Vision for Improving Interoperability for Eye Heath Data
Institute or Center: National Eye Institute (NEI)
Project: Vision for Improving Interoperability for Eye Heath Data
- Familiarity with standard health care terminologies, including SNOMED and LOINC and common data models (e.g. Observational Medical Outcomes Partnership (OMOP))
- Experience working with human research data, knowledge of data standards, and best practices
- Experience with data science techniques for handling large data sets and performing quality evaluation
- Demonstrated leadership, management and communication skills, and proven ability to build trust and form alliances with diverse stakeholders across different scientific fields, such as health disparities, big data analytics, statistics, and mathematics
About the position: The NEI Office of Data Science & Health Informatics (ODSHI) seeks a DATA Scholar to develop a strategy and lead community consensus building to improve ocular health care through data standardization. The scholar will:
- Build on community expertise of the Observational Health Data Sciences and Informatics (OHDSI) OMOP CDM to advance standard representation of ocular concepts.
- Identify the need for new standards or modifications to existing ones for improved, computable data representation.
- Create a publicly available central mapping resource that would allow transformation of vision data in disparate databases to the OMOP CDM to allow cross-cutting research using these multiple data sources.
About the work: Leveraging multiple databases is facilitated by CDMs, allowing each source to map data to existing standards (e.g. LOINC or SNOMED CT). However, not all ocular health data have been mapped to standards or included in CDMs. Improving the inclusion of ocular elements in a CDM will ensure that large studies include vision health data in future research.
Datasets involved: Clinical data recorded in a variety of EHRs will be used for terminology mapping and gap analysis.
Why this project matters: Recent studies suggest that the eye can tell us many things about a person’s health beyond sight, including risk for Alzheimer’s and heart disease. Advances in deep learning and machine learning have been made possible through the combination of multiple databases that have been designed for different purposes and with different terminologies and relational organization. Data standardization in ophthalmology will facilitate future research in diagnosing disease earlier and more easily.
Work Location: Remote; Bethesda, MD
Work environment: The scholar will work with a diverse team of data scientists, clinicians, policy makers, and researchers. The scholar will be supported through the NEI ODSHI, led by Kerry Goetz and the NEI Director, Michael Chiang. The scholar will also work closely with the Ocular Standards Working Group, comprised of clinicians, computer scientists, terminologists, and health services researchers.
To apply to this or other DATA Scholar positions, please see instructions here: datascience.nih.gov/data-scholars-2022.
This page last reviewed on April 7, 2022