Currently submitted to: JMIR Medical Education
Date Submitted: Dec 29, 2025
Open Peer Review Period: Dec 31, 2025 - Feb 25, 2026
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
AI-Generated Interactive Podcast vs Traditional Reading for Journal Club Preparation: Randomized Crossover Trial
ABSTRACT
Background:
Traditional journal clubs are a staple of graduate medical education (GME) designed to foster critical appraisal skills. However, learner engagement is often hindered by time constraints and low reading compliance. Generative Artificial Intelligence (AI) offers novel modalities for content delivery, yet its utility in journal club preparation remains under-explored.
Objective:
This study aims to evaluate the feasibility, learner satisfaction, and knowledge acquisition of an AI-generated interactive audio overview (NotebookLM) compared to traditional reading-based preparation for resident journal clubs.
Methods:
We conducted a prospective, randomized crossover trial involving 60 participants from General Surgery and Internal Medicine. While the initial cohort included attendings and fellows, the primary paired analysis was restricted to the 28 residents who completed both arms of the study to focus on the primary learner group. Participants were randomized to two sequences: the traditional format (reading the full text) and the AI-assisted format (using NotebookLM to generate an interactive audio podcast and briefing document). Knowledge acquisition was assessed via a 5-point multiple-choice quiz. Learner satisfaction and perceptions of utility were measured using a 5-point Likert scale.
Results:
Sixty participants completed the baseline survey. Twenty-eight residents completed both arms of the crossover study. In this primary paired analysis, there were no significant differences in objective comprehension scores between the Traditional and NotebookLM arms (Traditional: 3.9 ± 1.1 vs. NotebookLM: 4.2 ± 1.0; P=.28). Participants reported comparable engagement (P=.97) and likelihood of applying findings (P=.33). Regarding critical appraisal, participants rated the traditional format numerically higher for understanding "limitations and biases" (Traditional: 3.4 ± 1.0 vs. NotebookLM: 3.1 ± 1.0), though this difference was not statistically significant in the paired cohort (P=.31). Notably, 89.2% of participants indicated they would use the NotebookLM tool for future journal clubs, and 54% found the AI-generated briefing document "very" or "extremely" helpful.
Conclusions:
The AI-generated NotebookLM interactive podcast proved to be a feasible and highly acceptable alternative to traditional reading, demonstrating non-inferiority in factual knowledge acquisition. While traditional methods may offer advantages for identifying study nuances, the high user acceptance of the AI tool suggests it is an effective "primer" to enhance efficiency for time-constrained trainees. Clinical Trial: Not Applicable
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.