ChatGPT Tops Large Language Models for Microwave Ablation Advice

ChatGPT outperformed 4 other LLMs in providing microwave ablation guidance, achieving the highest mean quality score (3.65/4) when rated by radiologists. Claude and DeepSeek followed (3.47), while Gemini (3.00) and Meta (2.95) scored lower, suggesting potential for clinical deci…

• ChatGPT scored highest in subcategories like Risks and Complications (3.89/4) and Post-Procedure Care (3.89/4).
• Interrater reliability was moderate to good (ICC 0.56-0.75).
• The authors emphasize that human oversight and domain-specific validation remain essential.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.