Algorithm Captures Predictive Glaucoma Data

Researchers at the Kellogg Eye Center of the University of Michigan led by Joshua D. Stein, MD, MS, set out to determine what method other than assessing administrative billing codes can researchers apply, using big data, to accurately identify patients with ocular diseases of interest. In this study of the electronic health records of 122,339 eye-care recipients, a newly developed and validated algorithm that searches structured and unstructured data in electronic health records (EHRs) successfully detected most patients with and without exfoliation syndrome (XFS), a common and debilitating cause of glaucoma.

This study was a retrospective analysis of the EHR data of patients who received eye care at participating academic medical centers between August 2012 and August 2017. The algorithm was trained to search for evidence of XFS among a sample of patients with and without XFS (n=200) by reviewing ICD-9 or ICD-10 billing codes, the patient’s problem list, and text within the ocular examination section and unstructured data in the EHR. The EHR data of all patients were run through the algorithm to generate an XFS probability score for each patient.

Validated by glaucoma specialists, the algorithm had a positive predictive value of 95% and a negative predictive value of 100%. When there was ICD-9 billing code documentation of XFS (86%) or ICD-10 billing code documentation of XFS (96%), evidence of XFS was also recorded elsewhere in the EHR. Conversely, when there was clinical examination or free-text evidence of XFS, it was documented with ICD-9 codes only approximately 40% of the time and even less often with ICD-10 codes. The researchers concluded that algorithms may enhance the ability of researchers to make use of big data to study patients with ocular diseases.