Predicting brain damage with Hadoop big data

For several years now, Hadoop big data tools have provided companies with an open platform to pursue many ambitions. Although big data rose to prominence because of its ability to enhance marketing campaigns, organizations from numerous sectors have been finding new and exciting applications for the technology. Some of the most impressive developments in the data analytics field has come from the healthcare industry. Physicians have begun to leverage big data tools to diagnose patients as well as screen others for chronic illnesses. Recent developments in the field have gone one step further.

Brain injuries by the numbers
Traumatic brain injuries (TBI) are a matter of serious concern in the United States. According to data gathered by the Centers for Disease Control and Prevention, 1.7 million cases of TBI are recorded each year. In nearly half of those cases, the patient is reported to be a child under the age of 14. TBI has also been identified as a contributing factor in approximately 30 percent of the nation's injury-related deaths.

Patients at risk for TBI receive constant surveillance from brain activity monitoring equipment, but hospital staff is only notified of fluctuations in intracranial pressure if it reaches a critical level. At that point, the damage could be irreversible. 

Predicting harmful changes in brain pressure
Forbes contributor Tom Groenfeldt reported that neurologists at the UCLA Medical Center were collaborating with IBM research teams to better identify intracranial pressure changes with the help of data analytics. IBM has provided a potential solution to this problem with its InfoSphere Streams software, which is powered by Apache Hadoop technology. This analytics tool can process a range of medical information including EEK, EKG, genomics and treatment history to see health patterns that cannot be seen with traditional methods.

"We can see where early indicators are that something is not right, so the doctors can get it as early as possible," Nagui Halim, IBM's chief architect of big data, told Groenfeldt. "Nothing happens suddenly in medicine, it only seems sudden. Conditions increase risk, certain factors are stressing the system, but it has antecedents."

With that information in hand, critical intracranial pressure changes can be identified before a patient exhibits symptoms, allowing medical staff to intervene and prevent further damage. A Toronto neonatal facility has already utilized IBM's Hadoop data analytics tools. The software was reportedly able to alert medical staff to patient health problems as much as 24 hours before traditional forms of monitoring would have recognized them. The healthcare industry is quickly realizing that big data can save lives.

Categorized by :

Leave a Reply

Your email address will not be published. Required fields are marked *

Hortonworks Data Platform
The Hortonworks Data Platform is a 100% open source distribution of Apache Hadoop that is truly enterprise grade having been built, tested and hardened with enterprise rigor.
Get started with Sandbox
Hortonworks Sandbox is a self-contained virtual machine with Apache Hadoop pre-configured alongside a set of hands-on, step-by-step Hadoop tutorials.
Modern Data Architecture
Tackle the challenges of big data. Hadoop integrates with existing EDW, RDBMS and MPP systems to deliver lower cost, higher capacity infrastructure.