General-Purpose vs. Domain-Adapted Large Language Models for Extraction of Structured Data from Chest Radiology Reports

arXiv:2311.17213v3 Announce Type: replace
Abstract: Radiologists produce unstructured data that can be valuable for clinical care when consumed by information systems. However, variability in style limits usage. Study compares system using domain-adapted language model (RadLing) and general-purpose LLM (GPT-4) in extracting relevant features from chest radiology reports and standardizing them to common data elements (CDEs). Three radiologists annotated a retrospective dataset of 1399 chest XR reports (900 training, 499 test) and mapped to 44 pre-selected relevant CDEs. GPT-4 system was …

abstract arxiv clinical cs.cl data domain eess.iv extraction features general gpt gpt-4 however information language language model language models large language large language models llm radiology reports structured data study style systems type unstructured unstructured data usage