Mapping computerized clinical guidelines to electronic medical records: knowledge-data ontological mapper (KDOM)

Area of Science:

• Health Informatics
• Medical Informatics
• Clinical Decision Support

Background:

• Clinical guidelines establish quality standards for patient care.
• Integrating computer-interpretable guidelines (CIGs) with Electronic Medical Records (EMRs) can provide real-time, patient-specific recommendations.
• Sharing CIGs requires mapping guideline data items to institutional EMRs.

Purpose of the Study:

• To develop a framework, the Knowledge-Data Ontological Mapper (KDOM), for bridging the gap between CIG abstractions and specific EMR data.
• To facilitate the sharing of CIGs among healthcare institutions by automating the mapping process.

Main Methods:

• Developed the KDOM framework utilizing a mapping ontology and an optional reference information model.
• Implemented a two-step mapping process: gradual abstraction to EMR codes and automatic SQL query generation for data retrieval.
• Evaluated KDOM by mapping a GLIF3 guideline to two EMR schemas and defining mappings for 15 GLIF3 CIGs and one SAGE CIG.

Main Results:

• Successfully demonstrated the KDOM framework's capability to map CIGs to different EMR schemas.
• Established a mapping ontology to define relationships between guideline abstractions and EMR data elements.
• Automated the generation of SQL queries for efficient EMR data extraction.

Conclusions:

• The KDOM framework effectively bridges the gap between computer-interpretable guidelines and Electronic Medical Records.
• KDOM facilitates the sharing and implementation of CIGs, enhancing the delivery of patient-specific care recommendations.
• Ontology-driven mapping and automated query generation are key components for successful guideline integration into EMR systems.