Validating a Deep Learning Algorithm to Identify Patients with Glaucoma using Systemic Electronic Health Records

TL;DR

This study validates a deep learning model trained on national data to identify glaucoma risk using only systemic electronic health records, achieving high accuracy and potential for scalable pre-screening.

Contribution

It demonstrates that an EHR-only deep learning model can effectively predict glaucoma risk, enabling accessible pre-screening without specialized imaging.

Findings

Achieved AUROC of 0.883 in identifying glaucoma.

Calibration aligned with clinical risk, with high diagnosis and treatment rates in top deciles.

Model performance improved with more trainable layers and additional data.

Abstract

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.