A group of researchers led by Dr Carolyn McGregor, a University of Ontario Institute of Technology (UOIT) associate professor, are to use software developed at IBM Research to build a system that will help doctors detect subtle changes in the condition of critically ill premature babies.
The IBM software will be used to process a constant stream of biomedical data, such as heart rate and respiration, along with environmental data, on and around the babies. The software will then be used to analyse the data so that doctors treating the sick children will be able to predict potential changes in an infant’s condition with greater accuracy.
Physicians in neonatal intensive care units (NICU) at Toronto’s Hospital for Sick Children and two other international hospitals are participating in the research.
Monitoring premature babies as a patient group is especially important as certain life-threatening conditions such as infection can be detected up to 24 hours in advance by observing changes in physiological data streams. But currently, physicians monitoring them rely on manually looking at the readings from various monitors and getting feedback from the nurses providing care.
By developing the new system, McGregor hopes to be able to provide medical staff with an early warning system that could identify patterns from the data collected from the child to predict a medical event.
Initially researchers will use NICU medical devices in UOIT’s Health Informatics Laboratory to test the IBM software using simulated patient data. Then the software will be tested using actual patient data. The data is recorded in a way that enables researchers to alter some variables, play it back and run simulations for further study.
IBM awarded McGregor access to the prototype software, patented by researchers at its TJ Watson research facility in New York, under its ‘First of a Kind’ programme, which is designed to accelerate the delivery of innovative technologies to the market and link IBM’s research work to real-world problems.