IBM Big Data Monitors Patients For Brain Injury

7 Big Data Solutions Try To Reshape Healthcare

The UCLA Department of Neurosurgery in Los Angeles has started testing an experimental system that uses big data analytics software to examine real-time data streams collected from patients' bedside monitors.

Developed by IBM Research and Excel Medical Electronics (EME), a developer of clinical and research software for hospital patient monitoring devices, the system spots subtle changes in vital signs that suggest dangerous increases in brain pressure are imminent.

The software analyzes this streaming data and looks for changes in a patient's pulse, heart activity, blood and intracranial pressure, and respiration, according to IBM.

[ Want to know more about IBM's big data plans? See IBM CEO Rometty Shares Vision Of Big Data Era. ]

"Traditional clinical care involves having nurses and physicians do rounds on the floors in the hospital, looking at instrumentation that has readouts for various instruments," said IBM fellow and big data chief architect Nagui Halim in a phone interview with InformationWeek. "It's a fairly crude process in terms of time and the handoff between (worker) shifts."

The IBM/EME system automates the observational process and ideally can do a better job of examining the patient's condition and drawing conclusions about the person's current and future health.

"It's kind of an online analytic framework that allows the analysis to be done continuously and incrementally," said Halim, "as the patient's signals are coming in real time."

Conventional bedside monitors also check the vital signs of patients with traumatic brain injuries, but only sound an alarm when brain pressure crosses a dangerous threshold. A nurse or doctor must then make a snap judgment, deciding whether the alarm is false or if the condition is life-threatening and requires immediate action.

The UCLA test monitoring system includes IBM's InfoSphere Streams software, which is part of Big Blue's big data platform. The software can analyze and share streaming data, as well as make thousands of real-time decisions every second, the company said.

The other key component is EME's BedMasterEX analytics software, which collects, reviews and distributes patient data from hospital monitors and medical devices. EME worked with researchers at IBM's T.J. Watson Laboratory to integrate its application with IBM's software, and to develop an end-user interface for hospital workers.

"The ability to do continuous, real-time monitoring of patients in a clinical setting, which we're striving for, is potentially transformative for the healthcare business," said Halim.

The UCLA study is underway and will run for an indeterminate length of time, depending on funding. The school's department of neurosurgery has been studying the impact of rising intracranial pressure on brain trauma patients for eight years, according to IBM. It has received a $1.2 million grant from the National Institute of Neurological Disorders and Stroke to conduct the research, which includes developing a predictive alarm system.

The IBM and EME system deftly handles the three defining characteristics of big data: volume, velocity and variety, said Halim.

In the UCLA study, for instance, the system handles real-time streaming data (high velocity) and can accumulate very large amounts of data over time (high volume).

When it comes to variety -- as in different types of unstructured data, such as sensor readings and video -- the IBM/EME platform tackles that too.

"We stream data from all kinds of different sources," said Halim. "We're not doing this at UCLA, but conceivably you could also stream and observe the patient through video, and a multiplicity of environmental things."

Approximately 1.7 million people in the U.S. sustain traumatic brain injury every year, according to the Centers for Disease Control and Prevention. About 52,000 of those individuals die, 275,000 are hospitalized and 1.365 million are treated and released from an emergency care facility.

Attend Interop Las Vegas May 6-10 and learn the emerging trends in information risk management and security. Use Priority Code MPIWK by March 22 to save an additional $200 off the early bird discount on All Access and Conference Passes. Join us in Las Vegas for access to 125+ workshops and conference classes, 300+ exhibiting companies, and the latest technology. Register today!