Database Reference
In-Depth Information
reduce tax and call-routing fees by using the greater volume of granular data
to defend against false claims. To top it off, T-Mobile has been able to increase
network availability by identifying and fixing network bottlenecks and
congestion issues whenever they arise.
State University of New York: Using Analytics
to Help Find a Cure for Multiple Sclerosis
The State University of New York (SUNY) at Buffalo is home to one of the
leading multiple sclerosis (MS) research centers in the world. MS is a devas-
tating, chronic neurological disease that affects nearly one million people
worldwide. The SUNY team has been looking at data obtained from scanned
genomes of MS patients to identify genes whose variations could contribute
to the risk of developing MS. Their researchers postulated that environmen-
tal factors, along with genetic factors, determine a person's MS risk profile.
SUNY's goal was to 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, and living and working conditions. Their data
sources for this analysis included medical records, lab results, MRI scans,
and patient surveys; in short, a wide variety of data in enormous volumes.
The data sets used in this type of multivariable research are very large, and
the analysis is computationally very demanding because the researchers are
looking for significant interactions among thousands of genetic and environ-
mental factors. The computational challenge in gene-environmental interaction
analysis is due to a phenomenon called
combinatorial explosion
. Just to give
you a sense of the number of computations necessary for data mining in this
scenario, think about a 1 followed by 18 zeroes (we're talking
quintillions
here)!
SUNY researchers wanted to not only see which variable is significant to
the development of MS, but also which combinations of variables are signifi-
cant. They decided to use Netezza as their data platform. By using Revolu-
tion R Enterprise for Netezza, in conjunction with the IBM Netezza Analytics
system, they were able to quickly build models using a range of variable types
and to run them against huge data sets spanning more than 2,000 genetic and
environment factors that might contribute to MS. This solution helped the
SUNY researchers to consolidate all reporting and analysis into a single
