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.
翻译:重症护理股电子健康记录(ICU EHRs)存储了有关病人的多式联运数据,包括临床笔记、稀少和不定期抽样的生理时间序列、实验室结果等等。迄今为止,从ICU EHR数据中学习预测模型的大多数方法都集中在单一模式上。在本文中,我们利用最近提议的内插渗透深层学习结构(Shukla和Marlin 2019)作为基础,探讨如何将生理时间序列数据和临床笔记纳入统一的死亡率预测模型中。我们研究了早期和晚期的聚合方法,并展示临床文本和生理数据相对预测值随时间变化。我们的结果显示,迟融合方法可以在统计上显著改善死亡率预测绩效,而不是单独使用单个模式。