Elabd N, Rahman ZM, Abu Alinnin SI, Jahan S, Campos LA, Baltatu OC. Designing Personalized Multimodal Mnemonics With AI: A Medical Student's Implementation Tutorial.
JMIR MEDICAL EDUCATION 2025;
11:e67926. [PMID:
40341190 PMCID:
PMC12080963 DOI:
10.2196/67926]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/24/2024] [Revised: 03/20/2025] [Accepted: 04/06/2025] [Indexed: 05/10/2025]
Abstract
Background
Medical education can be challenging for students as they must manage vast amounts of complex information. Traditional mnemonic resources often follow a standardized approach, which may not accommodate diverse learning styles.
Objective
This tutorial presents a student-developed approach to creating personalized multimodal mnemonics (PMMs) using artifical intelligence tools.
Methods
This tutorial demonstrates a structured implementation process using ChatGPT (GPT-4 model) for text mnemonic generation and DALL-E 3 for visual mnemonic creation. We detail the prompt engineering framework, including zero-shot, few-shot, and chain-of-thought prompting techniques. The process involves (1) template development, (2) refinement, (3) personalization, (4) mnemonic specification, and (5) quality control. The implementation time typically ranges from 2 to 5 minutes per concept, with 1 to 3 iterations needed for optimal results.
Results
Through systematic testing across 6 medical concepts, the implementation process achieved an initial success rate of 85%, improving to 95% after refinement. Key challenges included maintaining medical accuracy (addressed through specific terminology in prompts), ensuring visual clarity (improved through anatomical detail specifications), and achieving integration of text and visuals (resolved through structured review protocols). This tutorial provides practical templates, troubleshooting strategies, and quality control measures to address common implementation challenges.
Conclusions
This tutorial offers medical students a practical framework for creating personalized learning tools using artificial intelligence. By following the detailed prompt engineering process and quality control measures, students can efficiently generate customized mnemonics while avoiding common pitfalls. The approach emphasizes human oversight and iterative refinement to ensure medical accuracy and educational value. The elimination of the need for developing separate databases of mnemonics streamlines the learning process.
Collapse