Validating a Deep Learning Algorithm to Identify Patients with Glaucoma using Systemic Electronic Health Records
For healthcare systems, this provides a scalable, imaging-free pre-screening tool for glaucoma, though it is an incremental application of existing methods to a new dataset.
The study validated a deep learning model using only systemic EHR data to identify glaucoma patients, achieving AUROC 0.883 and PPV 0.657 on a held-out test set, with the highest prediction decile showing a 65.7% glaucoma diagnosis rate.
We evaluated whether a glaucoma risk assessment (GRA) model trained on All of Us national data can identify patients at high probability of glaucoma using only systemic electronic health records (EHR) at an independent institution. In this cross-sectional study, 20,636 Stanford patients seen from November 2013 to January 2024 were included (15% with glaucoma). A pretrained GRA model was fine-tuned on the Stanford cohort and tested on a held-out set using demographics, systemic diagnoses, medications, laboratory results, and physical examination measurements as inputs. The best model achieved AUROC 0.883 and PPV 0.657. Calibration was consistent with clinical risk: the highest prediction decile showed the greatest glaucoma diagnosis rate (65.7%) and treatment rate (57.0%). Performance improved with more trainable layers up to 15 and with additional data. An EHR-only GRA model may enable scalable and accessible pre-screening without specialized imaging.