Large Neural Network Based Detection of Apnea, Bradycardia and Desaturation Events

TL;DR

This paper presents a large neural network approach for detecting apnea, bradycardia, and desaturation events in newborns, demonstrating effective performance with limited and unbalanced training data suitable for clinical use.

Contribution

It introduces a neural network model that requires minimal parameter tuning and performs well with limited, unbalanced data, advancing clinical detection of ABD events.

Findings

Neural network outperforms two state-of-the-art algorithms.

Effective detection with limited training data.

Suitable for clinical application.

Abstract

Apnea, bradycardia and desaturation (ABD) events often precede life-threatening events including sepsis in newborn babies. Here, we explore machine learning for detection of ABD events as a binary classification problem. We investigate the use of a large neural network to achieve a good detection performance. To be user friendly, the chosen neural network does not require a high level of parameter tuning. Furthermore, a limited amount of training data is available and the training dataset is unbalanced. Comparing with two widely used state-of-the-art machine learning algorithms, the large neural network is found to be efficient. Even with a limited and unbalanced training data, the large neural network provides a detection performance level that is feasible to use in clinical care.