Risk of learning difficulties can be predicted earlier in very premature babies — study

The researchers in Cork and Sweden were able to identify 93% of surviving very preterm (VPT) infants who would later screen positive for cognitive difficulties at 24 months. 

New research has found that the risk of impaired cognition for babies who are born very preterm can be predicted before they have been discharged from hospital.

Children who are born before 32 weeks are at a high risk of having learning difficulties at school age but it is currently difficult to predict at an individual level who is most at risk. A new study conducted by researchers in Cork and Sweden has identified the most important risk factors for delayed cognitive development.

Using this, the team was able to identify 93% of surviving very preterm (VPT) infants who would later screen positive for cognitive difficulties at 24 months. 

Currently, the process to predict cognitive difficulties in VPTs takes longer and is considered highly resource-intensive. It begins in the hospital but also requires frequent visits to the families in their homes.

By predicting the risk at an early stage it means that doctors will know which children will benefit the most from preventative interventions.

The study found that in addition to known risk factors such as low birth weight, male gender and neonatal cerebral hemorrhage, prolonged ventilator treatment and lack of breastfeeding at discharge from neonatal care were identified as important risk factors. 

Chair in Early Brain Injury and Cerebral Palsy, Professor Deirdre Murray said: "We need to improve our ability to predict those preterm children who are at highest risk of learning difficulties down the line.

"Improved early prediction will ensure that they have targeted follow-up and will help us to find effective early interventions.” 

Lead researcher of the study, Professor Mikael Norman, said the prediction tool aims to make the necessary interventions accessible for everyone.

"There is effective help available today, but it is often very resource-intensive and therefore may not be available to everyone. Therefore, new prediction tools like the one we developed are needed."

The data used in the research, which involved data from 1,062 VPTs, came from routinely collected information from pregnancy, birth, and early life.

Researchers from the Irish Centre for Maternal and Child Health Research (INFANT) at University College Cork, and Karolinska Institutet, Sweden, examined data from the Swedish Neonatal Quality Registry.

Machine learning (AI) expertise of the INFANT centre was combined with the world-leading perinatal databases in Sweden to identify the most important risk factors.