University project to help premature babies

DURHAM -- More critically ill premature babies could be saved through a joint research project with the University of Ontario Institute of Technology (UOIT).

The project, intended to help detect subtle changes in the condition of premature babies, was recently announced by the UOIT, which is collaborating with IBM and Canadian hospitals for the venture. Physicians at Toronto's Hospital for Sick Children and two other international hospitals are also participating in the study.

"This research has the potential to greatly impact neonatal care through reduced mortality and morbidity rates and overall health-care costs," said Doctor Carolyn McGregor, UOIT associate professor and Canada research chairwoman in health informatics.

For the project, she leads a group of researchers in using advanced stream computing software to work toward enhancing doctors' decision-making capabilities.

Developed by IBM Research, the software uses a constant stream of biomedical data, such as heart rate and respiration, along with environmental information gathered from advanced sensors and more traditional monitoring equipment on and around the babies.

Researchers will also use the software to apply findings from Dr. McGregor's body of research to help make sense of the data and, in near-real-time, feed back the resulting analysis to health-care professionals so they can predict potential changes in an infant's condition with greater accuracy and intervene more quickly.

Currently, physicians monitoring premature babies rely on a paper-based process that involves manually looking at the readings from various monitors and getting feedback from the nurses providing care.

When fully developed, IBM's software will be capable of processing the 512 readings per second generated by some of these medical devices and UOIT researchers will further test and develop its ability to analyze these vast quantities of data in real time.

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.

Initially researchers will use neonatal intensive care unit medical devices in UOIT's health informatics laboratory to test IBM's software using simulated patient mirroring data. Then the software will be tested using patient data, recorded in a way that enables researchers to alter some variables, play it back and run simulations for further study.

---