DeepSeek-V3 and ChatGPT-4o excelled in accurately answering patient questions about interventional radiology procedures, suggesting LLMs' growing role in clinical communication.
Key Details
- 1Study evaluated four LLMs (ChatGPT-4o, DeepSeek-V3, OpenBioLLM-8b, BioMistral-7b) on 107 real-world patient questions covering TAPE, CT-guided HDR brachytherapy, and BEST.
- 2Questions and their answers were independently scored for accuracy by two board-certified radiologists using a Likert scale.
- 3DeepSeek-V3 achieved the highest mean scores for BEST (4.49) and CT-HDR (4.24), while matching ChatGPT-4o on TAPE (4.20 vs 4.17).
- 4OpenBioLLM-8b and BioMistral-7b scored significantly lower and produced potentially hazardous responses.
- 5LLMs' responses show promise for supporting—but not replacing—comprehensive medical consultations.
- 6Future studies should include patient feedback and focus on alignment with clinical guidelines.
Why It Matters
Accurate, scalable patient education via AI could improve understanding and consent for complex interventional radiology procedures, potentially enhancing workflow efficiency and patient outcomes. However, inconsistent model performance highlights the need for careful integration and validation.
Source
AuntMinnie
Related News
•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.
•Radiology Business
AI Model Uses CT Scans to Reveal Biomarker for Chronic Stress
Researchers developed an AI model to measure chronic stress using adrenal gland volume on routine CT scans.