GENIE: Generative Note Information Extraction model for structuring EHR data

2025-01-30

AI Summary

Existing EHR text structuring methods suffer from low efficiency and poor generalizability, while large language models (LLMs) remain impractical for clinical deployment due to prohibitive computational costs. Method: We propose the first end-to-end generative information extraction framework tailored for clinical notes, enabling joint identification of entities, assertion status, anatomical locations, modifiers, numeric values, and clinical purposes in a single inference pass. Our approach leverages a fine-tuned small open-weight LLM, integrated with robust preprocessing and a unified generative paradigm—eliminating reliance on rule-based engines or post-processing modules. Contribution/Results: The framework supports extensible attribute definitions and significantly outperforms traditional tools (e.g., cTAKES, MetaMap) on entity recognition and relation extraction. It achieves both high accuracy and lightweight deployability, and has been successfully scaled to production in real-world healthcare systems. We publicly release both the model and a benchmark evaluation dataset.

Technology Category

• Natural Language Processing: Information Extraction
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Electronic Health Records (EHRs) hold immense potential for advancing healthcare, offering rich, longitudinal data that combines structured information with valuable insights from unstructured clinical notes. However, the unstructured nature of clinical text poses significant challenges for secondary applications. Traditional methods for structuring EHR free-text data, such as rule-based systems and multi-stage pipelines, are often limited by their time-consuming configurations and inability to adapt across clinical notes from diverse healthcare settings. Few systems provide a comprehensive attribute extraction for terminologies. While giant large language models (LLMs) like GPT-4 and LLaMA 405B excel at structuring tasks, they are slow, costly, and impractical for large-scale use. To overcome these limitations, we introduce GENIE, a Generative Note Information Extraction system that leverages LLMs to streamline the structuring of unstructured clinical text into usable data with standardized format. GENIE processes entire paragraphs in a single pass, extracting entities, assertion statuses, locations, modifiers, values, and purposes with high accuracy. Its unified, end-to-end approach simplifies workflows, reduces errors, and eliminates the need for extensive manual intervention. Using a robust data preparation pipeline and fine-tuned small scale LLMs, GENIE achieves competitive performance across multiple information extraction tasks, outperforming traditional tools like cTAKES and MetaMap and can handle extra attributes to be extracted. GENIE strongly enhances real-world applicability and scalability in healthcare systems. By open-sourcing the model and test data, we aim to encourage collaboration and drive further advancements in EHR structurization.

Problem

• Electronic Health Records
• Language Models
• Information Extraction

Innovation

• GENIE Model
• Automated Information Extraction
• Medical Data Standardization