Arturo LoAIza-Bonilla, Systemwide Chief of Hematology and Oncology at St. Luke’s University Health Network, and Co-Founder and Chief Medical AI Officer (CMAIO) of Massive Bio, shared a post on LinkedIn:
“AI in oncology isn’t about bigger models. It’s about better grounding.
At GI26, we showed that a guideline-anchored RAG model restricted to NCCN GI guidelines outperformed both baseline GPT-4 and broad literature-retrieval LLMs, with higher guideline concordance and fewer hallucinations.
Source of truth matters. Congrats to Connor Yost and our other co-authors, more to follow!!
Proving the point that partnerships like OpenEvidence + National Comprehensive Cancer Network (NCCN) | American Society of Clinical Oncology (ASCO) + Google Cloud bring much better results for highly specialized care.”
More posts featuring Arturo LoAIza-Bonilla.