arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.09483cs.LGcs.AIstat.ML
收藏

时间逐点卷积网络用于重症监护病房住院时间预测

Temporal Pointwise Convolutional Networks for Length of Stay Prediction in the Intensive Care Unit

University of Cambridge(剑桥大学);Microsoft Research(微软研究院)

Emma Rocheteau, Pietro Liò, Stephanie Hyland

摘要:

不断增长的患者需求和预算限制的压力使医院床位管理成为临床工作人员的日常挑战。最关键的是有效地将资源密集的重症监护病房(ICU)病床分配给需要生命支持的患者。解决这个问题的核心是了解目前的ICU患者可能会在病房呆多久。在这项工作中,我们提出了一种新的深度学习模型,该模型基于时间卷积和逐点(1x 1)卷积的组合,以解决eICU和MIMIC-IV重症监护数据集上的住院时间预测任务。该模型-我们称之为时间逐点卷积(TPC)-专门设计用于缓解电子健康记录的常见挑战,例如偏斜,不规则采样和缺失数据。在这样做的过程中,我们已经实现了18-68%的显着性能优势(依赖于指标和数据集),超过了常用的长短期记忆(LSTM)网络和称为Transformer的多头自注意力网络。通过将死亡率预测作为副任务,我们可以进一步提高性能,导致预测剩余住院时间的平均绝对偏差为1.55天(eICU)和2.28天(MIMIC-IV)。

英文摘要:

The pressure of ever-increasing patient demand and budget restrictions make hospital bed management a daily challenge for clinical staff. Most critical is the efficient allocation of resource-heavy Intensive Care Unit (ICU) beds to the patients who need life support. Central to solving this problem is knowing for how long the current set of ICU patients are likely to stay in the unit. In this work, we propose a new deep learning model based on the combination of temporal convolution and pointwise (1x1) convolution, to solve the length of stay prediction task on the eICU and MIMIC-IV critical care datasets. The model - which we refer to as Temporal Pointwise Convolution (TPC) - is specifically designed to mitigate common challenges with Electronic Health Records, such as skewness, irregular sampling and missing data. In doing so, we have achieved significant performance benefits of 18-68% (metric and dataset dependent) over the commonly used Long-Short Term Memory (LSTM) network, and the multi-head self-attention network known as the Transformer. By adding mortality prediction as a side-task, we can improve performance further still, resulting in a mean absolute deviation of 1.55 days (eICU) and 2.28 days (MIMIC-IV) on predicting remaining length of stay.

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。

↑