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
•Radiology Business
Meta Funds Ohio State’s Radiology AI Innovation Projects
Meta will fund Ohio State researchers to explore AI-driven advancements in radiology, including chest X-ray reporting and disease prediction.
•AuntMinnie
ChatGPT-5 Performs Poorly at Detecting Distal Radius Fractures on X-rays
ChatGPT-5 missed about half of distal radius fractures on x-rays, showing limited diagnostic capability in a real-world scenario.
•AuntMinnie
AI Triage Tool Speeds Up ICH Head CT Turnaround in ED
AI-based triage for intracranial hemorrhage on head CT reduced emergency department report turnaround by 13 minutes.