Content area
Full Text
Articles Clinical Investigation
nature publishing group
Predicting 2-y outcome in preterm infants using early multimodal physiological monitoring
RhodriO.Lloyd1,2, JohnM.OToole1, VickiLivingstone1, WilliamD.Hutch1, ElenaPavlidis1,2, Anne-MarieCronin3, EugeneM.Dempsey1,2, PeterM.Filan1,2 and GeraldineB.Boylan1,2
BACKGROUND: Preterm infants are at risk of adverse outcome. The aim of this study is to develop a multimodal model, including physiological signals from the rst days of life, to predict 2-y outcome in preterm infants.
METHODS: Infants <32wk gestation had simultaneous multi-channel electroencephalography (EEG), peripheral oxygen saturation (SpO2), and heart rate (HR) monitoring. EEG grades were combined with gestational age (GA) and quantitative features of HR and SpO2 in a logistic regression model to predict outcome. Bayley Scales of Infant Development-III assessed 2-y neurodevelopmental outcome. A clinical course score, grading infants at discharge as high or low morbidity risk, was used to compare performance with the model.
RESULTS: Forty-three infants were included: 27 had good outcomes, 16 had poor outcomes or died. While performance of the model was similar to the clinical course score graded at discharge, with an area under the receiver operator characteristic (AUC) of 0.83 (95% condence intervals (CI): 0.690.95) vs. 0.79 (0.660.90) (P = 0.633), the model was able to predict 2-y outcome days after birth.
CONCLUSION: Quantitative analysis of physiological signals, combined with GA and graded EEG, shows potential for predicting mortality or delayed neurodevelopment at 2 y of age.
Of the 15 million premature births worldwide each year, one to three million infants will die, approximately 1012% will
develop cerebral palsy and a further 19% will develop motor or cognitive problems (1,2). Accurate and early prediction of neurodevelopmental outcome in the preterm infant provides important clinical information that can be used to guide early intervention, assist clinical management, and ensure appropriate long-term needs are identied. Predicting outcome at 2 y or more, in the rst few days aer birth is ambitious however, as preterm infants are vulnerable to brain injury during their entire stay in the neonatal intensive care unit (NICU) (3).
Many studies have attempted to predict short-term outcome, within the NICU period. Early clinical information, including Apgar scores, gender, birth weight (BW), gestational age
(GA) (47), and illness severity scores, such as SNAP-II and SNAPPE-II have been used to predict short-term outcome (8). Quantitative analysis of multiple risk...