PREDICTION OF OUTCOME WITH MACHINE LEARNING IN INFANTS.
At the neonatal intensive care unit of UMC Utrecht, up to 80 newborns per year are born extremely preterm (<28 weeks of gestation), with high risk for brain damage and long-term consequences such as behavioral impairment. There is a need for early personalized prognosis of behavioral outcomes for the individual patient.
The vulnerability of the preterm brain is due to the major transformations happening the last extrauterine trimester of gestation, with a peak in neuroplasticity providing also a precious window of opportunity for early interventions to reduce injury. These interventions should be initiated as early as possible in at-risk infants to reduce the risk of a neurodevelopmental disability. Therefore, we need an early personalized prognosis of behavioral outcomes for the individual patient. Developing these precise, personalized prognoses for outcomes in neonates with brain damage is complex.
About the project
PROMISE: PRediction of Outcome with Machine Learning in Infants: a Synergistic Exploration
Mykola Pechenizkiy (TU/e), Rick Bezemer (TU/e), Clara Belzer (WUR), Chantal Kemner (UU), Albert Salah (UU), Maria Luisa Tataranno (UMC Utrecht), Manon Benders (UMC Utrecht), Bauke van der Velde (UMC Utrecht), Bob Walraad (UMC Utrecht)
This research project aims to develop a prediction model for preterm born infants at high risk of behavioural impairment. And to ensure that this is conform to the state-of-the-art values of trustworthy AI. Once validated, this prediction model will be made accessible to a larger network of clinicians through a web-based service.