Forecasting respiratory collapse: theory and practice for averting life-threatening infant apneas

Abstract

Apnea of prematurity is a common disorder of respiratory control among preterm infants, with potentially serious adverse consequences on infant development. We review the capability for automatically assessing apnea risk and predicting apnea episodes from multimodal physiological measurements, and for using this knowledge to provide timely therapeutic intervention. We also review other, similar clinical domains of respiratory distress assessment and prediction in the hope of gaining useful insights. We propose an algorithmic framework for constructing discriminative feature vectors from physiological measurements, and for building robust and effective statistical models for apnea assessment and prediction.

Keywords: Infant apnea; Machine learning; Monitoring devices; Respiratory control; Signal processing; Statistical modeling; Stochastic resonance.