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

Abstract

Clinical guidelines recommend quality standards for patient care. Encoding guidelines in a computer-interpretable format and integrating them with an Electronic Medical Record (EMR) can enable delivery of patient-specific recommendations when and where needed. GLIF3 is a language for representing computer-interpretable guidelines (CIGs) and sharing them among healthcare institutions. Sharing a CIG necessitates mapping its data items to the institutional EMRs. We developed a framework called Knowledge-Data Ontological Mapper (KDOM) that enables bridging the gap from abstractions used in CIGs to specific EMRs. Briding the gap involves: (1) using an ontology of mappings, and an optional reference information model, to map an abstraction gradually into EMR codes, and (2) automatically creating SQL queries to retrieve the EMR data. We evaluated the KDOM framework by mapping a GLIF3-encoded guideline into two different EMR schemas and by using the mapping ontology to define mappings from 15 GLIF3 CIGs and one SAGE CIG into our reference information model.

An Archetype-Based Solution for the Interoperability of Computerised Guidelines and Electronic Health Records

“…The KDOM framework [10] and the MEIDA architecture [11] are remarkable examples of recent work dealing with this problem using standards. Overall, our approach is similar to the ideas of these latter platforms.…”

Analysis of the process of representing clinical statements for decision-support applications: a comparison of openEHR archetypes and HL7 virtual medical record

“…The use of a simplified version of the HL7 RIM was selected by KDOM [5], MEIDA [10], and Cho et al's work [11]. A standard RM is necessary but may not be sufficient to constrain and represent specific semantics needed for DSS applications.…”

“…This allows the CIG to be executed for a specific patient. To aid in the mapping task, using an intermediate (mediated) schema providing a reconciled, integrated and virtual view of the local repositories is a feasible solution [5,6]. The mediated schema is designed to represent the attributes of the domain relevant to the integration application and does not necessarily represent all of the attributes available in the sources [7].…”

Data Integration for Clinical Decision Support Based on openEHR Archetypes and HL7 Virtual Medical Record

“…It was aimed to ease the process of mapping guideline patient data items evaluated by CDSS, allowing decision, eligibility criteria and patient states to be defined in guideline models, by referencing to the vMR rather than to specific EMRs. Projects such as KDOM [5] or openCDS (www.opencds.org) also use a vMR model to achieve their goals. The purpose of the KDOM framework [5] is to allow specifying CIGs that refer to clinical abstractions, while using the framework to map the abstractions to the schema used by different EMRs.…”

“…The mapping [5] is a knowledge-data integration problem, where high-level concepts (e.g. 'high blood pressure') need to be linked to low-level data (e.g., systolic and diastolic BP values), whose evaluation will determine if the pressure is high or not.…”