English

Predicting Length of Stay in the Intensive Care Unit with Temporal Pointwise Convolutional Networks

Machine Learning 2020-11-16 v2 Machine Learning

Abstract

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 critical care dataset. The model - which we refer to as Temporal Pointwise Convolution (TPC) - is specifically designed to mitigate for common challenges with Electronic Health Records, such as skewness, irregular sampling and missing data. In doing so, we have achieved significant performance benefits of 18-51% (metric dependent) over the commonly used Long-Short Term Memory (LSTM) network, and the multi-head self-attention network known as the Transformer.

Keywords

Cite

@article{arxiv.2006.16109,
  title  = {Predicting Length of Stay in the Intensive Care Unit with Temporal Pointwise Convolutional Networks},
  author = {Emma Rocheteau and Pietro Liò and Stephanie Hyland},
  journal= {arXiv preprint arXiv:2006.16109},
  year   = {2020}
}

Comments

Machine Learning for Health (ML4H) at NeurIPS 2020 - Extended Abstract. Also accepted for spotlight presentation at Healthcare Systems, Population Health, and the Role of Health-Tech (HSYS) at ICML 2020. The full length version of this paper can be found at arXiv:2007.09483