Leveraging Prompt-Learning for Structured Information Extraction from Crohn's Disease Radiology Reports in a Low-Resource Language

TL;DR

This paper presents SMP-BERT, a prompt learning approach that effectively extracts structured information from Crohn's disease radiology reports in Hebrew, outperforming traditional methods especially for rare findings.

Contribution

Introduction of SMP-BERT, a novel prompt learning method tailored for low-resource languages and imbalanced medical datasets, improving extraction accuracy in radiology reports.

Findings

SMP-BERT achieved an AUC of 0.99, outperforming traditional methods.

SMP-BERT significantly improved F1 scores for rare conditions.

The method enhances AI diagnostics in low-resource language medical data.

Abstract

Automatic conversion of free-text radiology reports into structured data using Natural Language Processing (NLP) techniques is crucial for analyzing diseases on a large scale. While effective for tasks in widely spoken languages like English, generative large language models (LLMs) typically underperform with less common languages and can pose potential risks to patient privacy. Fine-tuning local NLP models is hindered by the skewed nature of real-world medical datasets, where rare findings represent a significant data imbalance. We introduce SMP-BERT, a novel prompt learning method that leverages the structured nature of reports to overcome these challenges. In our studies involving a substantial collection of Crohn's disease radiology reports in Hebrew (over 8,000 patients and 10,000 reports), SMP-BERT greatly surpassed traditional fine-tuning methods in performance, notably in detecting infrequent conditions (AUC: 0.99 vs 0.94, F1: 0.84 vs 0.34). SMP-BERT empowers more accurate AI diagnostics available for low-resource languages.