A Dynamic Framework for Semantic Grouping of Common Data Elements (CDE) Using Embeddings and Clustering

2025-06-02

AI Summary

To address the challenges of cross-source integration and poor interoperability among Biomedical Common Data Elements (CDEs)—stemming from semantic heterogeneity, structural variability, and context dependence—this paper proposes the first four-step closed-loop framework integrating: (1) LLM-powered context-aware embeddings, (2) HDBSCAN hierarchical density-based clustering, (3) LLM-driven automatic labeling, and (4) supervised classification. The framework enables dynamic extensibility and real-time categorization of novel CDEs. Evaluated on over 24,000 NIH CDEs, it yields 118 semantically coherent clusters (minimum cluster size: 20) with a classification accuracy of 90.46%. External validation achieves an Adjusted Rand Index (ARI) of 0.52 and a Normalized Mutual Information (NMI) of 0.78, demonstrating substantial improvements in CDE semantic alignment efficiency and cross-platform interoperability.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Clustering

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Web data integration and cleaning
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

This research aims to develop a dynamic and scalable framework to facilitate harmonization of Common Data Elements (CDEs) across heterogeneous biomedical datasets by addressing challenges such as semantic heterogeneity, structural variability, and context dependence to streamline integration, enhance interoperability, and accelerate scientific discovery. Our methodology leverages Large Language Models (LLMs) for context-aware text embeddings that convert CDEs into dense vectors capturing semantic relationships and patterns. These embeddings are clustered using Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) to group semantically similar CDEs. The framework incorporates four key steps: (1) LLM-based text embedding to mathematically represent semantic context, (2) unsupervised clustering of embeddings via HDBSCAN, (3) automated labeling using LLM summarization, and (4) supervised learning to train a classifier assigning new or unclustered CDEs to labeled clusters. Evaluated on the NIH NLM CDE Repository with over 24,000 CDEs, the system identified 118 meaningful clusters at an optimized minimum cluster size of 20. The classifier achieved 90.46 percent overall accuracy, performing best in larger categories. External validation against Gravity Projects Social Determinants of Health domains showed strong agreement (Adjusted Rand Index 0.52, Normalized Mutual Information 0.78), indicating that embeddings effectively capture cluster characteristics. This adaptable and scalable approach offers a practical solution to CDE harmonization, improving selection efficiency and supporting ongoing data interoperability.

Problem

• Dynamic framework for semantic grouping of Common Data Elements (CDEs)
• Addressing semantic heterogeneity in biomedical datasets for interoperability
• Leveraging LLMs and clustering to harmonize CDEs efficiently

Innovation

• LLM-based text embedding for semantic context
• HDBSCAN clustering of semantic embeddings
• Supervised classifier for new CDEs