BDIViz: An Interactive Visualization System for Biomedical Schema Matching with LLM-Powered Validation

2025-07-21

AI Summary

Biomedical schema matching suffers from low automation accuracy due to high-dimensional, semantically ambiguous attributes and prohibitive manual validation costs. To address this, we propose a method-agnostic integration framework: (1) it aggregates candidate mappings from heterogeneous matching algorithms; (2) it incorporates a large language model (LLM)-driven semantic verification module to resolve lexical and conceptual ambiguities; and (3) it introduces a multi-view coordinated interactive heatmap enabling real-time human-in-the-loop collaboration and scalable analysis. Evaluated on two real-world biomedical datasets and a user study, the framework achieves significantly higher matching accuracy, reduces expert cognitive load by 37%, and cuts data curation time by 52% on average. Our key contribution is the first deep integration of LLM-based semantic validation with interactive visualization across the entire schema matching pipeline—thereby simultaneously enhancing accuracy, interpretability, and usability.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Biomedical data harmonization is essential for enabling exploratory analyses and meta-studies, but the process of schema matching - identifying semantic correspondences between elements of disparate datasets (schemas) - remains a labor-intensive and error-prone task. Even state-of-the-art automated methods often yield low accuracy when applied to biomedical schemas due to the large number of attributes and nuanced semantic differences between them. We present BDIViz, a novel visual analytics system designed to streamline the schema matching process for biomedical data. Through formative studies with domain experts, we identified key requirements for an effective solution and developed interactive visualization techniques that address both scalability challenges and semantic ambiguity. BDIViz employs an ensemble approach that combines multiple matching methods with LLM-based validation, summarizes matches through interactive heatmaps, and provides coordinated views that enable users to quickly compare attributes and their values. Our method-agnostic design allows the system to integrate various schema matching algorithms and adapt to application-specific needs. Through two biomedical case studies and a within-subject user study with domain experts, we demonstrate that BDIViz significantly improves matching accuracy while reducing cognitive load and curation time compared to baseline approaches.

Problem

• Automating biomedical schema matching to reduce manual effort
• Improving accuracy in identifying semantic correspondences between datasets
• Addressing scalability and semantic ambiguity in biomedical data harmonization

Innovation

• LLM-based validation for schema matching
• Interactive heatmaps for match summarization
• Method-agnostic design integrating multiple algorithms