RESUMEN
BACKGROUND: The aim of this study was to understand how neurological development of preterm infants can be predicted at earlier stages and explore the possibility of applying personalized approaches. METHODS: Our study included a cohort of 64 preterm infants, between 24 and 34 weeks of gestation. Linear and nonlinear models were used to evaluate feature predictability to Bayley outcomes at the corrected age of 2 years. The outcomes were classified into motor, language, cognitive, and socio-emotional categories. Pediatricians' opinions about the predictability of the same features were compared with machine learning. RESULTS: According to our linear analysis sepsis, brain MRI findings and Apgar score at 5th minute were predictive for cognitive, Amiel-Tison neurological assessment at 12 months of corrected age for motor, while sepsis was predictive for socio-emotional outcome. None of the features were predictive for language outcome. Based on the machine learning analysis, sepsis was the key predictor for cognitive and motor outcome. For language outcome, gestational age, duration of hospitalization, and Apgar score at 5th minute were predictive, while for socio-emotional, gestational age, sepsis, and duration of hospitalization were predictive. Pediatricians' opinions were that cardiopulmonary resuscitation is the key predictor for cognitive, motor, and socio-emotional, but gestational age for language outcome. CONCLUSIONS: The application of machine learning in predicting neurodevelopmental outcomes of preterm infants represents a significant advancement in neonatal care. The integration of machine learning models with clinical workflows requires ongoing education and collaboration between data scientists and healthcare professionals to ensure the models' practical applicability and interpretability.
RESUMEN
AIM: To evaluate the relationship between the neurological outcome, neonatal epileptic seizures, and signal-intensity visibility of the frontal and parietal periventricular crossroads of pathways on brain magnetic resonance imaging (MRI) in preterm infants at term-equivalent age. METHODS: The study enrolled 48 preterm infants born between 2012 and 2016. The signal-intensity characteristics of the frontal and parietal periventricular crossroads were evaluated and classified into four grades. A non-favorable outcome was defined as a motor and functional disorder with developmental delay and/or cerebral palsy. RESULTS: Neonatal seizures, epilepsy, pathological EEG and brain ultrasound finding, and brain MRI abnormalities were mostly found in neonates with non-favorable outcomes. Visible frontal and parietal periventricular crossroads were associated with a normal neurologic outcome (P=0.0004; P=0.0009, respectively). Not-visible or slightly visible periventricular crossroads were associated with non-favorable outcomes in the case of frontal crossroads (P=0.036) and not-visible periventricular crossroads in the case of both frontal and parietal crossroads (P=0.001, P=0.015, respectively). The visibility of the frontal and parietal periventricular crossroads was associated with a lack of neonatal epileptic seizures (P=0.03; P=0.02, respectively). The frontal crossroads were more frequently slightly visible, while the parietal periventricular crossroads were more frequently visible. CONCLUSION: Poor visibility of the frontal and parietal crossroads of pathways on MRI is associated with neonatal epileptic seizures and poor neurological outcomes in preterm infants at term-equivalent age.
