Back to all news
ChatGPT-Generated Questions Match Quality of Radiologist-Written MCQs for Residents
Tags:Research
A study found that ChatGPT can generate multiple-choice questions for radiology residents of comparable quality to those written by attending radiologists.
Key Details
- 1Study published July 7 in Academic Radiology assessed MCQs for resident education.
- 2144 MCQs were generated by ChatGPT from lecture transcripts; 17 used in the study.
- 3Questions were mixed with 11 radiologist-written MCQs; 21 residents participated.
- 4No significant difference in perceived quality: ChatGPT MCQ mean score 6.93 vs. 7.08 for attendings.
- 5Correct answer rate similar: ChatGPT (57%), attendings (59%).
- 6Residents were less likely to identify ChatGPT questions as written by attendings.
Why It Matters
This validation shows that large language models like ChatGPT can support radiology education by efficiently generating high-quality, non-image-based assessment material. Such tools could address faculty participation gaps and streamline resident assessment in radiology programs.
Source
AuntMinnie
Related News
•AuntMinnie
Study: Computer Vision Models Best LLMs in Chest CT Breast Abnormality Detection
Computer vision models (CVMs) surpass large language models (LLMs) in accurately labeling incidental breast abnormalities on chest CT scans.
•AuntMinnie
Deep Learning Models Rival Radiologists for Pancreatic Cancer Detection on CT
Deep-learning models achieved comparable or superior accuracy to experienced radiologists in detecting pancreatic cancer on CT scans, especially for small tumors.
•Radiology Business
Radiology AI Devices at Elevated Risk for FDA Recalls, Study Finds
Radiology AI devices are more likely to face FDA recalls, largely due to deviations from intended use and incomplete clinical data.