Development of Portable Electronic Health Record Based Algorithms to Identify Individuals with Diabetic Retinopathy.

OBJECTIVES/AIMS: To develop, validate and implement algorithms to identify diabetic retinopathy (DR) cases and controls from electronic health care records (EHR)s.

METHODS: We developed and validated EHR-based algorithms to identify DR cases and individuals with type I or II diabetes without DR (controls) in three independent EHR systems: Vanderbilt University Medical Center Synthetic Derivative (VUMC), the VA Northeast Ohio Healthcare System (VANEOHS), and Massachusetts General Brigham (MGB). Cases were required to meet one of three criteria: 1) two or more dates with any DR ICD-9/10 code documented in the EHR, or 2) at least one affirmative health-factor or EPIC code for DR along with an ICD9/10 code for DR on a different day, or 3) at least one ICD-9/10 code for any DR occurring within 24 hours of an ophthalmology exam. Criteria for controls included affirmative evidence for diabetes as well as an ophthalmology exam.

RESULTS: The algorithms, developed and evaluated in VUMC through manual chart review, resulted in a positive predictive value (PPV) of 0.93 for cases and negative predictive value (NPV) of 0.97 for controls. Implementation of algorithms yielded metrics that were similar in VANEOHS (PPV=0.94; NPV=0.86) and lower in MGB (PPV=0.84; NPV=0.76). In comparison, the algorithm for DR implemented in Phenome-wide association study (PheWAS) in VUMC, yielded similar PPV (0.92) but substantially reduced NPV (0.48). Implementation of the algorithms to the Million Veteran Program identified over 62,000 DR cases with genetic data including 14,549 cases who identify as African American and 6,209 cases who identify as Hispanics.

CONCLUSIONS/INTERPRETATIONS: We demonstrate the robustness of the algorithms at three separate health-care centers, with all sites achieving a PPV of 0.84 or greater and substantially improved NPV than existing automated methods. We show EHR algorithms for DR are portable between separate EHR systems and also discuss lessons learned from these implementations. Algorithms reported here are advanced starting points. We strongly encourage independent validation and incorporation of features unique to each EHR to enhance algorithm performance for DR cases and controls.