文献速递眼底病与葡萄膜炎

预测早发型年龄相关性黄斑变性:一种机器学习方法

Predicting Early Onset of Age-Related Macular Degeneration: A Machine Learning Approach.
PubMed 文献 · Am J Ophthalmol · 2025-07-21

本研究利用三级眼科中心1999至2023年930例AMD患者数据(392例早发型、538例晚发型)及All of Us数据集验证,采用无监督聚类与监督机器学习模型,发现炎症性关节病、高血压和血脂异常是早发型AMD最具预测性的特征,模型预测准确率约76%。

要点

  • 聚类识别出2个患者组,其中1组以早发型AMD为主(占93.08%),该组炎症性关节病、高血压和血脂异常发生率较高。
  • 多种监督机器学习模型基于55岁前诊断的早期共病预测早发型AMD,准确率约76%。
  • 在All of Us验证数据集中,原发性高血压(OR 5.80)、类风湿关节炎(OR 4.61)和高脂血症(OR 5.16)与早发型AMD强关联。

核心结论

  • 在眼科评估中筛查高血压、血脂异常和炎症性关节病可能有助于更早发现和干预AMD。

研究设计与样本

  • 回顾性病例对照研究,使用三级眼科中心数据集(930例AMD患者,392例早发型,538例晚发型)和All of Us数据集进行验证(560至580例早发型AMD患者,560至580例匹配的无AMD对照)。
  • 收集三级医院1999至2023年AMD患者健康记录,以及All of Us研究项目(美国成人全国性纵向队列,数据收集时间2016年6月至2025年2月)数据。
  • 对三级眼科中心数据集采用统一流形近似与投影(UMAP)进行无监督聚类以识别患者亚组,并训练梯度提升决策树(GBDT)、逻辑回归和随机森林等监督机器学习模型预测早发型AMD。
  • 模型性能采用受试者工作特征曲线下面积(AUC)评估,特征重要性在树模型中采用基尼指数评估、在逻辑回归中采用系数大小评估;在All of Us验证数据集中采用2×2列联表估计与早发型AMD相关共病的比值比(OR)。

主要发现

  • 聚类识别出2个不同患者组,其中1组以早发型AMD为主(占93.08%),该组炎症性关节病、高血压和血脂异常发生率较高。
  • 多种监督机器学习模型基于55岁前诊断的早期共病预测早发型AMD,准确率约76%。
  • 与聚类分析一致,监督机器学习模型分析识别出炎症性关节病、高血压和血脂异常为最具预测性的特征。
  • 在All of Us验证数据集中,原发性高血压(OR 5.80,95%CI 4.25-7.93,P<.05)、类风湿关节炎(OR 4.61,95%CI 1.55-13.72,P<.05)和高脂血症(OR 5.16,95%CI 3.76-7.08,P<.05)与早发型AMD强关联。

临床怎么用

  • 作者认为,在眼科评估中筛查高血压、血脂异常和炎症性关节病可能有助于更早发现和干预AMD。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

PURPOSE: Develop a machine learning model that predicts early-onset AMD based on early patient comorbidities DESIGN: Retrospective case-control study. SUBJECTS: This study used 2 datasets: a tertiary eye care center dataset (930 AMD patients, 392 early-onset, 538 late-onset) and the All of Us dataset for validation (560-580 AMD patients early-onset, 560-580 matched controls without AMD). METHODS: Health records of AMD patients from a tertiary hospital (1999-2023) and the All of Us Research Program, a nationwide longitudinal cohort of U.S. adults (data collected 6/2016-2/2025) were collected. Unsupervised clustering using Uniform Manifold Approximation and Projection (UMAP) was performed on the tertiary eye care center dataset to identify distinct patient subgroups. Supervised machine learning models, including gradient-boosted decision trees (GBDT), logistic regression, and random forests, were trained to predict early-onset AMD. MAIN OUTCOMES MEASURES: Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), while feature importance was assessed using the Gini index for tree-based models and coefficient magnitudes for logistic regression. Additionally, odds ratios for comorbidities associated with early-onset AMD were estimated using 2 × 2 contingency tables in the validation dataset (All of Us). RESULTS: Clustering identified 2 distinct patient groups, with 1 (93.08% early-onset AMD dominated) showing high rates of inflammatory joint disorders, hypertension, and dyslipidemia. Multiple supervised machine learning models achieved ∼76% accuracy in predicting early-onset AMD from early comorbidities (diagnosed before age of 55). Like clustering, analysis of supervised machine learning models identified inflammatory joint disorders, hypertension, and dyslipidemia as the most predictive features. These comorbidities were validated using the All of Us dataset, with essential hypertension (OR: 5.80, 95% CI: [4.25-7.93], P < .05), rheumatoid arthritis (OR: 4.61, 95% CI: [1.55-13.72], P < .05), and hyperlipidemia (OR: 5.16, 95% CI: [3.76-7.08], P < .05) showing strong associations with early-onset AMD. CONCLUSION: Screening hypertension, dyslipidemia, and inflammatory joint disorders in ophthalmologic evaluations may enable earlier AMD detection and intervention.

来源:Am J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Wu E, Hasan N, Vupparaboina S, et al. Predicting Early Onset of Age-Related Macular Degeneration: A Machine Learning Approach. Am J Ophthalmol. 2025. PMID: 40701376. doi:10.1016/j.ajo.2025.07.020

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。