. 2025;15(2):671.
- Cohn C, Hutchins N, Le T. A chain-of-thought prompting approach with LLMs for evaluating students’ formative assessment responses in science. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38:23182–90. doi:10.1609/aaai.v38i21.30364
[Google Scholar] - Introducing gpts. (2024, March 13). https://openai.com/index/introducing-gpts/
- Google notebooklm | note taking & research assistant powered by ai. (n.d.). Retrieved 19 April 2025, from https://notebooklm.google/
- Weidener L, Fischer M. Teaching AI ethics in medical education: a scoping review of current literature and practices. Perspect Med Educ. 2023;12(1):399–410.
- Busch F, Adams LC, Bressem KK. Biomedical ethical aspects towards the implementation of artificial intelligence in medical education. Med Sci Educ. 2023;33(4):1007–12.
- Alam F, Lim MA, Zulkipli IN. Integrating AI in medical education: embracing ethical usage and critical understanding. Front Med (Lausanne). 2023;10:1279707.
- Weidener L, Fischer M. Proposing a principle-based approach for teaching AI ethics in medical education. JMIR Med Educ. 2024;10:e55368.
- Dijkstra P, Greenhalgh T, Mekki YM, Morley J. How to read a paper involving artificial intelligence (AI). BMJ Med. 2025;4:e001394.