The fetal brain grows and develops all the way from the ninth week of pregnancy up until even after birth, and during this time undergoing incredible changes in morphology and function. But preterm infants, those born before the 37-week gestation, are at a risk of brain complications and damage, as found in previous studies.
It is unfortunate that the cases of premature births are not uncommon in that they occur in one out of ten live patients and account for almost half of the admissions to the neonatal intensive care unit (NICU) per year. For these reasons, effectively overseeing and keeping a constant check on the brain maturation of infants has become an important tool.
At the University of Helsinki and Helsinki University Hospital, Finland, scientists have developed a technique that can determine an infant’s brain maturity during the late pregnancy stage by way of interpretive electroencephalogram (EEG) signals. In the paper published in Scientific Reports, it has been described as the world’s first EEG-based brain maturity evaluation system. Compared to earlier approaches of monitoring cerebral development, with the help of sensors placed on the scalps of neonates, this is believed to be a more precise and objective assessment technique.
Lead investigator, Prof. Sampsa Vanhatalo said, “The practical problem with EEG monitoring is that analyzing the EEG data has been slow and required special expertise from the doctor performing it. This problem may be solved reliably and globally by using automatic analysis as part of the EEG device.” He also mentioned that: “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.”
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. Credit: University of Helsinki
How Machine Learning Can Help Preterm Infants
101 serial EEG recordings from 39 infants (less than 28 weeks old scheduled for normal neurodevelopmental outcomes) when entered into a software on the computer, along with the support vector algorithms, were able to derive several computational features from the measurements taken, without a doctor’s presence. At the end, with maturational age of infants kept as a standard, the EEG estimation versus the known age was compared.
Results showed an 80% accuracy, meaning that the age deviation was just within two weeks, which proved that the computer-generated maturation numbers were reliable. The brains’ development was then continuously tracked and measurements taken over the next few weeks.
“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”, said the research team, about the method involved.
The automated estimate of EMA (EEG maturational age) of preterm infants shows great promise in the world of medicine and healthcare, and let us all hope, in the future, it can change the fate of the risks surrounding premature babies too.
Top image: Evaluate brain maturity of preterm infants. (University of Helsinki)
References:
Lehtinen, P. (2017), University of Helsinki, https://www.helsinki.fi/en/news/health/artificial-intelligence-to-evaluate-brain-maturity-of-preterm-infants, (accessed 17 Nov 2017)
Wilson, S. (2017), Health Informative, http://www.healthinformative.com/news-research/artificial-intelligence-evaluate-brain-maturity-preterm-infants/, (accessed 17 Nov 2017)
Stiles, J. (2010), ‘The Basics of Brain Development’, Neuropsychol Rev., 20 (4), Pp 327-348
Stevenson, N. J. et al. (2017), ‘Functional maturation in preterm infants measured by serial recording of cortical activity’, Scientific Reports, 7 (12969)
No comment