Analytics technology helps with MS research
Data Dude - 86.48 Kb
Researchers from the State University of New York (SUNY) at Buffalo are using IBM analytics technology to study more than 2,000 genetic and environmental factors that may contribute to multiple sclerosis (MS) symptoms.

Using an IBM Netezza analytics appliance with software from IBM business partner, Revolution Analytics, SUNY Buffalo researchers can, for the first time, explore clinical and patient data to find hidden trends among MS patients by looking at factors such as gender, geography, ethnicity, diet, exercise, sun exposure, as well as living and working conditions. The big data, which includes medical records, lab results, MRI scans and patient surveys, arrives in various formats and sizes, requiring researchers to spend days making it manageable before analysis.  

Previously, the computations associated with this kind of data analysis would take researchers days or even weeks.”Once we developed the algorithms, they ran so much faster we were able to do things we couldn’t previously,” said Murali Ramanathan, PhD, lead researcher at SUNY Buffalo, in an interview.

MS is a chronic neurological disease for which there is no cure. The disease is believed to be caused by a combination of genetic, environmental, infectious and autoimmune factors making it treatment difficult. According to the National Multiple Sclerosis Society, there are approximately 400,000 people in the U.S. with MS, and 200 people are diagnosed every week. Worldwide, MS is estimated to affect more than 2.1 million people.

“Multiple sclerosis is a debilitating and complex disease with an unknown cause. No two people share the exact same symptoms, and individual symptoms can worsen unexpectedly,” said Ramanathan. “Identifying common trends across massive amounts of data related to the disease is a monumental task that is much like trying to shoot a speeding bullet out of the sky with another bullet. Our goal is to demystify why the disease progresses more rapidly in some patients and get those insights back to other researchers, so they can find new treatments.”

Ramanathan and his colleagues are focusing specifically on gene-environment interactions and how they relate to MS. “In MS, no single gene or environmental factor explains the risk of developing the disease. As a result, we don’t have a good understanding of what causes MS,” he said. “We know that genes don’t act alone. They act by interacting with other genes and gene products as well as environmental factors.”

Since 2007, SUNY Buffalo researchers have been at the forefront of studying clinical and historical data from MS patients to identify genetic and environmental factors that contribute to the risk of developing the disease. These researchers are studying different age groups to see why the disease appears early in some children and why people who are diagnosed later in life tend to have a more aggressive course that affects their ability to walk. They are also looking at why MS is more common in northern latitudes and less common towards the equator, calling into question the role sunlight or lack thereof plays in the disease.

Many of the metrics techniques developed at SUNY Buffalo are generalizable to other diseases, Ramanathan said, and “we use datasets from many other diseases to test and validate our algorithms.”

The hope, according to Ramanathan, is that by identifying critical gene-gene and gene-environment interactions, MS researchers would have two advantages: the ability to translate findings directly to the bedside to provide rational guidance to patients and, at the other end of the care continuum, identify drug targets.