Effect of Generative Artificial Intelligence Use on Diagnostic Learning in Medical Students: A Quasi-Experimental Study
DOI:
https://doi.org/10.56294/saludcyt20251564Keywords:
generative artificial intelligence, clinical reasoning, diagnostic learning, medical education, quasi-experimental studyAbstract
Generative artificial intelligence (GenAI) has emerged as a transformative tool in medical education, particularly in the development of diagnostic learning and clinical reasoning skills. This study aimed to examine the effect of GenAI use on diagnostic learning among medical students through a quasi-experimental pretest–posttest design. A total of 62 students participated, assigned to an experimental group that used GenAI to solve clinical cases and a control group that relied on traditional study methods. Findings showed a markedly greater improvement in the experimental group, which achieved higher gains in diagnostic accuracy, quality of reasoning and reduced case-resolution time. Students' perceptions were highly positive, emphasising the usefulness, clarity and cognitive support offered by GenAI. Although moderate risks of error were identified, they did not significantly affect the overall evaluation of the tool. The study concludes that generative AI significantly enhances diagnostic learning and strengthens essential clinical competencies, provided its implementation occurs within an appropriate ethical and pedagogical framework. These results open new avenues for research regarding curriculum integration, impact on more complex clinical scenarios and its potential as an intelligent tutoring resource in contemporary medical education.
References
1. World Health Organization. Ethics and governance of artificial intelligence for health. Geneva: WHO; 2021.
2. UNESCO. Artificial Intelligence in Education: Challenges and Opportunities. Paris: UNESCO; 2021.
3. Kung TH, Cheatham M, Medenilla A, et al. Performance of ChatGPT on USMLE: Potential for AI-assisted medical education. PLOS Digit Health. 2023;2(2):e0000198. doi:10.1371/journal.pdig.0000198 DOI: https://doi.org/10.1371/journal.pdig.0000198
4. Gilson A, Safranek CW, Huang T, et al. How Does ChatGPT Perform on the United States Medical Licensing Examination? JMIR Med Educ. 2023;9:e45312. doi:10.2196/45312 DOI: https://doi.org/10.2196/45312
5. Chen CY, Chou YH, Lee CC. Performance of ChatGPT and Bard on the medical licensing examination: a comparative study. BMC Med Educ. 2024;24:6309. doi:10.1186/s12909-024-06309-x DOI: https://doi.org/10.1186/s12909-024-06309-x
6. Yanagita T, Takagi S, Tokumasu K, et al. Accuracy of ChatGPT on Medical Questions in the National Medical Licensing Examination in Japan. JMIR Form Res. 2023;7:e48023. doi:10.2196/48023 DOI: https://doi.org/10.2196/48023
7. Liu X, Wu J, Ge Y. Performance of ChatGPT across different versions in medical licensing examinations. NPJ Digit Med. 2024;7:45. DOI: https://doi.org/10.2196/60807
8. Schmidt HG, Boshuizen HPA. On the origin of intermediate effects in clinical reasoning. Med Educ. 1993;27(5):422–432.
9. Norman G. Building expertise in clinical reasoning. Med Educ. 2005;39(1):98–106. DOI: https://doi.org/10.1111/j.1365-2929.2004.01972.x
10. Croskerry P. Diagnostic failure: A cognitive and affective approach. BMJ Qual Saf. 2013;22(Suppl 2):ii23–ii28. DOI: https://doi.org/10.1136/bmjqs-2012-001622
11. Graber ML. The incidence of diagnostic error in medicine. BMJ Qual Saf. 2013;22(2):ii21–ii27. DOI: https://doi.org/10.1136/bmjqs-2012-001615
12. Topol E. Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again. New York: Basic Books; 2019.
13. Shadish WR, Cook TD, Campbell DT. Experimental and Quasi‑Experimental Designs for Generalized Causal Inference. Boston: Houghton-Mifflin; 2002.
14. Hernández-Sampieri R, Mendoza C. Metodología de la Investigación. 7th ed. México DF: McGraw‑Hill; 2021.
15. DeVellis RF. Scale Development: Theory and Applications. 4th ed. Thousand Oaks: Sage; 2016.
16. Nunnally JC, Bernstein IH. Psychometric Theory. 3rd ed. New York: McGraw-Hill; 1994.
17. Field A. Discovering Statistics Using SPSS. 5th ed. London: Sage; 2018.
18. Rao AA, Pang T, et al. Evaluating the educational impact of generative AI in clinical reasoning tasks. Med Educ Online. 2024;29(1):e22914.
19. Lee J, Kim D, Cho Y. Acceleration of diagnostic decision-making using large language models. Digit Health. 2024;10:1–12.
20. Aydin A, Kara B, Colak C. Diagnostic performance of GPT‑4 in clinical case analysis: A comparative study. Front Artif Intell. 2024;7:145829.
21. Huang Y, Chen L, Wu J. Student perceptions of AI‑supported clinical reasoning learning. BMC Med Educ. 2024;24:112.
22. Khan S, Omari A. Critical student engagement with AI tools in medical training. J Med Educ Curric Dev. 2024;11:1–9.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Johanna Nathaly Hidalgo Guevara, Alexander Ismael Hidalgo Guevara (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
