CDE-Mapper: Using Retrieval-Augmented Language Models for Linking Clinical Data Elements to Controlled Vocabularies

2025/05/07 by Komal Gilani, Marlo Verket, Gilani, Komal +8
Biochemistry, Genetics and Molecular Biology · Computer Science · #Abstraction #Biomedical Text Mining and Ontologies #Data integration #Data modeling #Information model #Interoperability #Language model #Machine Learning in Healthcare #Modular design #Query language #Representation (politics) #Standardization #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2505.04365

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/05/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

The standardization of clinical data elements (CDEs) aims to ensure consistent and comprehensive patient information across various healthcare systems. Existing methods often falter when standardizing CDEs of varying representation and complex structure, impeding data integration and interoperability in clinical research. We introduce CDE-Mapper, an innovative framework that leverages Retrieval-Augmented Generation approach combined with Large Language Models to automate the linking of CDEs to controlled vocabularies. Our modular approach features query decomposition to manage varying levels of CDEs complexity, integrates expert-defined rules within prompt engineering, and employs in-context learning alongside multiple retriever components to resolve terminological ambiguities. In addition, we propose a knowledge reservoir validated by a human-in-loop approach, achieving accurate concept linking for future applications while minimizing computational costs. For four diverse datasets, CDE-Mapper achieved an average of 7.2% higher accuracy improvement compared to baseline methods. This work highlights the potential of advanced language models in improving data harmonization and significantly advancing capabilities in clinical decision support systems and research.

Citations

• ICD Codes are Insufficient to Create Datasets for Machine Learning: An Evaluation Using All of Us Data for Coccidioidomycosis and Myocardial Infarction
• SNOBERT: A Benchmark for clinical notes entity linking in the SNOMED CT clinical terminology
• Retrieval-Augmented Generation for Large Language Models: A Survey
• Biomedical knowledge graph-optimized prompt generation for large language models
• A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
• Entity Matching using Large Language Models
• Benchmarking Large Language Models in Retrieval-Augmented Generation
• Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
• 🧜Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models
• Large language models in medicine
• A Comprehensive Overview of Large Language Models
• A Survey on Evaluation of Large Language Models
• A Survey on Evaluation of Large Language Models
• Lost in the Middle: How Language Models Use Long Contexts
• Exploring the In-context Learning Ability of Large Language Model for Biomedical Concept Linking
• A Survey of Large Language Models
• GPT-4 Technical Report
• LLaMA: Open and Efficient Foundation Language Models
• Atlas: Few-shot Learning with Retrieval Augmented Language Models
• Large Language Models are Zero-Shot Reasoners
• Learning To Retrieve Prompts for In-Context Learning
• Knowledge-Rich Self-Supervision for Biomedical Entity Linking
• Entity Linking Meets Deep Learning: Techniques and Solutions
• SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval
• SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking
• What Makes Good In-Context Examples for GPT-3?
• Self-Alignment Pretraining for Biomedical Entity Representations
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Biomedical Entity Representations with Synonym Marginalization
• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications
• Cumulated gain-based evaluation of IR techniques

Related

• CDEMapper: Enhancing NIH Common Data Element Normalization using Large Language Models
• ClinLinker: Medical Entity Linking of Clinical Concept Mentions in Spanish
• Almanac: Retrieval-Augmented Language Models for Clinical Medicine
• Large Language Models for Automating Clinical Data Standardization: HL7 FHIR Use Case
• Reviewing Clinical Knowledge in Medical Large Language Models: Training and Beyond