By Jane Clabby

Researchers at The State University of New York (SUNY) Buffalo are using IBM analytics to create algorithms to analyze big data containing genomic datasets to discover factors that contribute to the progression of multiple sclerosis (MS). By studying more than 2000 genetic and environmental factors, researchers hope to identify trends in MS patients that can be used to improve treatment and slow the cognitive, physical and brain impairments caused by MS.

According to IBM, the breadth of clinical data including medical records, lab reports, and test results combined with individual patient data including characteristics such as gender, diet, exercise, sun exposure and living and working conditions would take researchers days to analyze and correlate to find any meaningful patterns. But by using Big Data analytics, both structured and unstructured patient and clinical data can be sorted and analyzed in minutes, allowing researchers to look at trends and patterns in the data rather than focusing on the data itself.

Researchers at SUNY Buffalo are using IBM Netezza, a purpose-built, standards-based data warehouse appliance based on IBM BladeCenter technology that integrates database, server, storage, and analytics software into a single, easy-to-manage system. Also part of the solution is software from an IBM partner, Revolution Analytics, a leading commercial provider of software and services based on the open source R programming language designed for statistical computing and data analysis.

For complex medical conditions such as MS, analytics are the best way to look for subtle differences in a patient’s history and symptoms that explain, for example, why one patient’s condition worsens at a different rate than another patient with similar symptoms. The goal is to individualize and personalize treatment based on a thorough understanding of the patient and all factors relating to their condition. Analytics can be used in the same way in other industries. For example, in retail, understanding a person’s buying patterns, preferences, and response to sales and promotions can help on-line retailers target consumers with individual offers that are based on information learned about their specific buying habits.