Prompts to Table: Specification and Iterative Refinement for Clinical Information Extraction with Large Language Models.

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 2,297 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. W

SUBMITTER: Hein D 

PROVIDER: S-EPMC11844613 | biostudies-literature | 2025 Apr

REPOSITORIES: biostudies-literature