BriefGPT.xyz
Mar, 2024
在线临床时间序列多模态对比学习
Multi-Modal Contrastive Learning for Online Clinical Time-Series Applications
HTML
PDF
Fabian Baldenweg, Manuel Burger, Gunnar Rätsch, Rita Kuznetsova
TL;DR
利用先进的自监督多模式对比学习技术， 注重临床笔记和时间序列，我们引入了一种损失函数: 多模式邻域对比损失 (MM-NCL)，展示了我们方法在线预测任务中出色的线性验证和零样本表现。
Abstract
electronic health record
(EHR) datasets from
intensive care units
(ICU) contain a diverse set of data modalities. While prior works have successfully leveraged multiple modalities in supervised settings, we apply
→