仅用电子病历数据，就能高效识别青光眼高风险患者。
Validating a Deep Learning Algorithm to Identify Patients with Glaucoma using Systemic Electronic Health Records
- 用全国健康数据训练模型，在斯坦福数据上微调并验证。
- 模型准确率AUROC达0.883，高风险人群确诊率达65.7%。
- 无需眼科影像，适合大规模早期筛查，尤其基层医疗。
本研究评估了基于美国全民健康数据训练的青光眼风险评估（GRA）模型，能否仅通过系统性电子健康记录（EHR）在独立机构中识别高风险患者。横断面研究纳入20,636名斯坦福患者（2013年11月至2024年1月），其中15%确诊为青光眼。使用人口学、系统性疾病诊断、用药记录、检验结果及体格检查数据作为输入，对预训练的GRA模型进行微调，并在保留测试集上评估。最优模型达到AUROC 0.883，阳性预测值（PPV）0.657。校准良好：预测得分最高十等分组的青光眼确诊率高达65.7%，治疗率57.0%。模型性能随可训练层数增加至15层而提升，且数据越多效果越好。仅依赖EHR的GRA模型有望实现无需专业成像的可扩展、可及的前期筛查。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。