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

TL;DR

BDIViz is an interactive visualization system that enhances biomedical schema matching accuracy and efficiency by integrating multiple matching methods with LLM-based validation and user-friendly visualizations.

Contribution

The paper introduces BDIViz, a novel visual analytics system that combines ensemble schema matching with LLM validation to improve biomedical data harmonization.

Findings

BDIViz significantly improves matching accuracy.

Reduces cognitive load and curation time.

Effective in biomedical case studies.

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.