A Real-World Data Solution to Understanding Uveitic Macular Edema

Uveitic macular edema (UME) – the leakage of fluid within retinal layers, is a common  complication of uveitis, or eye inflammation. This can lead to changes in vision, damage to the eye or permanent loss of vision, making early diagnosis and management crucial.

A variety of treatment options exist for UME, including steroids. However, such treatments often require regular injections to prevent the condition from progressing and often causing unwanted side effects. This highlights a need for alternative therapies and opportunities to better understand the most effective treatment plans that are based on patient characteristics. Analyzing curated, quality real-world data (RWD) can help us identify these potential therapies.

Finding Clues in Electronic Health Records

These variables can fill in the gap in UME research and treatment by helping to understand disease progression and patient outcomes.

A UME diagnosis is confirmed by performing an optical coherence tomography (OCT) or fundus fluorescein angiography (FFA). Results from both are documented in the clinician notes section of electronic health records (EHRs). These images can help provide a better understanding of the diagnosis, compared to diagnosis codes alone. 

Also noted in unstructured and semi-structured fields within EHRs are key outcomes, such as visual acuity (VA), central subfield thickness (CST) and intraocular pressure (IOP). These variables can fill in the gap in UME research and treatment by helping to understand disease progression and patient outcomes.

In order to extract these key insights, access to de-identified medical registry data, advanced data analysis technology, as well as clinical and data science expertise, are necessary. Verana Health’s partnership with the American Academy of Ophthalmology IRIS^Ⓡ Registry (Intelligent Research in Sight) allows access to nearly 80 million de-identified patients from 15,000 contributing clinicians. The company’s Medical team and data experts apply artificial intelligence-powered large language models and machine learning models to analyze patterns of language within clinical notes and signal key milestones that occur during the patient journey. The insights are referred to as Qdata^Ⓡ – research-ready, fit-for-purpose data modules.

Qdata Uveitic Macular Edema 

Verana Health recently launched Qdata Uveitic Macular Edema, which is an expansive, high-quality, real-world dataset with an average of nearly four years of follow-up data on more than 152,000 de-identified patients with UME. By offering critical insights into diagnosis accuracy, patient journey specifics, and treatment efficacy, this module can help accelerate therapy development and monitor real-world treatment patterns and outcomes to help improve the quality of life for patients.