Roux-lette at “Discharge Me!”: Reducing EHR Chart Burden with a Simple, Scalable, Clinician-Driven AI Approach
Suzanne Wendelken, A. John Paul Antony, Rajashekar Korutla, Bhanu Pachipala, Dushyant Mahajan, James Shanahan, Walid S. Saba · 2024
Healthcare providers spend a significant amount of time reading and synthesizing electronic health records (EHRs), negatively impacting patient outcomes and causing provider burnout.Traditional supervised machine learning approaches using large language models (LLMs) to summarize clinical text have struggled due to hallucinations and lack of relevant training data.Here, we present a novel, simplified solution for the "Discharge Me!" shared task.Our solution uses a questionbased approach to treat this summarization task as a context-aware and domainspecific question-answering process.Our pipeline prompts an LLM answer specific questions posed by subject-matter experts (SMEs) using only patient specific context data.This method (i) avoids hallucinations through hybrid RAG/zero-shot contextualized prompting; (ii) requires no extensive training or fine-tuning; and (iii) is adaptable to various clinical tasks.