FHIR-Enabled Social and Health Information Platform: Integrating a Closed-Loop Social Services Referral System Into Electronic Health Records in Federally Qualified Health Centers Using FHIR
There is a growing recognition across the healthcare industry that by capturing and accessing social determinants of health (SDOH) data during patients’ care, providers can more easily identify and address non-clinical factors, such as food, housing, and transportation insecurities through collaboration with community-based organizations delivering social care. A lack of interoperability between clinical and community resource systems limits crucial information sharing to support individuals accessing services.
The University of Texas at Austin will create a Health Level 7 International (HL7®) Fast Healthcare Interoperability Resources (FHIR®) -enabled Social and Health Information Platform to integrate a closed-loop social services referral system accessible through the electronic health records (EHRs) maintained and used by Federally Qualified Health Centers (FQHCs). The system will help manage social needs identified in clinical settings; exchange information between clinical providers and community-based organizations; and integrate clinical workflows and EHRs. The system will also provide patient access, consent, and navigation via a mobile platform. The system will leverage FHIR APIs and the Gravity Project’s Use Case Package, which outline use cases for the collection of social determinants of health data as they relate to food security, housing stability, and transportation access.
This project began in 2021 and is estimated to be completed in 2024
The goals of this project are to:
- Develop an open source, “closed loop” social services referral management system using Health IT standards and FHIR APIs to demonstrate information exchange between clinical providers, social service organizations, and patients.
- Demonstrate the feasibility of the referral management system to fulfill the Gravity Project Use Cases Package for SDOH for screening, diagnosis, planning, and interventions in patients.
- Develop and implement a toolkit to pilot the referral management system using synthetic patient data and regional health information exchanges.
This project will build a data processing framework to enable semantic harmonization of health data collected from multiple providers with different EHR systems. The framework will be built using the Layered Schemas Architecture (LSA) – an open technology developed by Cloud Privacy Labs that enables semantic interoperability of data collected from heterogeneous sources by addressing variations due to factors such as different vendors, conventions, or jurisdictions using schemas and overlays. Data will be collected from at least four different EHR systems, and then existing semantic web tools will be used to produce high quality outputs in the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) for artificial intelligence (AI) training and research.
This project addresses the Leading Edge Acceleration Projects (LEAP) in Health Information Technology (Health IT) fiscal year 2021 special area of interest 2: Health IT Tools to Make Electronic Health Records (EHR) Data Research – and Artificial Intelligence (AI)-Ready.
This project began in 2021 and is estimated to be completed in 2023.
The goals of this project are to:
- Develop a data processing framework that harmonizes semantics for EHR data pooled from heterogeneous sources in the form of FHIR messages, CCDAs, and tabular data (CSV files) by using Layered Schemas to translate source data into a linked format for semantic processing to enable the use of semantic web technologies.
- Translate linked data into AI training sets using the OMOP CDM research format to systematically evaluate data quality (completeness, conformance, and plausibility) using the Layered Schemas process versus the transformation with existing methods.