Previously submitted to: JMIR Formative Research (no longer under consideration since Aug 18, 2025)
Date Submitted: Nov 1, 2024
Warning: This is an author submission that is not peer-reviewed or edited.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 Mnemonic Images Improve Long-Term Retention of Coronary Artery Occlusions in STEMI: A Comparative Study
ABSTRACT
Background:
Medical students often face challenges in retaining complex information about coronary artery occlusions when using traditional ECG diagrams. Visual mnemonics may enhance learning by making information more memorable and easier to recall.
Objective:
This study aimed to evaluate the effectiveness of artificial intelligence (AI)-generated mnemonic-based images overlayed on a 12-lead ECG in improving long-term retention and student preference compared to traditional ECG diagrams.
Methods:
Mnemonic images were created using DALLE-3 and refined for educational use. A comparative study was conducted with 275 first-year medical students across six campuses. Forty students in the experimental group (n=40) received lectures and mnemonic-based images, while 235 students in the control group received traditional ECG diagrams only (n=235). Exam performance was assessed using a weekly and final course exam, and student engagement was measured using the Situational Interest Survey for Multimedia (SIS-M) with a 78% response rate (n=31).
Results:
All control group sites showed a significant drop in successive exam scores which was not observed in the experimental group suggesting better long-term retention. Furthermore, experimental group students showed higher preference of the mnemonic images, as shown by high average scores for triggered situational interest (M = 4.685, SD = 0.432, p<.001), maintained interest (M = 4.60, SD = 0.48, p<.001), maintained-feeling interest (M = 4.459, SD = 0.616, p<.001), and maintained-value interest (M = 4.742, SD = 0.472, p=.006). Additionally, 80% of students in the experimental group preferred the mnemonic-based images over traditional ECG diagrams, indicating enhanced engagement and preference. Qualitative feedback highlighted increased impact on retention, engagement, and preference for the mnemonic images while also showing challenges related to difficulty understanding the images and timing of image presentation.
Conclusions:
The use of AI-generated mnemonic images improved student engagement, retention, and interest by leveraging the strengths of visual memory aids. These findings suggest that generative AI can be a valuable tool in creating effective mnemonic-based learning resources, with the potential to enhance outcomes in medical education.
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.