Accepted for/Published in: JMIR Medical Education
Date Submitted: May 29, 2026
Date Accepted: Oct 13, 2026
Date Submitted to PubMed: Oct 14, 2026
Curriculum-Aligned Conversational AI to Support Pathology Self-Directed Learning in Preclinical Medical Students: A Crossover Randomized Pilot Study
ABSTRACT
Background:
Artificial intelligence (AI) is reshaping the landscape of medical education, yet the widespread adoption of general-purpose AI tools in student learning raises substantial concerns about curricular alignment, information accuracy, and the absence of pedagogical scaffolding.
Objective:
This crossover pilot study evaluated a curriculum-aligned custom GPT tool that was developed to support Socratic, case-based, self-directed learning (SDL) against traditional preparation methods in second-year medical students at the University of South Carolina, Floyd School of Medicine (USCFSOM).
Methods:
Forty-four voluntary participants participated in two faculty-led pathology small group discussions (on the topics of Cushing's disease and prostate cancer) using the custom GPT or conventional resources, then switched methods for the second case. Faculty assessed SDL documentation forms and small group discussion performance using validated rubrics.
Results:
Students using the curriculum-aligned custom GPT tool achieved significantly higher SDL rubric scores (10.27 vs. 9.36 out of 12; p < 0.0001, Cohen's d = 0.71) and small group discussion scores (14.89 vs. 13.68 out of 16; p < 0.0001, Cohen's d = 0.78), with large effect sizes. They also demonstrated a borderline-significant advantage in delayed NBME-style retention (Wilcoxon signed-rank p = 0.052; paired t-test p = 0.048) and significantly greater self-reported gains in understanding and pathophysiological reasoning. Seventy-seven percent reported improved reasoning clarity, and 70% improved conceptual understanding. Safety analysis revealed minimal risk across five domains. Low performers showed the greatest retention benefit.
Conclusions:
These findings support the integration of curriculum-aligned custom GPTs into second-year pathology SDL curricula and provide evidence that curriculum-aligned AI tools can safely and effectively enhance self-directed learning, clinical reasoning, and learner engagement in undergraduate medical education. Clinical Trial: NA
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.