文献速递眼底病与葡萄膜炎

利用基线临床特征通过机器学习预测葡萄膜炎复发过程

Machine Learning for Predicting Recurrent Course in Uveitis Using Baseline Clinical Characteristics.
PubMed 文献 · Invest Ophthalmol Vis Sci · 2025-01-01

基于Ocular Autoimmune Systemic Inflammatory Infectious Study登记库的966例(1432眼)葡萄膜炎患者进行回顾性分析,训练三种机器学习分类器预测复发风险。随机森林模型测试准确度最高(0.77),特异度高(0.93)但敏感度有限(0.44)。玻璃体混浊、晶状体后细胞和非感染性病因是重要预测因子。

要点

  • 随机森林模型在识别葡萄膜炎低复发风险患者方面特异度高达0.93。
  • 但敏感度仅为0.44,预测罕见事件仍面临挑战。
  • 玻璃体混浊、晶状体后细胞和非感染性病因是复发关键预测因子。

核心结论

  • 机器学习模型特别是随机森林能有效识别葡萄膜炎低复发风险患者,具有高特异度。
  • 但敏感度仍有限,凸显在异质性葡萄膜炎人群中预测低频事件的挑战。

研究设计与样本

  • 基于Ocular Autoimmune Systemic Inflammatory Infectious Study登记库的回顾性分析,纳入966例(1432眼)葡萄膜炎患者。
  • 训练随机森林、eXtreme Gradient Boosting和径向基函数支持向量分类器三种机器学习分类器,输入预处理后的基线人口学和临床数据。
  • 通过双变量分析并经错误发现率校正选择预测因子,使用网格搜索结合五折分层交叉验证优化模型。
  • 在留出测试集上使用准确度、敏感度、特异度、受试者工作特征曲线下面积和Shapley加性解释值评估模型性能。

主要发现

  • 随机森林模型测试准确度最高(0.77),识别复发的特异度高(0.93)但敏感度有限(0.44)。
  • eXtreme Gradient Boosting和径向基函数支持向量分类器准确度相近(分别为0.73和0.74),但敏感度略低。
  • Shapley加性解释分析识别玻璃体混浊、晶状体后细胞和非感染性病因为关键预测因子。
  • 学习曲线表明模型性能在现有样本量下趋于稳定,提示训练数据充足。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 敏感度仍有限,凸显在异质性葡萄膜炎人群中预测低频事件的挑战。

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: We developed and evaluated machine learning models for predicting the risk of recurrent uveitis using baseline clinical characteristics, to inform clinical decision-making and risk stratification. METHODS: A retrospective analysis was conducted using the Ocular Autoimmune Systemic Inflammatory Infectious Study registry, including 966 patients (1432 eyes) with uveitis. Three machine learning classifiers-random Forest, eXtreme Gradient Boosting, and radial basis function support vector classifier-were trained on preprocessed baseline demographic and clinical data. Predictors were selected through bivariate analysis with false discovery rate correction. Models were optimized using grid search with five-fold stratified cross-validation. Performance was evaluated on a hold-out test set using accuracy, sensitivity, specificity, area under the receiver operating characteristic curve, and Shapley additive explanations values for feature importance. RESULTS: The random Forest model achieved the highest test accuracy (0.77), with high specificity (0.93) but modest sensitivity (0.44) for identifying recurrences. eXtreme Gradient Boosting and radial basis function support vector classifier showed comparable accuracies (0.73 and 0.74, respectively) but slightly lower sensitivities. Shapley additive explanation analysis identified vitreous haze, retrolental cells, and noninfectious etiology as key predictors. Learning curves indicated that model performance stabilized with the available sample size, suggesting adequate training data. CONCLUSIONS: Machine learning models, particularly random Forest, effectively identified patients at low risk of uveitis recurrence, offering high specificity. However, sensitivity remained limited, highlighting challenges in predicting infrequent events in a heterogeneous disease population.

来源:Invest Ophthalmol Vis Sci,查看原文。版权归原作者所有。

引用

  1. Rojas-Carabali W, Cifuentes-González C, Utami A, et al. Machine Learning for Predicting Recurrent Course in Uveitis Using Baseline Clinical Characteristics. Invest Ophthalmol Vis Sci. 2025. PMID: 40862668. doi:10.1167/iovs.66.11.67

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。