

























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.
| Comments: | submitted to AMIA Annual Symposium 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.20921 [cs.LG] |
| (or arXiv:2604.20921v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.20921 arXiv-issued DOI via DataCite (pending registration) |
From: Sophia Wang [view email]
[v1]
Wed, 22 Apr 2026 05:07:20 UTC (1,336 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。