Open-Weight Language Models and Retrieval Augmented Generation for Automated Structured Data Extraction from Diagnostic Reports: Assessment of Approaches and Parameters.

Abstract

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop and evaluate an automated system for extracting structured clinical information from unstructured radiology and pathology reports using open-weights language models (LMs) and retrieval augmented generation (RAG) and to assess the effects of model configuration variables on extraction performance. Materials and Methods This retrospective study utilized two datasets: 7,294 radiology reports annotated for Brain Tumor Reporting and Data System (BT-RADS) scores and 2,154 pathology reports annotated for IDH mutation status (January 2017 to July 2021). An automated pipeline was developed to benchmark the performance of various LMs and RAG configurations for structured data extraction accuracy from reports. The impact of model size, quantization, prompting strategies, output formatting, and inference parameters on model accuracy was systematically evaluated. Results The best performing models achieved up to 98% accuracy in extracting BT-RADS scores from radiology reports and over 90% for IDH mutation status extraction from pathology reports. The best model was medical finetuned llama3. Larger, newer, and domain fine-tuned models consistently outperformed older and smaller models (mean accuracy, 86% versus 75%; P < .001). Model quantization had minimal impact on performance. Few-shot prompting significantly improved accuracy (mean increase: 32% ± 32%, P = .02). RAG improved performance for complex pathology reports +48% ± 11% (P = .001), but not for shorter radiology reports-8% ± 31% (P = .39). Conclusion This study demonstrates the potential of open LMs in automated extraction of structured clinical data from unstructured clinical reports with local privacy-preserving application. Careful model selection, prompt engineering, and semiautomated optimization using annotated data are critical for optimal performance. ©RSNA, 2025.