| Table of Contents: |
Data Baby: 24-Hour
Head's Up on Preemie Problems
With premature babies, even the slightest variation in biomedical readings such as heart rate can signal a turn for the worse. Many such changes are often early warning indicators of more serious problems to come. Unfortunately, physicians and nurses usually have too much data from a variety of sources to pick out the true indicators from simple variations.
Currently, physicians monitoring preemies rely on a paper-based process that involves manually looking at the readings from various monitors and getting feedback from the nurses providing care.
To improve this process, IBM and the University of Ontario Institute of Technology are collaborating on a research project to help doctors detect subtle yet important changes. The project makes use of advanced stream-computing software that ingests a constant flow of biomedical data, such as temperature and respiration. It also monitors environmental data gathered from advanced sensors and more traditional monitoring equipment on and around the babies. To put the data volume into perspective, some of the monitoring devices collect thousands of pieces of information per second.
Using advanced analytics on the streaming data, the project hopes to be able to detect certain life-threatening conditions, such as infection, up to 24 hours in advance by observing changes in physiological data streams.
Which of these projects are you most excited about? Sound off in the comments section below.

