A semi-autonomous approach to connecting proprietary EHR standards to FHIR
This addresses interoperability challenges in healthcare by enabling easier integration of diverse EHR systems with FHIR, though it is incremental as it builds on existing standards and methods.
The paper tackles the problem of converting proprietary electronic health record (EHR) data to the FHIR standard for interoperability, proposing a semi-autonomous process that uses similarity metrics and parameters to enable efficient translation, as demonstrated in the CONSULT project for stroke patient decision support.
HL7's Fast Healthcare Interoperability Resources (FHIR) standard is designed to provide a consistent way in which to represent and exchange healthcare data, such as electronic health records (EHRs). SMART--on--FHIR (SoF) technology uses this standard to augment existing healthcare data systems with a standard FHIR interface. While this is an important goal, little attention has been paid to developing mechanisms that convert EHR data structured using proprietary schema to the FHIR standard, in order to be served by such an interface. In this paper, a formal process is proposed that both identifies a set of FHIR resources that best capture the elements of an EHR, and transitions the contents of that EHR to FHIR, with a view to supporting the operation of SoF containers, and the wider interoperability of health records with the FHIR standard. This process relies on a number of techniques that enable us to understand when two terms are equivalent, in particular a set of similarity metrics, which are combined along with a series of parameters in order to enable the approach to be tuned to the different EHR standards encountered. Thus, when realised in software, the translation process is semi-autonomous, requiring only the specification of these parameters before performing an arbitrary number of future conversions. The approach is demonstrated by utilising it as part of the CONSULT project, a wider decision support system that aims to provide intelligent decision support for stroke patients.