Researchers evaluated ChatGPT, Gemini, and Copilot for explaining radiology reports to patients.
Key Details
- 1Study published in 'Insights Into Imaging' compared ChatGPT, Gemini, and Copilot.
- 2100 anonymized radiology reports were input into each LLM using a standard prompt.
- 3Outputs were rated on a 3-point scale for understandability, readability, and medical accuracy.
- 4Researchers also assessed each model's use of uncertainty language and quality of patient guidance.
- 5Aim was to determine which LLM most accurately and clearly conveyed imaging findings.
Why It Matters
As patients increasingly access their own imaging reports, reliable and accurate AI explanations can improve understanding while minimizing anxiety and confusion. Ensuring LLMs perform well in this setting could help bridge communication gaps between radiologists and patients.
Source
Radiology Business
Related News
•AuntMinnie
AI-CAD Demonstrates High Sensitivity in Breast Cancer Screening
A large study found that AI-based computer-aided detection (AI-CAD) can improve breast cancer detection and support radiologists in screening mammography.
•AuntMinnie
AI Tool Mirai Shows Robust Performance for Interval Breast Cancer Detection
The Mirai AI model significantly improves detection of interval breast cancers in negative screening mammograms.
•Radiology Business
AI Tool Predicts Interval Breast Cancer Risk from Negative Mammograms
AI can predict interval breast cancer risk up to three years after a negative mammogram.