Iterative refinement and goal articulation to optimize large language models for clinical information extraction
David Hein, Alana Christie, Michael J. Holcomb, Bingqing Xie, Apurva Jain, Joseph Vento, Neil Rakheja, Ameer Hamza Shakur, Scott Christley, Lindsay G. Cowell, James Brugarolas, Andrew R. Jamieson, Payal Kapur
Abstract
Extracting structured data from free-text medical records at scale is laborious, and traditional approaches struggle in complex clinical domains. We present a novel, end-to-end pipeline leveraging large language models (LLMs) for highly accurate information extraction and normalization from unstructured pathology reports, focusing initially on kidney tumors. Our innovation combines flexible prompt templates, the direct production of analysis-ready tabular data, and a rigorous, human-in-the-loop iterative refinement process guided by a comprehensive error ontology. Applying the finalized pipeline to 2297 kidney tumor reports with pre-existing templated data available for validation yielded a macro-averaged F1 of 0.99 for six kidney tumor subtypes and 0.97 for detecting kidney metastasis. We further demonstrate flexibility with multiple LLM backbones and adaptability to new domains, utilizing publicly available breast and prostate cancer reports. Beyond performance metrics or pipeline specifics, we emphasize the critical importance of task definition, interdisciplinary collaboration, and complexity management in LLM-based clinical workflows.