A unified fuzzy ontology for distributed electronic health record semantic interoperability

Abstract

Abstract Electronic health records (EHR) provide efficient management of clinical information in any healthcare organization. It is a complete and longitudinal electronic registration of all occasions and data identified with the person s health status, from birth to death. Medical data are growing rapidly. These data are heterogeneous, distributed, and nonstructured. Each data element can have its schema, structure, standard, format, coding system, level of abstraction, and semantic. Medical personnel need to query the distributed EHR systems anonymously by using a single language. Combination and integration of the data are vital to recover the history of patients, to share information, and to elicit queries. Semantic interoperability provides a meaningful exchange and the use of clinical data between many healthcare systems. Physicians often send fuzzy questions to EHR systems and need answers from distributed systems. In this chapter, a unified semantic interoperability framework for distributed EHR based on fuzzy ontology is proposed. The framework architecture consists of three main layers. The lowest layer (local ontologies construction) stores the EHRs heterogeneous data with different database schemas, standards, terminologies, purposes, locations, and formats. The sources of this information may be different databases (e.g., MySQL, SqlServer, DB2, Access, and Oracle) in heterogeneous schemas, EHR standards, XML files, spreadsheet files, or archetype definition language (ADL) files. These different inputs are transformed into crisp ontology using a mediator (e.g., DB2OWL, X2OWL or ADL2OntoModule) suitable for each type. In the middle layer (global ontology construction), the local ontologies are mapped (using mapping algorithms or human experts with the help of common terminology vocabularies) to a crisp global one. The global reference ontology combines and integrates all local ontologies and therefore describes all data. Then this crisp ontology is converted to a unified fuzzy ontology. Finally, the third layer is the user interface in which a doctor or any specialist can ask any linguistic or semantic queries by dealing with only the global reference fuzzy ontology. That ontology is more dynamic and helps in understanding natural language deep medical queries. The result is a global and robust semantic interoperability technique. The proposed solution is based on a fuzzy ontology semantic to integrate different healthcare systems. That framework has many benefits and advantages over frameworks that rely on crisp ontology only, including: (1) it moves toward achieving full semantic interoperability of heterogeneous EHRs, (2) it supports the idea of plug and play where any system with any structure can be integrated anonymously with existing systems without affecting the current working environment, and (3) it is an expandable and designed in a modular way as it based on using ontologies and terminologies; the functionality of the proposed framework can be extended uniformly. We expect that our framework will handle the current EHR semantic interoperability challenges, reduce the cost of the integration process, and get a higher acceptance and accuracy rate than previous studies.