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

Abstract

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 first days of life, to predict 2-y outcome in preterm infants.

Methods: Infants <32 wk 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% confidence intervals (CI): 0.69-0.95) vs. 0.79 (0.66-0.90) (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.