Artificial intelligence (AI) is a wonderful thing. New software based on machine learning (ML) has been developed by researchers from the University of Helsinki and the Helsinki University Hospital (HUH) that can produce an estimate of a premature infant’s brain maturity using EEG signals. It’s a major breakthrough as is the first of its kind in the world.
The new software is far more precise than any other method out there that can evaluate the development of an infant’s brain. “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,” states leader of the research, Professor Sampsa Vanhatalo from the University of Helsinki. “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.”
Unfortunately, premature births happen quite often. As many as one in ten live births is a premature one. In the later stages of pregnancy, brain development within the fetus is rapid and changes happen almost weekly. In order to develop correctly, the brain must be able to function first. Various health issues connected with preterm birth can slow brain development. Previous research carried out in the 1980s revealed that early health problems in preterm infants often led to slower brain development in the first few months.
If we are to try and develop new forms of treatment we need to first understand how brain functions in infants develop. EEG sensors are the most obvious choice for evaluating the maturation of the brain as are low-cost, non-invasive, and have gained a lot of credibility over the past few years. However, according to Vanhatalo, “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.”
While the new software was primarily developed by Australian engineer, Nathan Stevenson, with the help of a few others. The EEG measurement data from preterm infants was gathered previously by Professor Katrin Klebermass’ research group at the Medical University of Vienna. Using machine learning techniques the software was able to calculate several features of each measurement without the need for any doctors. By combining these features (with the help of a support vector machine algorithm), the computer was able to generate an accurate estimate of the EEG maturation age of the infant.
Results from the study demonstrated that in over 80% of cases the infant’s real age and that which the computer predicted was within two weeks of one another.
More News to Read