Optimizing Medication Querying Using Ontology-Driven Approach with OMOP: with an application to a large-scale...

Area of Science:

• Health Informatics
• Clinical Data Management
• Pharmacology

Background:

• Efficient querying of medication information in Electronic Health Records (EHR) is vital for patient care and clinical research.
• Large EHR datasets present challenges in data volume and complexity for medication information retrieval.
• Existing methods may lack comprehensiveness in identifying relevant medication terms.

Purpose of the Study:

• To propose and validate an ontology-driven medication query (ODMQ) optimization approach.
• To enhance the accuracy and efficiency of medication information retrieval from EHR datasets.
• To improve the scope of medication term identification beyond traditional methods.

Main Methods:

• Leveraging the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM).
• Integrating semantic ontology structures to broaden medication term scope (drug names, National Drug Codes, generics).
• Validating ODMQ efficacy using real-world COVID-19 EHR data and manual review for relevance.

Main Results:

• ODMQ significantly reduces manual search time and enhances query capabilities.
• Demonstrated improved query performance in real-world COVID-19 EHR data.
• Ensured expanded search terms are relevant through comprehensive manual review.

Conclusions:

• The ontology-driven medication query (ODMQ) approach effectively optimizes medication information retrieval from EHRs.
• ODMQ enhances query accuracy, efficiency, and comprehensiveness compared to traditional methods.
• The approach includes an intuitive interface and visualization tools for result validation.