论文标题
将生理时间序列和临床笔记与深度学习相结合，以改善ICU死亡率预测
Integrating Physiological Time Series and Clinical Notes with Deep Learning for Improved ICU Mortality Prediction
论文作者
论文摘要
重症监护室电子健康记录（ICU EHRS）存储有关患者的多模式数据，包括临床笔记，稀疏和不规则采样的生理时间序列，实验室结果等。迄今为止，大多数旨在从ICU EHR数据中学习预测模型的方法都集中在单个模态上。在本文中，我们利用了最近提出的插值预测深度学习体系结构（Shukla和Marlin 2019），作为探索生理时间序列数据和临床注释如何将其集成到统一死亡率预测模型中的基础。我们研究了早期和晚期融合方法，并证明了临床文本和生理数据的相对预测价值如何随着时间而变化。我们的结果表明，晚期融合方法可以在孤立的单个模态上提供统计学上的死亡率预测性能的显着改善。
Intensive Care Unit Electronic Health Records (ICU EHRs) store multimodal data about patients including clinical notes, sparse and irregularly sampled physiological time series, lab results, and more. To date, most methods designed to learn predictive models from ICU EHR data have focused on a single modality. In this paper, we leverage the recently proposed interpolation-prediction deep learning architecture(Shukla and Marlin 2019) as a basis for exploring how physiological time series data and clinical notes can be integrated into a unified mortality prediction model. We study both early and late fusion approaches and demonstrate how the relative predictive value of clinical text and physiological data change over time. Our results show that a late fusion approach can provide a statistically significant improvement in mortality prediction performance over using individual modalities in isolation.
