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

Biomedical data harmonization is essential forenabling exploratory analyses and meta-studies, but the process of schema matching-identifying semantic correspondences between elements of disparate datasets (schemas)-remain salabor-intensive and error-prone task. Evenstate-of-the-art automated methods of ten yield low accuracy when applied to biomedical schemas due to the large number of attribute sand nuanced semantic differences between them. We present BDIViz, anovel visualanalytics system designed to stream line 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 am biguity. 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. Ourmethod-agnostic design allows the system to integrate various schema matching algorithms and adapt to application-specificneeds. 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 base line approaches.