Predicting Patient State-of-Health using Sliding Window and Recurrent Classifiers

TL;DR

This paper compares sliding window and recurrent neural network classifiers for predicting patient health states in ICUs, showing slight improvements with RNNs on most targets, aiming to enhance alarm accuracy and response times.

Contribution

It introduces a comparative analysis of sliding window and recurrent classifiers for ICU patient health prediction, highlighting the potential benefits of RNNs.

Findings

RNNs slightly outperform sliding window methods on three of four health targets

Recurrent classifiers show promise for improving ICU alarm systems

Study suggests RNNs can enhance patient monitoring accuracy

Abstract

Bedside monitors in Intensive Care Units (ICUs) frequently sound incorrectly, slowing response times and desensitising nurses to alarms (Chambrin, 2001), causing true alarms to be missed (Hug et al., 2011). We compare sliding window predictors with recurrent predictors to classify patient state-of-health from ICU multivariate time series; we report slightly improved performance for the RNN for three out of four targets.