arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1811.04752cs.LGstat.ML
收藏

缺失数据的学习表示用于预测患者结局

Learning Representations of Missing Data for Predicting Patient Outcomes

Brandon Malone, Alberto Garcia-Duran, Mathias Niepert

摘要:

从电子健康记录(EHR)中提取可操作的见解对传统的机器学习方法提出了几个挑战。患者之间往往缺少相关数据;数据有多种形式,如多变量时间序列、自由文本和分类人口统计信息;患者之间的重要关系可能难以检测;以及许多其他数据。在这项工作中,我们提出了一种新的方法来解决这前三个挑战,使用基于消息传递的表示学习计划。我们表明,我们提出的方法是有竞争力的,或优于最先进的预测住院死亡率(二进制分类),住院时间(回归)和出院目的地(多类分类)。

英文摘要:

Extracting actionable insight from Electronic Health Records (EHRs) poses several challenges for traditional machine learning approaches. Patients are often missing data relative to each other; the data comes in a variety of modalities, such as multivariate time series, free text, and categorical demographic information; important relationships among patients can be difficult to detect; and many others. In this work, we propose a novel approach to address these first three challenges using a representation learning scheme based on message passing. We show that our proposed approach is competitive with or outperforms the state of the art for predicting in-hospital mortality (binary classification), the length of hospital visits (regression) and the discharge destination (multiclass classification).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑