Enhancing narrative clinical guidance with computer-readable artifacts: Authoring FHIR implementation guides based on WHO recommendations

Abstract

IntroductionNarrative clinical guidelines often contain assumptions, knowledge gaps, and ambiguities that make translation into an electronic computable format difficult. This can lead to divergence in electronic implementations, reducing the usefulness of collected data outside of that implementation setting. This work set out to evolve guidelines-based data dictionaries by mapping to HL7 Fast Health Interoperability Resources (FHIR) and semantic terminology, thus progressing toward machine-readable guidelines that define the minimum data set required to support family planning and sexually transmitted infections. Material and methodsThe data dictionaries were first structured to facilitate mapping to FHIR and semantic terminologies, including ICD-10, SNOMED-CT, LOINC, and RxNorm. FHIR resources and codes were assigned to data dictionary terms. The data dictionary and mappings were used as inputs for a newly developed tool to generate FHIR implementation guides. ResultsImplementation guides for core data requirements for family planning and sexually transmitted infections were created. These implementation guides display data dictionary content as FHIR resources and semantic terminology codes. Challenges included the use of a two-dimensional spreadsheet to facilitate mapping, the need to create FHIR profiles and resource extensions, and applying FHIR to a data dictionary that was created with a user interface in mind. ConclusionsAuthoring FHIR implementation guides is a complex and evolving practice, and there are limited examples for this groundbreaking work. Moving toward machine-readable guidelines by mapping to FHIR and semantic terminologies requires a thorough understanding of the context and use of terminology, an applied information model, and other strategies for optimizing the creation and long-term management of implementation guides. Next steps for this work include validation and, eventually, real-world application. The process for creating the data dictionary and for generating implementation guides should also be improved to prepare for this expanding work.Funding.This work was supported by the World Health Organization, which also worked as a collaborative partner throughout the study.