[1] | Hswen, Y. and Abbasi, J. (2023). AI will-and should-change medical school, says Harvard's dean for medical education. JAMA 330(19): 1820−1823. DOI: 10.1001/jama.2023.19295. |
[2] | Abd-Alrazaq, A., AlSaad, R., Alhuwail, D., et al. (2023). Large language models in medical education: Opportunities, challenges, and future directions. JMIR Med Educ 9: e48291. DOI: 10.2196/48291. |
[3] | Vaswani, A., Shazeer, N., Parmar, N., et al. (2017). Attention is all you need. 31st Conference on Neural Information Processing Systems, Long Beach, CA, USA. https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf. |
[4] | Han, Z., Battaglia, F., Udaiyar, A., et al. (2023). An explorative assessment of ChatGPT as an aid in medical education: Use it with caution. Med Teach 20: 1−8. DOI: 10.1080/0142159X.2023.2271159. |
[5] | Sallam, M. (2023). ChatGPT utility in healthcare education, research, and practice: Systematic review on the promising perspectives and valid concerns. Healthcare 11(6): 887. DOI: 10.3390/healthcare11060887. |
[6] | Dahl, M., Magesh, V., Suzgun, M., et al. (2024). Large legal fictions: profiling legal hallucinations in large language models. ArXiv. DOI: https://arxiv.org/abs/2401.01301v1. |
Han Z., Battaglia F., and (2024). Transforming challenges into opportunities: Leveraging ChatGPT'slimitations for active learning and prompt engineering skill. The Innovation Medicine 2(2): 100065. https://doi.org/10.59717/j.xinn-med.2024.100065 |
ChatGPT has certain inherent limitations when responding to questions from users. However, medical educators can leverage these limitations to develop activities to engage students in critical and active learning as well as developing their “prompt engineering” skills.