There has been a push to use OpenEvidence AI for doctors. But this paper suggests general models are much better: “Frontier LLMs outperformed clinical AI tools
A recent paper indicates that general-purpose frontier Large Language Models (LLMs) significantly outperform specialized clinical AI tools for medical applications. The study found that these advanced LLMs were superior in all three evaluation metrics, performing comparably to AI-powered search engines like Google's AI Overview. This challenges the current trend of developing bespoke AI solutions for healthcare, suggesting broader models may be more effective. AI
IMPACT Suggests a shift towards using general LLMs in healthcare, potentially impacting the development and adoption of specialized medical AI tools.