DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk Screening
By Yung Wei Shueh · Paper · cs.CL
Large language models (LLMs) offer promising clinical decision support but remain vulnerable to hallucinated facts, unsupported recommendations, and citation errors. We present DIASENTINEL, a fully on-premise multi-agent system for one-year type 2 diabetes mellitus (T2DM) risk sc