The IBM Analytics technology is being put to good use at the State University of New York (SUNY), Buffalo, where researchers are using it to study environmental and genetic factors that may contribute to Multiple Sclerosis (MS). The researchers will develop algorithms for big data to study over 2,000 factors that will uncover such things as their effect on MS speed of progression as well as help gain insight into individual treatments. It is hoped that these genomic datasets will be used to create treatments that help slow brain damage, physical and cognitive impairments on MS patients.

Revolution Analytics, an IBM (News - Alert) business partner has provided the software that will be used with the IBM Netezza analytics appliance to analyze the large and disparate amount of data that would otherwise have taken days to analyze. The technology frees up researchers from managing data so they can focus more on analyzing trends. SUNY researchers have been studying MS since 2007 have so far been at the forefront in gathering clinical and historical data on the disease.

According to the lead researcher at SUNY, Dr. Murali Ramanathan, MS is a complex, debilitating disease with no cure. No two people display the same exact symptoms and symptoms can worsen unexpectedly. Analyzing all the common trends is thus much like trying to shoot a speeding bullet with another bullet out of the sky. By use of IBM analytics, it will be easier to “fine tune the aim and match the speed of analysis with the rate of data coming into the systems.” Dr. Murali said that the goal is simply to demystify why the disease progresses differently in each patient and thus help find new treatments.

According to the GM, healthcare and life sciences at IBM, Dan Pelino, “The work at SUNY is a prime example of how IBM clients are literally changing the world with big data analytics, from advancing medical research, to generating clean energy and giving consumers what they want before they know they want it.” The IBM Netezza (News - Alert) appliances being used in the research is based on the IBM BladeCenter technology that is able to analyze petabytes of data at a low cost of ownership.