SUMMARY
Guoqian Jiang, M.D., Ph.D., conducts research on biomedical terminologies and ontologies, data standards, and common data elements and common data models for clinical studies.
Dr. Jiang has specifically focused on these subareas of research:
- Semantic and explainable artificial intelligence (AI) in health care
- A Fast Healthcare Interoperability Resources (FHIR)-based data access framework for clinical and translational research
- Quality auditing of large-scale biomedical terminologies and ontologies and clinical data models
- Electronic health record (EHR)-driven phenotype algorithm authoring and execution
- Semantic interoperability and optimization of integrated clinical data repositories (for example, i2b2, OMOP, PCORnet and FHIR)
- Medical device safety and effectiveness evaluation using real-world evidence
Dr. Jiang is a member of the American Medical Informatics Association. He has served as a reviewer for a number of core journals and proceedings on biomedical informatics. He has also served as a member of scientific program committees for several national and international conferences and workshops.
Focus areas
- Enabling the semantics of FHIR and terminologies for clinical and translational research. The goal is to design, develop and evaluate a novel informatics platform known as FHIRCat. This platform leverages semantic web and linked data technologies, FHIR models and profiles, and ontologies for effective standards-based data integration and distributed analytics that enable high-quality reproducible clinical and translational research.
- Phenotype execution and modeling architecture (PhEMA). The goal is to develop semantic tools for supporting EHR-driven phenotype algorithm authoring and execution. We will extend, scale and evaluate PhEMA by developing novel methods and tools for deep phenotyping from EHR data, including (1) standards-based authoring and execution of temporal phenotypes using clinical quality language, (2) integration of FHIR natural language processing extensions and temporal reasoning, (3) dynamic and interpretable hybrid learning for temporal phenotype discovery, and (4) iterative usability evaluation of the PhEMA workbench.
- LexEVS terminology service and tooling. LexEVS provides a common terminology model and open access to a wide range of terminologies, terminology value sets and cross-terminology mappings needed by the National Cancer Institute and its partners. LexEVS provides a collection of program interfaces, affording users and developers open access to both controlled terminologies available from the NCI and other supported terminologies.
- Development of an FHIR-based data access framework. In collaboration with the National Center for Data to Health (CD2H), Dr. Jiang is leading an effort to develop an FHIR-based data access framework for clinical and translational research. CD2H accelerates advancements in informatics by using findable, accessible, interoperable and reusable (FAIR) principles to promote collaboration across the Clinical and Translational Science Awards (CTSA) Program community. CD2H coordinates and contributes to many FHIR initiatives with the goal of making its adoption for translational research useful, easy and a best practice. The ultimate goal is to make data management and transformation tasks in translational research simpler and less resource intensive.
- Center of Excellence in Regulatory Science and Innovation (CERSI) collaboration. Dr. Jiang is leading a collaborative effort with Mayo Clinic, Yale University and the U.S. Food and Drug Administration (FDA) to demonstrate the value of unique device identifiers (UDIs) and common data models in improving the medical device recall process and facilitating medical device effectiveness and safety evaluation research. The UDI system for medical devices has remarkable potential to improve clinical care, including effective device recall management.
Dr. Jiang also has been involved as a co-investigator in several other projects, including:
- National Center for Biomedical Ontology project
- CTSA Adverse Event Phenotype Ontology project
- Pharmacogenomics Research Network (PGRN) Phenotype Ontology project
- Electronic Medical Records and Genomics (eMERGE) Network
- Strategic Health IT Advanced Research Projects (SHARP) — Research Focus Area 4: Secondary Use of Electronic Health Record Data
- Cancer Biomedical Informatics Grid Vocabulary Knowledge Center
Significance to patient care
Clinical data and unstructured information from many providers is currently not standardized. Ontologies and controlled terminologies provide the infrastructure for the transformation of nonstandard patient data into standards-conforming, comparable information suitable for large-scale analyses, inferencing and integration of disparate health data. Dr. Jiang's research on biomedical informatics, particularly on the building of infrastructure and innovative technologies to achieve high-quality biomedical terminologies and clinical data standards, will facilitate the standardization of electronic health records systems and improve the quality, safety and efficiency of health care.