MS-MLB：基于血液的 MS 分类开放机器学习基准
原标题：MS-MLB: An Open Machine Learning Benchmark for Blood-Based MS Classification
AI 摘要
arXiv 发布了一项名为 MS-MLB 的开放机器学习基准，用于基于全血 RNA 表达数据的多发性硬化症（MS）分类研究。该基准使用公共 GSE17048 数据集，在防泄漏的共享流程中评估多种算法，并包含嵌套交叉验证、独立测试集等。结果显示梯度提升模型在测试集上取得最佳 MS 研究评分（93.83），但该评分仅用于研究比较，未经临床验证。
正文节选
Computer Science > Machine Learning Title:MS-MLB: An Open Machine Learning Benchmark for Blood-Based MS Classification View PDF HTML (experimental) Abstract:Multiple sclerosis (MS) is diagnosed through clinical assessment, magnetic resonance imaging, laboratory evidence when appropriate, and exclusion of better explanations. Blood RNA expression data may contain disease associated immune signal, but a blood RNA classifier cannot be treated as a replacement for clinical diagnosis. Thi