RESUMO
BACKGROUND: Hypoxic-ischemic encephalopathy (HIE) appears in neurological conditions where some brain areas are likely to be injured, such as deep grey matter, basal ganglia area, and white matter subcortical periventricular áreas. Moreover, modeling these brain areas in a newborn is challenging due to significant variability in the intensities associated with HIE conditions. This paper aims to evaluate functional measurements and 3D machine learning models of a given HIE case by correlating the affected brain areas with the pathophysiology and clinical neurodevelopmental. CASE PRESENTATION: A comprehensive analysis of a term infant with perinatal asphyxia using longitudinal 3D brain information from Machine Learning Models is presented. The clinical analysis revealed the perinatal asphyxia diagnosis with APGAR <5 at 5 and 10 minutes, umbilical arterial pH of 7.0 BE of -21.2 mmol / L), neonatal seizures, and invasive ventilation mechanics. Therapeutic interventions: physical, occupational, and language neurodevelopmental therapies. Epilepsy treatment: vagus nerve stimulation, levetiracetam, and phenobarbital. Furthermore, the 3D analysis showed how the volume decreases due to age, exhibiting an increasing asymmetry between hemispheres. The results of the basal ganglia area showed that thalamus asymmetry, caudate, and putamen increase over time while globus pallidus decreases. CLINICAL OUTCOMES: spastic cerebral palsy, microcephaly, treatment-refractory epilepsy. CONCLUSIONS: Slight changes in the basal ganglia and cerebellum require 3D volumetry for detection, as standard MRI examinations cannot fully reveal their complex shape variations. Quantifying these subtle neurodevelopmental changes helps in understanding their clinical implications. Besides, neurophysiological evaluations can boost neuroplasticity in children with neurological sequelae by stimulating new neuronal connections.
