UCLA, IBM team to use big data to prevent brain swelling

Tools

Researchers at the University of California Los Angeles are using an experimental software system that uses big data analytics to test the effectiveness of a real-time alarm designed to predict the development of brain swelling in trauma cases.

The system--the result of a partnership between physicians in the UCLA Department of Neurosurgery and IBM and Excel Medical Electronics--analyzes in real time the vital signs obtained from a patient's bedside monitor in order to detect changes in the patient's pulse, blood and intracranial pressure, heart activity and respiration.

Current alarm systems are designed to alert caregivers when these vital signs pass a critical threshold, forcing physicians into action if the condition is considered to be life threatening or could cause brain damage.

With this experimental system, the UCLA researchers will evaluate the information coming from the bedside monitors in order to identify key physiological patterns that can help physicians predict when a brain pressure event will occur so they can take preventive action in a timely manner.

In an article in the Financial Times, Nagui Halim, IBM's chief architect of big data, explained that the technology can be understood by comparing the patient to the author of a book. Computer scientists will analyze data after its been compiled, much in the same way that an individual will scan a book(s) for keywords. In this case, Halim said, "we do the analysis as the word is being typed." IBM's InfoSphere Streams software analyzes and shares data in motion, while Excel Medical Electronics BedmasterEx analytics software collects, stores, reviews and distributes patient data from hospital monitors and bedside devices.

Halim added that in the future, doctors may be able to make predictions about medical events based on evaluating data from a patient's medical history, in the same way that a scholar can evaluate how an authors develops plots and characters based on his previous books.

"The field of big data analytics is evolving to include new kinds of data from sources such as medical monitors, giving us insights into patients that weren't previously possible," said Martin Kohn, M.D., chief medical scientist, IBM Research, in an announcement. "We believe that UCLA's promising research may one day transform the way that doctors and nurses interact with patients inside the neuro-intensive care unit."

"This is not the cure for brain injury," Brent Masel, M.D., the medical director of the Transitional Learning Center in Galveston, Texas, said, according to the Financial Times article. "Bit it will make a much more significant impact on brain injury recovery. It will make what we do more accurate and more meaningful.

To learn more:
- read the announcement
- see the Financial Times article

Related Articles:
Bedside technology separates strokes from benign dizziness
Neural imaging shows how human brain adapts to trauma
Predictive tool helps ID at-risk trauma patients
Personalized mobile technologies, big data driving health into the future
Genetics-based personalized medicine gets big data boost
EHR data-mining using NLP can improve cancer pain management