论文标题
暂时的卷积网络，用于重症监护病房的住宿时间长度
Temporal Pointwise Convolutional Networks for Length of Stay Prediction in the Intensive Care Unit
论文作者
论文摘要
越来越多的患者需求和预算限制的压力使医院的床位管理成为临床人员的每日挑战。最关键的是将资源过度重症监护室（ICU）床的有效分配给需要生活支持的患者。解决此问题的核心是知道当前的ICU患者可能会停留多长时间。在这项工作中，我们基于时间卷积和点旋（1x1）卷积的组合提出了一个新的深度学习模型，以解决EICU和MIMIC-IV重症监护数据集上的停留预测任务。该模型（我们称为时间旋转卷积（TPC））是专门设计的，目的是通过电子健康记录（例如偏斜，不规则采样和缺少数据）来减轻共同的挑战。在此过程中，我们已经在常用的长期术语内存（LSTM）网络和称为变压器的多头自我注意力网络中获得了18-68％（指标和数据集）的显着性能优势。通过添加死亡率预测作为副任务，我们可以进一步提高绩效，从而导致预测剩余的住院时间的平均绝对偏差为1.55天（EICU）和2.28天（模仿IV）。
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.
