Large Language Models in Medicine
Cross-source consensus on Large Language Models in Medicine from 1 sources and 4 claims.
1 sources · 4 claims
Risks & contraindications
Comparisons
Evidence quality
Highlighted claims
- Large language models may sound fluent and helpful while still making high-stakes reasoning errors. — ChatGPT Health triage advice falls short in key cases
- Users may rely on AI-generated medical advice even when its accuracy is imperfect. — ChatGPT Health triage advice falls short in key cases
- The briefing connects ChatGPT Health’s triage performance to wider concerns about clinical AI. — ChatGPT Health triage advice falls short in key cases
- Prior literature describes capabilities and limitations of large language models for clinical decision-making tasks including triage. — ChatGPT Health triage advice falls short in key cases