用常规临床数据提升慢性肾病早期分类准确率
NORA: A Nephrology-Oriented Representation Learning Approach Towards Chronic Kidney Disease Classification
- 基于电子病历中的非肾科变量，通过对比学习生成患者表征
- 在本地和公开数据集上均提升早期肾病分类的F1分数
- 适合关注慢病筛查与医疗资源有限场景的研究者
慢性肾病（CKD）影响全球数百万人，但其早期检测仍具挑战性，尤其在门诊环境中缺乏实验室肾功能生物标志物。本文研究了常规收集的非肾科临床变量（如人口统计学、共病情况、尿检结果）对CKD分类的预测潜力。提出一种肾病导向表示学习方法NORA，结合监督对比学习与非线性随机森林分类器。NORA首先从表格型电子病历数据中提取具有判别性的患者表征，用于下游CKD分类任务。在来自里弗赛德肾病医师诊所的临床电子病历数据集上评估，结果显示NORA显著提升类别可分性和整体分类性能，尤其增强了早期阶段CKD的F1分数。此外，在UCI CKD数据集上验证了其泛化能力，证明其在不同患者群体中均能有效进行肾病风险分层。
原文摘要 · Abstract (English)
Chronic Kidney Disease (CKD) affects millions of people worldwide, yet its early detection remains challenging, especially in outpatient settings where laboratory-based renal biomarkers are often unavailable. In this work, we investigate the predictive potential of routinely collected non-renal clinical variables for CKD classification, including sociodemographic factors, comorbid conditions, and urinalysis findings. We introduce the Nephrology-Oriented Representation leArning (NORA) approach, which combines supervised contrastive learning with a nonlinear Random Forest classifier. NORA first derives discriminative patient representations from tabular EHR data, which are then used for downstream CKD classification. We evaluated NORA on a clinic-based EHR dataset from Riverside Nephrology Physicians. Our results demonstrated that NORA improves class separability and overall classification performance, particularly enhancing the F1-score for early-stage CKD. Additionally, we assessed the generalizability of NORA on the UCI CKD dataset, demonstrating its effectiveness for CKD risk stratification across distinct patient cohorts.
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。