Related Experiment Video
Updated: Jan 17, 2026
09:52
Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide
Published on: January 15, 2017
17.6K
Artificial intelligence-assisted shared decision-making training for medical students transitioning to residency
Young-Min Kim1, Young-Mee Lee2, Do-Hwan Kim3,4
1Department of Emergency Medicine, Department of Medical Education, The Catholic University of Korea College of Medicine, Seoul, South Korea.
Summary
This study trained medical students in artificial intelligence (AI)-assisted shared decision-making (SDM). The simulation-based course improved students' confidence and comprehension in using AI tools for patient communication and diagnosis.
Area of Science:
- Medical Education
- Artificial Intelligence in Healthcare
- Clinical Decision Support
Background:
- Clinical practice increasingly uses artificial intelligence (AI) for diagnosis, yet medical education lacks training on integrating AI insights into diagnosis and shared decision-making (SDM).
- Effective use of AI-generated information requires specific training for clinicians to navigate diagnostic aids and patient communication.
Purpose of the Study:
- To develop and pilot a simulation-based course to train final-year medical students in AI-assisted SDM.
- To evaluate the impact of the course on students' comprehension and confidence in utilizing AI tools within the SDM process.
Main Methods:
- A simulation-based course combining online prelearning and onsite simulations was conducted with final-year medical students.
- Participants used clinically approved AI tools (Lunit INSIGHT CXR, MMG) in simulated patient encounters focusing on incidental findings and SDM.
- The course included simulated patient feedback and expert-facilitated debriefing for 27 students from 3 medical schools.
Main Results:
- Significant improvements were observed in participants' comprehension and confidence in both SDM and AI-assisted SDM (P < .001).
- Students reported AI tools facilitated SDM and patient communication, particularly through visual outputs for diagnosis support.
- Identified limitations included student knowledge gaps and AI explainability issues, with suggestions for curriculum integration.
Conclusions:
- The developed course effectively enhanced medical students' skills in AI-assisted SDM.
- Integrating such training into formal curricula is recommended to better prepare future physicians for AI-assisted clinical practice.
- Future efforts should focus on incorporating this training into undergraduate or transition programs for experiential learning.
Related Concept Videos
01:20Decision Making
898
Decision-making is a fundamental cognitive process that involves evaluating alternatives and selecting among them. This process can range from simple choices, such as deciding what to wear, to complex decisions, like choosing a major in college or a career path. The complexity of the decision often dictates the approach we use, which can be broadly categorized into two types: automatic and controlled decision-making.
Automatic decision-making is fast, intuitive, and relies on gut feelings...
Automatic decision-making is fast, intuitive, and relies on gut feelings...
898
01:14Decision Making: Traditional Method
5.1K
The process of hypothesis testing based on the traditional method includes calculating the critical value, testing the value of the test statistic using the sample data, and interpreting these values.
First, a specific claim about the population parameter is decided based on the research question and is stated in a simple form. Further, an opposing statement to this claim is also stated. These statements can act as null and alternative hypotheses, out of which a null hypothesis would be a...
First, a specific claim about the population parameter is decided based on the research question and is stated in a simple form. Further, an opposing statement to this claim is also stated. These statements can act as null and alternative hypotheses, out of which a null hypothesis would be a...
5.1K