Tracking Cancer Through Text: Longitudinal Extraction From Radiology Reports Using Open-Source Large Language Models

TL;DR

This paper introduces an open-source, locally deployable pipeline utilizing large language models to extract and link longitudinal tumor data from radiology reports, demonstrating high accuracy and privacy preservation.

Contribution

It presents a novel open-source system using LLMs for longitudinal oncology data extraction from radiology reports, ensuring privacy and reproducibility.

Findings

High attribute-level accuracy for lesion extraction (over 93%)

Effective longitudinal lesion linking across time points

Open-source LLMs can perform clinically meaningful tasks

Abstract

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.