Standardizing Longitudinal Radiology Report Evaluation via Large Language Model Annotation

TL;DR

This paper introduces an LLM-based pipeline for automatically annotating longitudinal information in radiology reports, enabling standardized evaluation of report generation models and outperforming existing annotation methods.

Contribution

The study develops a novel LLM-based annotation pipeline for longitudinal radiology report analysis, creating a large benchmark dataset and improving annotation accuracy over prior methods.

Findings

Qwen2.5-32B was selected for annotation due to its efficiency and performance.

The annotated dataset enabled evaluation of seven report generation models.

The LLM-based method achieved 11.3% and 5.3% higher F1-scores in detection and tracking.

Abstract

Longitudinal information in radiology reports refers to the sequential tracking of findings across multiple examinations over time, which is crucial for monitoring disease progression and guiding clinical decisions. Many recent automated radiology report generation methods are designed to capture longitudinal information; however, validating their performance is challenging. There is no proper tool to consistently label temporal changes in both ground-truth and model-generated texts for meaningful comparisons. Existing annotation methods are typically labor-intensive, relying on the use of manual lexicons and rules. Complex rules are closed-source, domain specific and hard to adapt, whereas overly simple ones tend to miss essential specialised information. Large language models (LLMs) offer a promising annotation alternative, as they are capable of capturing nuanced linguistic patterns and semantic similarities without extensive manual intervention. They also adapt well to new contexts. In this study, we therefore propose an LLM-based pipeline to automatically annotate longitudinal information in radiology reports. The pipeline first identifies sentences containing relevant information and then extracts the progression of diseases. We evaluate and compare five mainstream LLMs on these two tasks using 500 manually annotated reports. Considering both efficiency and performance, Qwen2.5-32B was subsequently selected and used to annotate another 95,169 reports from the public MIMIC-CXR dataset. Our Qwen2.5-32B-annotated dataset provided us with a standardized benchmark for evaluating report generation models. Using this new benchmark, we assessed seven state-of-the-art report generation models. Our LLM-based annotation method outperforms existing annotation solutions, achieving 11.3\% and 5.3\% higher F1-scores for longitudinal information detection and disease tracking, respectively.