Unified Peripartum Database with Natural-Language-to-SQL Capabilities at Udine University Hospital: Design and Prototype
🤖 AI Summary
Perinatal data are fragmented across electronic health records, bedside monitoring systems, and laboratory information systems, severely impeding clinical collaboration and reproducible research. To address this, we developed the first unified relational database specifically designed for perinatal medicine. Guided by clinical stakeholder input, we engineered a comprehensive entity-relationship model integrating heterogeneous data—including maternal history, antenatal course, labor and delivery events, and neonatal outcomes. A key innovation is the first integration of a natural language–to-SQL (NL2SQL) interface in this domain, enabling clinicians to query the database using plain English. Prototype evaluation demonstrates that our system substantially lowers barriers to data access, improves analytical efficiency, and enhances auditability through real-time querying. This infrastructure establishes a foundational platform for rigorous, reproducible perinatal research.
Application Category
📝 Abstract
The fragmentation of obstetric information across electronic health record modules, device repositories, and laboratory systems, as it is common in hospitals, hinders both intrapartum care and reproducible research. In this work, we present a practical blueprint for transforming heterogeneous peripartum records into computable, queryable assets by designing and prototyping a unified peripartum relational database with natural-language-to-SQL (NL2SQL) capabilities at the Obstetrics Clinic of Udine University Hospital. Requirements were co-defined with clinicians and formalized as an Entity-Relationship diagram, from which the logical schema and SQL implementation of the database were then derived. The latter integrates heterogeneous sources to connect maternal anamnestic and longitudinal history, current-pregnancy findings, intrapartum course, and delivery and neonatal outcomes. The NL2SQL layer enables clinicians to pose natural-language queries to the system, lowering barriers to audit and exploratory analysis.
Problem
Research questions and friction points this paper is trying to address.
Integrating fragmented obstetric data from multiple hospital systems
Enabling natural language queries for clinical database access
Supporting intrapartum care and reproducible research through unified records
Innovation
Methods, ideas, or system contributions that make the work stand out.
Unified relational database integrates obstetric data sources
Natural-language-to-SQL enables clinical query capabilities
Entity-Relationship design formalizes clinical requirements collaboratively
🔎 Similar Papers
No similar papers found.
