Tracking Cancer Through Text: Longitudinal Extraction From Radiology Reports Using Open-Source Large Language Models
This addresses the need for privacy-preserving, automated analysis of clinical text in oncology, though it's an incremental application of existing open-source LLMs to a specific domain.
The researchers tackled the problem of extracting longitudinal cancer progression data from unstructured radiology reports by developing a fully open-source pipeline using the qwen2.5-72b model, achieving attribute-level accuracies of 93.7-94.9% across different lesion types on Dutch CT reports.
Radiology reports capture crucial longitudinal information on tumor burden, treatment response, and disease progression, yet their unstructured narrative format complicates automated analysis. While large language models (LLMs) have advanced clinical text processing, most state-of-the-art systems remain proprietary, limiting their applicability in privacy-sensitive healthcare environments. We present a fully open-source, locally deployable pipeline for longitudinal information extraction from radiology reports, implemented using the llm_extractinator framework. The system applies the qwen2.5-72b model to extract and link target, non-target, and new lesion data across time points in accordance with RECIST criteria. Evaluation on 50 Dutch CT Thorax/Abdomen report pairs yielded high extraction performance, with attribute-level accuracies of 93.7% for target lesions, 94.9% for non-target lesions, and 94.0% for new lesions. The approach demonstrates that open-source LLMs can achieve clinically meaningful performance in multi-timepoint oncology tasks while ensuring data privacy and reproducibility. These results highlight the potential of locally deployable LLMs for scalable extraction of structured longitudinal data from routine clinical text.