Preterm babies are at risk of reduced heart function, leading to vital organ injuries. Routine monitoring only detects the low blood pressure and cardiac dysfunction after it has occurred and produced vital organ injuries. There is thus an urgent need to develop new predictive markers, to enable early detection and treatment.
Associate Professor Flora Wong and team aims to predict cardiac dysfunction in preterm babies, by measuring heart rate variability (HRV) at the cotside, and applying deep learning (advanced machine learning) to develop the predictive model.
HRV detects early subtle heart rate changes in response to disease development, and these changes can be used to predict cardiac dysfunction. Heart rate is routinely monitored on cotside monitors. The team will calculate HRV in real-time, and apply deep learning to develop the most accurate predictive model for cardiac dysfunction in preterm babies.
The novel predictive monitoring in preterm babies will allow early detection and personalised treatment of cardiac dysfunction, therefore reducing the risk of organ injuries.
Last updated01 April 2022