Advanced analyses of physiological signals in the neonatal intensive care unit.

Management and monitoring of infants within the neonatal intensive care unit represents a unique challenge. It involves an array of life-threatening diseases, procedures with potentially lifelong impacts, co-morbidities associated with preterm birth and risk of infection from prolonged exposure to the hospital environment. With the integration of monitoring systems and increasing accessibility of high-resolution data, there is a growing interest in the utility of advanced data analyses in predictive monitoring and characterising patterns of disease. Such analyses may offer an opportunity to identify infants at high risk of certain conditions and to detect the onset of disease prior to manifestation of clinical signs. This allows caregivers more time to respond and mitigate any abnormal or potentially fatal changes. We review techniques for variability analysis as they have been or have the potential to be applied to neonatal intensive care, the disease conditions in which they have been tested, and technical as well as clinical challenges relevant to their application.