Raja-Elie Abdulnour, Editor, Clinical Development and AI Innovation at NEJM Group, posted on X:
“RAG improves a GPT copilot in oncology guidelines questions. No RAG: 57% correct. RAG: 84% correct. Is that enough? The need for a human pilot remains, but attaching reliability evidence like this paper to a copilot can help clinicians make entrustment decisions.”
Source: Raja-Elie Abdulnour/X