Generative AI Supports Medical Interview Evaluation: AI Scoring Shows High Agreement with Instructor Evaluation
NQ Score
82/100
N1 Content Completeness
8
AI Summary (NQ-processed)
Juntendo University demonstrated the effectiveness of using generative AI for evaluating medical interviews, achieving high correlation (0.87-0.90) with human instructors and reducing scoring time by roughly 60%.
AI Analysis
Frequently Asked Questions
- Q: What is the scoring accuracy of AI-generated medical interviews?
- A: It showed a very high correlation coefficient of 0.87 to 0.90 compared to scoring by clinical instructors.
- Q: What are the benefits of introducing AI scoring?
- A: It can reduce instructors' grading time by about 60% and provide consistent, standardized feedback to medical students quickly.
- Q: What are the future challenges?
- A: This study was preliminary and based on a single case, so future verification will require more cases and multiple facilities.