Early prediction of respiratory failure in the intensive care unit

TL;DR

This paper presents an early warning system using machine learning to predict moderate to severe respiratory failure up to 8 hours in advance in ICU patients, outperforming traditional clinical decision methods.

Contribution

The study introduces a novel machine learning-based early prediction system for respiratory failure in ICU patients, with a user-friendly interface for model diagnostics.

Findings

System predicts respiratory failure up to 8 hours early

Outperforms traditional clinical decision-making baseline

Provides visual model diagnostics

Abstract

The development of respiratory failure is common among patients in intensive care units (ICU). Large data quantities from ICU patient monitoring systems make timely and comprehensive analysis by clinicians difficult but are ideal for automatic processing by machine learning algorithms. Early prediction of respiratory system failure could alert clinicians to patients at risk of respiratory failure and allow for early patient reassessment and treatment adjustment. We propose an early warning system that predicts moderate/severe respiratory failure up to 8 hours in advance. Our system was trained on HiRID-II, a data-set containing more than 60,000 admissions to a tertiary care ICU. An alarm is typically triggered several hours before the beginning of respiratory failure. Our system outperforms a clinical baseline mimicking traditional clinical decision-making based on pulse-oximetric oxygen saturation and the fraction of inspired oxygen. To provide model introspection and diagnostics, we developed an easy-to-use web browser-based system to explore model input data and predictions visually.