集成模型可高精度筛查重症监护室脑膜炎，排除风险效果极佳。
Ensemble Deep Learning Models for Early Detection of Meningitis in ICU: Multi-center Study
- 融合随机森林、LightGBM与深度神经网络构建堆叠集成模型
- 内部测试集阴性预测值超99.9%，在类别极度不平衡下仍有效
- 适合急诊与重症监护室作为排除诊断的初筛工具
结合随机森林、LightGBM和深度神经网络的堆叠集成模型在内部测试集中表现良好，即使在严重类别不平衡的情况下，阴性预测值仍超过99.9%。尽管在外部eICU队列中的性能低于内部测试集，但敏感性依然稳健。因此，该集成模型在经过进一步前瞻性多中心验证后，可能成为急诊科和重症监护室中用于排除脑膜炎的筛查工具。
原文摘要 · Abstract (English)
The stacking ensemble combining RF, LightGBM, and DNN performed well on internal test sets, exhibiting an NPV greater than 99.9% even with substantial class imbalance. While performance was lower on the external eICU cohort compared to the internal test sets, sensitivity remained robust. Therefore, the stacking ensemble may serve as a rule-out screening option for ERs and ICUs after additional prospective multi-site validation studies for its efficacy in real-world.
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。