# Improving Quality of Electronic Health Record Ophthalmic Data for Big Data Analytics

> **NIH NIH R21** · OREGON HEALTH & SCIENCE UNIVERSITY · 2020 · $231,000

## Abstract

PROJECT SUMMARY
The widespread adoption of EHRs has enabled the collection of massive amounts of digital ophthalmic data
which have great potential for secondary use in research, quality improvement, and clinical decision support.
While the amount of digital ophthalmic data recorded in the EHR is substantial and could be analyzed using
the latest techniques for big data, questions about the quality of the data are a barrier to its reuse. Now that the
American Academy of Ophthalmology has aggregated digital ophthalmic data from the EHR into the IRIS
Registry, data quality is even more imperative for reaching the potential of the registry. To date, there has not
be a comprehensive evaluation of the data quality of digital ophthalmic data, nor have there been any solutions
for improving its quality. These are important gaps that will limit the utility of EHR data as a tool for knowledge
discovery in ophthalmology. The goal of this grant is to assess the quality of digital ophthalmic exam data in
order to improve its ability to be reused for research. Our hypothesis is that studying the variability of data
quality in large datasets will provide insights into improving its quality. The first aim employs an established
framework for data quality analysis to assess the intrinsic quality of a single institution’s EHR data as well as its
fitness for use--the ability to be applied to a particular research scenario. In this proposal, we are evaluating the
data’s ability to identify patient cohorts for clinical trials and to accurately calculate outcome based clinical
quality measures. The variability in data’s quality and fitness among providers, subspecialties, diagnoses, and
visit types will be analyzed. The second aim validates the analysis of the first aim by repeating it for all of the
ophthalmic data in the IRIS Registry. For this analysis, the differences in quality and fitness between
institutions and EHR vendors will also be assessed, along with the barriers to data quality and reuse. For both
aims, ophthalmology experts will review the results to make recommendations for improving data quality and
utility for digital ophthalmic data. In the future, these recommendations will provide a direction for correcting
these quality issues and for ultimately advancing knowledge discovery in ophthalmic care.

## Key facts

- **NIH application ID:** 9953684
- **Project number:** 1R21EY031443-01
- **Recipient organization:** OREGON HEALTH & SCIENCE UNIVERSITY
- **Principal Investigator:** Michelle Hribar
- **Activity code:** R21 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2020
- **Award amount:** $231,000
- **Award type:** 1
- **Project period:** 2020-05-01 → 2022-04-30

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/9953684

## Citation

> US National Institutes of Health, RePORTER application 9953684, Improving Quality of Electronic Health Record Ophthalmic Data for Big Data Analytics (1R21EY031443-01). Retrieved via AI Analytics 2026-05-23 from https://api.ai-analytics.org/grant/nih/9953684. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*