Leveraging Prompt-Learning for Structured Information Extraction from Crohn's Disease Radiology Reports in a Low-Resource Language
This work addresses the challenge of accurate AI diagnostics for medical data in low-resource languages, which is incremental as it applies a novel method to a specific domain bottleneck.
The paper tackled the problem of extracting structured information from Crohn's disease radiology reports in Hebrew, a low-resource language, by introducing SMP-BERT, a prompt learning method that achieved superior performance over traditional fine-tuning, with AUC of 0.99 vs 0.94 and F1 of 0.84 vs 0.34 for rare conditions.
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.