RadGPT, an AI-driven tool, demonstrates high-quality performance in translating radiology reports for patients' understanding.
Key Details
- 1RadGPT, developed with ChatGPT-4, generates concept explanations and patient-focused Q&A for radiology report impressions.
- 2Radiologists rated 95% of the AI-generated explanations at 4 or higher (out of 5) for quality, with an average of 4.8.
- 3LLM-generated questions and answers received significantly higher quality ratings than template-based alternatives.
- 4The tool was validated on 30 reports spanning CT, MRI, and x-ray modalities.
- 5Inter-rater agreement among evaluators was high, with Fleiss’ kappa values of 0.66 (answers/explanations) and 0.65 (questions).
Why It Matters
Providing patients with clear, comprehensible information about their radiology findings is increasingly important due to transparency mandates like the Cures Act. Tools like RadGPT may reduce confusion, enhance patient engagement, and decrease the educational burden on radiology staff.
Source
AuntMinnie
Related News
•AuntMinnie
Paul Chang Discusses Foundation Models and Agentic AI at RSNA 2025
Dr. Paul Chang shares his insights on the role of foundation models and agentic AI in radiology at RSNA 2025.
•AuntMinnie
Toronto Study: LLMs Must Cite Sources for Radiology Decision Support
University of Toronto researchers found that large language models (LLMs) such as DeepSeek V3 and GPT-4o offer promising support for radiology decision-making in pancreatic cancer when their recommendations cite guideline sources.
•AuntMinnie
AI Model Using Mammograms Enhances Five-Year Breast Cancer Risk Assessment
A new image-only AI model more accurately predicts five-year breast cancer risk than breast density alone, according to multinational research presented at RSNA 2025.