Related Experiment Video
Updated: Jan 9, 2026
05:33
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
752
Medical students' perceptions of AI-generated practice questions as learning tools
Hudson Tate1, Brenton T Bicknell1, Paul Fiore1
1Marnix E. Heersink School of Medicine, University of Alabama at Birmingham, AL, USA.
Summary
Generative artificial intelligence (AI) tools can enhance medical education. AI-generated practice questions were well-received by medical students, with upperclassmen performing better, suggesting AI
Area of Science:
- Medical Education
- Artificial Intelligence in Education
- Health Professions Education
Background:
- Generative artificial intelligence (AI) tools, including large language models (LLMs), show promise for enhancing student learning in medical education.
- Formative assessment is crucial for medical student development, and AI offers novel approaches to creating practice materials.
- The United States Medical Licensing Examination (USMLE) style practice questions are a standard tool for assessing medical knowledge.
Purpose of the Study:
- To evaluate the perceived utility of AI-generated, USMLE-style practice questions as a formative learning tool for preclinical medical students.
- To assess the performance outcomes of medical students using AI-generated multiple-choice questions (MCQs).
- To explore differences in performance and perception based on student year and feedback.
Main Methods:
- ChatGPT 4.0 was used to generate MCQs for 15 microbiology and endocrinology lectures.
- A total of 386 preclinical medical students (198 first-year (MS1) and 188 second-year (MS2)) participated.
- 490 AI-generated question sets were completed optionally, with student feedback collected on 94.9% of sets.
Main Results:
- The majority of students found the AI-generated questions helpful (82.8%) or somewhat helpful (16.1%).
- Second-year medical students (MS2) achieved significantly higher correct answer rates (84.4%) compared to first-year students (MS1) (78.6%).
- No significant difference in average scores was found based on student feedback or rating of the questions.
Conclusions:
- AI-generated MCQs are broadly accepted by medical students as valuable supplemental formative learning tools.
- Performance on AI-generated questions varied between student cohorts and lecture topics, indicating potential areas for targeted learning.
- Further research is warranted to explore the broader feasibility and impact of AI tools in medical education.
Related Concept Videos
01:16Non-equilibrium in the Cell
5.3K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
5.3K
01:29Issues And Trends In Healthcare Delivery System
6.1K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
6.1K
01:08The Availability Heuristic
6.9K
A heuristic is a general problem-solving framework (Tversky & Kahneman, 1974). You can think of these as mental shortcuts that are used to solve problems. Different types of heuristics are used in different types of situations, and the impulse to use a heuristic occurs when one of five conditions is met (Pratkanis, 1989):
6.9K