Source: University of Helsinki
Summary: Researchers have developed a new software based on machine learning which can evaluate brain’s functional maturity of premature infants.
Late pregnancy is very important for the development of the fetal brain and electrical activity of the brain changes almost every week. The frequency of premature births is one in ten and approximately 50% of all patients in neonatal ICUs are there because of preterm birth. Researchers at the University of Helsinki and the Helsinki University Hospital have developed a new software based on machine learning which can independently interpret EEG (Electroencephalography) signals and evaluate brain’s functional maturity in premature infants. The study was published in the journal Scientific Reports.
This brain maturity evaluation system based on EEG is the first of its kind in the world. This method is more precise in comparison to the current methods which enables the automatic and objective monitoring development of a premature infant’s brain. This analysis software is based on machine learning. When a large amount of EEG data of preterm infants was fed into the computer, then the software calculated hundreds of computational features without doctor’s intervention. Along with the support of a vector machine algorithm these features are combined to produce a valid estimate of the EEG maturational age of the infant.
Professor Sampsa Vanhatalo said, “We currently track the development of an infant’s weight, height and head circumference with growth charts. EEG monitoring combined with automatic analysis provides a practical tool for the monitoring of the neurological development of preterm infants and generates information which will help plan the best possible care for the individual child” and further added “This method gives us a first-time opportunity to track the most crucial development of a preterm infant, the functional maturation of the brain, both during and after intensive care.”
More Information: N. J. Stevenson et al. “Functional maturation in preterm infants measured by serial recording of cortical activity”, Scientific Reports (2017). DOI: 10.1038/s41598-017-13537-3