Recurrent Neural Network on PICTURE Model

TL;DR

This paper implements a recurrent neural network to predict critical events in ICU patients using the PICTURE model, aiming to improve upon existing XGBoost benchmarks for patient deterioration prediction.

Contribution

It introduces a deep learning approach with RNNs for ICU event prediction, benchmarking its performance against the established XGBoost model.

Findings

RNN achieves comparable or better prediction accuracy than XGBoost.

Deep learning models can effectively predict ICU patient deterioration.

The study provides a new benchmark for ICU event prediction models.

Abstract

Intensive Care Units (ICUs) provide critical care and life support for most severely ill and injured patients in the hospital. With the need for ICUs growing rapidly and unprecedentedly, especially during COVID-19, accurately identifying the most critical patients helps hospitals to allocate resources more efficiently and save more lives. The Predicting Intensive Care Transfers and Other Unforeseen Events (PICTURE) model predicts patient deterioration by separating those at high risk for imminent intensive care unit transfer, respiratory failure, or death from those at lower risk. This study aims to implement a deep learning model to benchmark the performance from the XGBoost model, an existing model which has competitive results on prediction.