Predictive analytics is not just about forecasting what might happen. It’s also about detecting the warning signs of bad things that, if we don’t act quickly, might prove catastrophic or highly disruptive.
In the engineering world, for example, many organizations use statistical tools to predict breakdowns and other adverse consequences that might result from faulty design—unless we fix them in time. I’m referring to the widely established discipline of “survival analysis,” also known as “reliability analysis” or “duration analysis.” If you can find patterns of imminent failure or incremental performance degradation, you can implement corrective measures in the nick of time.
This is the art of preventive maintenance, and it is an imperative in many spheres of human activity, including healthcare. Preventive maintenance is, at heart, our ability to interdict potential failures before they become showstoppers. Ideally, the closed remediation loop should conform to established best practices embedded in the underlying big data analytics application platform as “patterns of expertise.”
When it comes to human health, closed-loop preventive remediation can literally spell the difference between life and death. Predictive monitoring of people’s vital signs—on an in-patient or out-patient basis—is the promise of big data analytics in healthcare maintenance. If we can do real-time medical monitoring, apply predictive models and rules to the continuous readings, and execute closed-loop next best actions—such as adjusting dosages or alerting doctors—everyone can breathe easier.
When someone has already suffered an irreversibly life-altering event, such as a traumatic brain injury, predictive maintenance of that impaired state is the best we can hope for. Of necessity, people with traumatic brain injuries must be kept under constant monitoring. In most intensive care units (ICUs), caregivers are only alerted when the patient’s brain pressure crosses a critical threshold. At that point, an instant decision must be made to determine if the alarm is false, if the condition is life-threatening, or if immediate action is needed to prevent brain damage or death. Introduction of predictive responses into the ICU has obvious life-saving potential.
On Wednesday, September 12, I will host an IBM Twitter chat with UCLA and Excel Medical Electronics to discuss how big data analytics can help predict dangerous brain pressure to prevent further damage. The event will take place from 1-2pm ET and use hashtag #IBMDataChat. Joining me will be Neil A. Martin, MD, FAANS Professor & W. Eugene Stern Chair, Dept. of Neurosurgery at UCLA; Xiao Hu, Ph.D., Associate Professor, Dept. of Neurosurgery at UCLA; and Lance Burton, General Manager at Excel Medical Electronics.
Drs. Martin and Hu will discuss their research into traumatic brain injuries. In particular, they will highlight how they are applying big data analytics in their research, leveraging the data acquired from bedside monitors and using predictive alarms and decision support tools for physicians and other caregivers in intensive care units.
We look forward to your participation in the Twitter chat. Please use hashtag #IBMDataChat.