Integration of Early Physiological Responses Predicts Later Illness Severity in Preterm Infants

Abstract

Physiological data are routinely recorded in intensive care, but their use for rapid assessment of illness severity or long-term morbidity prediction has been limited. We developed a physiological assessment score for preterm newborns, akin to an electronic Apgar score, based on standard signals recorded noninvasively on ad- mission to a neonatal intensive care unit. We were able to accurately and reliably estimate the probability of an individual preterm infant’s risk of severe morbidity on the basis of noninvasive measurements. This prediction algorithm was developed with electronically captured physiological time series data from the first 3 hours of life in preterm infants (≤34 weeks gestation, birth weight ≤2000 g). Extraction and integration of the data with state- of-the-art machine learning methods produced a probability score for illness severity, the PhysiScore. PhysiScore was validated on 138 infants with the leave-one-out method to prospectively identify infants at risk of short- and long-term morbidity. PhysiScore provided higher accuracy prediction of overall morbidity (86% sensitive at 96% specificity) than other neonatal scoring systems, including the standard Apgar score. PhysiScore was particularly accurate at identifying infants with high morbidity related to specific complications (infection: 90% at 100%; cardiopulmonary: 96% at 100%). Physiological parameters, particularly short-term variability in respiratory and heart rates, contributed more to morbidity prediction than invasive laboratory studies. Our flexible methodology of individual risk prediction based on automated, rapid, noninvasive measurements can be easily applied to a range of prediction tasks to improve patient care and resource allocation.

Predictive monitoring for sepsis and necrotizing enterocolitis to prevent shock

“…Although these illness severity scores are likely to be high in infants with early-onset sepsis and shock in the first day after birth, they have not been shown to predict later development of sepsis or NEC. A score incorporating gestational age, birth weight, and mean and standard deviation of heart rate, respiratory rate, and oxygen saturations in the first 3 h after birth was reported to be significantly associated with development of late-onset sepsis in a study of 138 preterm infants [17]. Low heart rate variability in the first week after birth was also found to be associated with development of NEC in a study of 70 preterm infants [18].…”

Predicting 2-y outcome in preterm infants using early multimodal physiological monitoring

“…Quantitative analysis of multiple risk factors combined in a multivariate model can improve outcome prediction (7). Saria et al (9) showed that a combination of quantitative features of early physiological measurements, including heart rate (HR), respiratory rate (RR), and peripheral oxygen saturation (SpO 2 ), could predict short-term outcome with a high level of accuracy (sensitivity of 86% and specificity of 96%). The absence of a reliable measure of neurological function, however, may limit the ability of these approaches to predict neurodevelopment in the longer term, beyond the early intensive care stage.…”

“…The multimodal model combines EEG grading with quantitative features of routinely-available physiological signals, namely SpO 2 and HR (9). A clinical course score, which represents a best estimate of long-term outcome from clinical history of the intensive care period, is used to compare performance of this multimodal approach.…”

Genomic technologies in neonatology

“…Иными словами, области трансляционной биоин-форматики отведена роль «мостика» между знаниями фундаментальных исследователей и врачей-клини-цистов, чтобы «принести инновации с лабораторно-го стола к постели пациента» («link innovations from bench to bedside») [51,52]. В частности, в Госпитале для больных детей (The Hospital for Sick Children) в Торонто (Канада) был осуществлен пилотный проект анализа жизненных показателей в режиме реального времени [53], а в другой работе было про-демонстрировано, что паттерны данных жизненных показателей могут помочь прогнозировать как кратко-срочную, так и долгосрочную заболеваемость у недо-ношенных детей [54].…”