Machine Learning Methods for Neonatal Heart Rate Prediction using Respiratory Signals

Abstract

Approximately 10% of neonates require assistance transitioning from intrauterine to extrauterine environments. Applying these interventions requires accurate monitoring of vitals such as heart and respiratory rates. However, the current methods of these vital measurements require many devices to be attached to the neonates, resulting in rather intrusive methods that could even harm the neonates if not administered properly. This pilot study investigates the possibility of applying signal processing along with automated machine learning and deep learning models to estimate heart rate from respiratory signals recorded using inductance bands. The best machine learning model can get an average MAE of 10.15 BPM, and the best deep learning model at 10.88 BPM. The advantage of applying such a method would be reducing devices attached to neonates while preserving estimation accuracy.