Utilizing Large Language Models for Zero-Shot Medical Ontology Extension from Clinical Notes

2025-11-20

AI Summary

To address insufficient coverage in medical ontologies, this work proposes CLOZE—the first zero-shot, annotation-free, and privacy-preserving clinical-note-driven ontology expansion framework. Methodologically, CLOZE leverages large language models (LLMs) to directly identify novel medical concepts and model their hierarchical relationships from unstructured clinical notes, while integrating de-identification techniques to automatically remove protected health information (PHI); no fine-tuning or labeled training data is required. Its key contributions are: (1) the first LLM-native zero-shot ontology expansion approach; (2) joint modeling of domain-specific knowledge and taxonomic structure; and (3) end-to-end automated ontology construction under strict privacy constraints. Experiments demonstrate that CLOZE significantly outperforms existing methods in concept discovery accuracy, cross-institutional scalability, and regulatory compliance—effectively supporting downstream applications such as terminology standardization and clinical decision support.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Privacy

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Integrating novel medical concepts and relationships into existing ontologies can significantly enhance their coverage and utility for both biomedical research and clinical applications. Clinical notes, as unstructured documents rich with detailed patient observations, offer valuable context-specific insights and represent a promising yet underutilized source for ontology extension. Despite this potential, directly leveraging clinical notes for ontology extension remains largely unexplored. To address this gap, we propose CLOZE, a novel framework that uses large language models (LLMs) to automatically extract medical entities from clinical notes and integrate them into hierarchical medical ontologies. By capitalizing on the strong language understanding and extensive biomedical knowledge of pre-trained LLMs, CLOZE effectively identifies disease-related concepts and captures complex hierarchical relationships. The zero-shot framework requires no additional training or labeled data, making it a cost-efficient solution. Furthermore, CLOZE ensures patient privacy through automated removal of protected health information (PHI). Experimental results demonstrate that CLOZE provides an accurate, scalable, and privacy-preserving ontology extension framework, with strong potential to support a wide range of downstream applications in biomedical research and clinical informatics.

Problem

• Automatically extending medical ontologies from clinical notes
• Extracting disease concepts and hierarchical relationships using LLMs
• Providing zero-shot privacy-preserving ontology extension framework

Innovation

• LLMs extract medical entities from clinical notes
• Zero-shot framework integrates concepts into ontologies
• Automated PHI removal ensures patient privacy protection